an open-source alternative to the dots, bots and muses of the world, run an office of claude code/codex like agents on your laptop, sandboxes or anywhere, uses your existing subscriptions
HTML agent-harnessagent-orchestrationagentsai-agentsautonomous-agentsclaude-codecodexcoding-agentsdesktop-appdeveloper-toolselectrongemini-cliharnessharness-engineeringlocal-firstmemorymulti-agentopencodeorchestrationtypescript
blog(mission): 5 founder requested posts with Antigravity images
chaitanyagiri85c82b2172f0
diff --git a/blog/src/_data/media.json b/blog/src/_data/media.jsonindex 792e2996..d6ae8f13 100644--- a/blog/src/_data/media.json+++ b/blog/src/_data/media.json@@ -425,6 +425,31 @@},"youtube": []},+ "claude-code-max-plan-tips": {+ "title": "How to Get the Most Out of Your Claude Code Max Plan",+ "category": "guides",+ "hero": {+ "file": "assets/media/claude-code-max-plan-tips/hero.png",+ "alt": "A yellow cartoon character at a desk with an hourglass, stacked terminal windows, a wall calendar with ticks and a nearly full gauge",+ "prompt": "Generated with Antigravity (gemini-3.1-flash-image) by jim-mu106131, 14 Sep 2026, house style: ink line art, yellow bean, no red, no text.",+ "status": "ready"+ },+ "inline": {+ "note-1": {+ "file": "assets/media/claude-code-max-plan-tips/note-1.png",+ "alt": "An hourglass beside a seven day strip with some days filled in",+ "prompt": "",+ "status": "ready"+ },+ "note-2": {+ "file": "assets/media/claude-code-max-plan-tips/note-2.png",+ "alt": "A yellow cartoon character conducting three terminal windows, each with a small bean typing inside",+ "prompt": "",+ "status": "ready"+ }+ },+ "youtube": []+ },"claude-code-multi-agent-setup-tutorial": {"title": "Set Up a Claude Code Multi-Agent Workflow in 10 Minutes","category": "guides",@@ -625,6 +650,31 @@},"youtube": []},+ "codex-max-plan-tips": {+ "title": "How to Make the Most of Your Codex Max Plan",+ "category": "guides",+ "hero": {+ "file": "assets/media/codex-max-plan-tips/hero.png",+ "alt": "A yellow cartoon character turning a big dial all the way up at a workbench while paper planes fly from a laptop to a cloud",+ "prompt": "Generated with Antigravity (gemini-3.1-flash-image) by jim-mu106131, 14 Sep 2026, house style: ink line art, yellow bean, no red, no text.",+ "status": "ready"+ },+ "inline": {+ "note-1": {+ "file": "assets/media/codex-max-plan-tips/note-1.png",+ "alt": "Parcels travelling between a laptop and a cloud along a dotted path, past a small meter",+ "prompt": "",+ "status": "ready"+ },+ "note-2": {+ "file": "assets/media/codex-max-plan-tips/note-2.png",+ "alt": "A yellow cartoon character reaching for a small screwdriver on a pegboard that also holds a wrench and a sledgehammer",+ "prompt": "",+ "status": "ready"+ }+ },+ "youtube": []+ },"command-center-guide": {"title": "The Command Center: Kanban, Fleet, and Budgets in One Place","category": "guides",@@ -1075,6 +1125,56 @@},"youtube": []},+ "grok-bot-alternatives": {+ "title": "Grok Bot Alternatives: Six Picks, Grouped by What You Want",+ "category": "comparisons",+ "hero": {+ "file": "assets/media/grok-bot-alternatives/hero.png",+ "alt": "A yellow cartoon character with a clipboard at a signpost, choosing between a cloud kiosk, a phone, a laptop desk and a small home server",+ "prompt": "Generated with Antigravity (gemini-3.1-flash-image) by jim-mu106131, 14 Sep 2026, house style: ink line art, yellow bean, no red, no text.",+ "status": "ready"+ },+ "inline": {+ "note-1": {+ "file": "assets/media/grok-bot-alternatives/note-1.png",+ "alt": "Papers locked in a drawer inside a faraway cloud, next to the same papers on a desk beside a laptop",+ "prompt": "",+ "status": "ready"+ },+ "note-2": {+ "file": "assets/media/grok-bot-alternatives/note-2.png",+ "alt": "A yellow cartoon character hands a ring of keys to a small robot helper while keeping one key back, with an open notebook between them",+ "prompt": "",+ "status": "ready"+ }+ },+ "youtube": []+ },+ "herdr-alternatives": {+ "title": "Herdr Alternatives: What to Pick and Who Each One Fits",+ "category": "comparisons",+ "hero": {+ "file": "assets/media/herdr-alternatives/hero.png",+ "alt": "A yellow cartoon character as a shepherd with a crook, herding small terminal windows with legs across a hill",+ "prompt": "Generated with Antigravity (gemini-3.1-flash-image) by jim-mu106131, 14 Sep 2026, house style: ink line art, yellow bean, no red, no text.",+ "status": "ready"+ },+ "inline": {+ "note-1": {+ "file": "assets/media/herdr-alternatives/note-1.png",+ "alt": "A monitor split into terminal panes next to a small office floor with a bean at each desk",+ "prompt": "",+ "status": "ready"+ },+ "note-2": {+ "file": "assets/media/herdr-alternatives/note-2.png",+ "alt": "Four terminal windows showing an hourglass, a spinning gear, a check mark and a sleeping cloud",+ "prompt": "",+ "status": "ready"+ }+ },+ "youtube": []+ },"hire-manifest-untrusted-input": {"title": "Treating a Hire Manifest as Untrusted Input","category": "internals",@@ -2215,6 +2315,31 @@},"youtube": []},+ "omniagent-alternatives": {+ "title": "OmniAgent Alternatives: What to Use Instead of Databricks Omnigent",+ "category": "comparisons",+ "hero": {+ "file": "assets/media/omniagent-alternatives/hero.png",+ "alt": "A yellow cartoon character in a control tower with binoculars, guiding differently shaped robot agents towards one building",+ "prompt": "Generated with Antigravity (gemini-3.1-flash-image) by jim-mu106131, 14 Sep 2026, house style: ink line art, yellow bean, no red, no text.",+ "status": "placeholder"+ },+ "inline": {+ "note-1": {+ "file": "assets/media/omniagent-alternatives/note-1.png",+ "alt": "A power strip with four different plugs, each cable leading to a different small robot",+ "prompt": "",+ "status": "placeholder"+ },+ "note-2": {+ "file": "assets/media/omniagent-alternatives/note-2.png",+ "alt": "A yellow cartoon character with a clipboard beside a rope gate while a robot waits and a long receipt unrolls on the floor",+ "prompt": "",+ "status": "placeholder"+ }+ },+ "youtube": []+ },"one-prompt-automated-pr-review": {"title": "One Prompt, Five PR Reviews, and an Hourly Automation — A Dogfooding Story","category": "story",diff --git a/blog/src/assets/media/claude-code-max-plan-tips/hero.png b/blog/src/assets/media/claude-code-max-plan-tips/hero.pngnew file mode 100644index 00000000..3a5fac77Binary files /dev/null and b/blog/src/assets/media/claude-code-max-plan-tips/hero.png differdiff --git a/blog/src/assets/media/claude-code-max-plan-tips/note-1.png b/blog/src/assets/media/claude-code-max-plan-tips/note-1.pngnew file mode 100644index 00000000..ead298c0Binary files /dev/null and b/blog/src/assets/media/claude-code-max-plan-tips/note-1.png differdiff --git a/blog/src/assets/media/claude-code-max-plan-tips/note-2.png b/blog/src/assets/media/claude-code-max-plan-tips/note-2.pngnew file mode 100644index 00000000..c2a4c450Binary files /dev/null and b/blog/src/assets/media/claude-code-max-plan-tips/note-2.png differdiff --git a/blog/src/assets/media/codex-max-plan-tips/hero.png b/blog/src/assets/media/codex-max-plan-tips/hero.pngnew file mode 100644index 00000000..b3a91c61Binary files /dev/null and b/blog/src/assets/media/codex-max-plan-tips/hero.png differdiff --git a/blog/src/assets/media/codex-max-plan-tips/note-1.png b/blog/src/assets/media/codex-max-plan-tips/note-1.pngnew file mode 100644index 00000000..592d073aBinary files /dev/null and b/blog/src/assets/media/codex-max-plan-tips/note-1.png differdiff --git a/blog/src/assets/media/codex-max-plan-tips/note-2.png b/blog/src/assets/media/codex-max-plan-tips/note-2.pngnew file mode 100644index 00000000..dabcf63aBinary files /dev/null and b/blog/src/assets/media/codex-max-plan-tips/note-2.png differdiff --git a/blog/src/assets/media/grok-bot-alternatives/hero.png b/blog/src/assets/media/grok-bot-alternatives/hero.pngnew file mode 100644index 00000000..dcd5c077Binary files /dev/null and b/blog/src/assets/media/grok-bot-alternatives/hero.png differdiff --git a/blog/src/assets/media/grok-bot-alternatives/note-1.png b/blog/src/assets/media/grok-bot-alternatives/note-1.pngnew file mode 100644index 00000000..fc22af92Binary files /dev/null and b/blog/src/assets/media/grok-bot-alternatives/note-1.png differdiff --git a/blog/src/assets/media/grok-bot-alternatives/note-2.png b/blog/src/assets/media/grok-bot-alternatives/note-2.pngnew file mode 100644index 00000000..b54c2b20Binary files /dev/null and b/blog/src/assets/media/grok-bot-alternatives/note-2.png differdiff --git a/blog/src/assets/media/herdr-alternatives/hero.png b/blog/src/assets/media/herdr-alternatives/hero.pngnew file mode 100644index 00000000..8d258ea5Binary files /dev/null and b/blog/src/assets/media/herdr-alternatives/hero.png differdiff --git a/blog/src/assets/media/herdr-alternatives/note-1.png b/blog/src/assets/media/herdr-alternatives/note-1.pngnew file mode 100644index 00000000..acb115cfBinary files /dev/null and b/blog/src/assets/media/herdr-alternatives/note-1.png differdiff --git a/blog/src/assets/media/herdr-alternatives/note-2.png b/blog/src/assets/media/herdr-alternatives/note-2.pngnew file mode 100644index 00000000..01c20d93Binary files /dev/null and b/blog/src/assets/media/herdr-alternatives/note-2.png differdiff --git a/blog/src/posts/claude-code-max-plan-tips.md b/blog/src/posts/claude-code-max-plan-tips.mdnew file mode 100644index 00000000..a42c9433--- /dev/null+++ b/blog/src/posts/claude-code-max-plan-tips.md@@ -0,0 +1,77 @@+---+title: "How to Get the Most Out of Your Claude Code Max Plan"+description: "Stretch a Claude Code Max plan: model choice, context hygiene, prompt caching, subagents and unattended runs, checked against Anthropic's own pages."+date: 2026-09-14+category: guides+categoryLabel: Guides+type: Technical+primaryKeyword: "how to get the most out of claude max"+secondaryKeywords: ["how to make the most of claude max", "claude code max plan tips", "how to maximize claude code usage", "how to reduce claude code token usage", "claude code usage limit reset", "does claude code max have weekly limits"]+tags: ["Guides", "Claude Code", "Cost", "Workflow"]+faq:+ - q: "Does Claude Code Max have weekly limits?"+ a: "Yes. Every Max plan has a session limit that resets every five hours and a weekly limit across all models that resets at a fixed time assigned to your account, per Anthropic's Max plan article as checked on 14 Sep 2026. Claude chat, Claude Code and the IDE extensions all draw from the same allowance."+ - q: "Does Claude Code Max include Fable?"+ a: "Yes. Anthropic's help article on Fable, updated 2 Sep 2026, says Fable 5 and Fable 5.1 are a standard part of Max, and you can spend up to half of your weekly limit on them at no extra cost. That half is a ceiling inside the same weekly allowance, not extra room. Past it you either pay with usage credits or switch to another model."+ - q: "Is Claude Code Max unlimited?"+ a: "No. Max 5x and Max 20x give five or twenty times Pro's usage per session, and Anthropic says it may limit usage in other ways too. If you turn on usage credits, work past the limit is billed at standard API rates, so decline them if you want to stay inside what the plan includes."+ - q: "When does the Claude Code usage limit reset?"+ a: "The session limit resets every five hours and the weekly limit at a fixed day and time assigned to your account. Run /usage in Claude Code or open Settings > Usage on claude.ai to see both reset times. In an interactive session, Claude Code 2.1.234 and later can wait for a session reset and then continue the task on its own."+ - q: "Can you share a Claude Code Max plan?"+ a: "No. Anthropic's Consumer Terms say you may not share your login or make your account available to anyone else, and its Claude Code legal page says advertised Pro and Max limits assume ordinary, individual use. A team that needs shared capacity should look at Team seats or an API key instead."+---++To get the most out of Claude Max in Claude Code, spend the plan on work, not on rereading context. Pick the model per task, `/clear` between tasks, plan before big edits, keep sessions inside the one hour cache, and watch `/usage` so the weekly limit never surprises you. Anthropic's figures below were checked on 14 Sep 2026.++Prices are in our post on [what Claude Code costs](/blog/how-much-does-claude-code-cost/), so this one sticks to using the plan well. If you already run more than one terminal, read [how to manage multiple Claude Code sessions](/blog/manage-multiple-claude-code-sessions/) too, because every extra session draws from the same allowance.++## How do Claude Max usage limits work in Claude Code?++Two meters run at once: a session limit that resets every five hours, and a weekly limit. The weekly one covers all models and resets at a fixed time assigned to your account ([Anthropic, What is the Max plan](https://support.claude.com/en/articles/11049741-what-is-the-max-plan), checked 14 Sep 2026). Max 5x and Max 20x multiply Pro's usage per session, and chat, Claude Code and the IDE extensions share one pool. Because both meters are shared across models, switching with `/model` does not bring back a spent session or week. The separate Opus and Sonnet family limits are different: switch outside that family and you keep working (Claude Code errors reference). Run `/usage` to see both bars and their reset times.++{% img "note-1" %}++## Did Claude Code weekly limits change in September 2026?++Yes, from 14 Sep 2026. On 29 Aug 2026 Anthropic's [ClaudeDevs account](https://x.com/ClaudeDevs/status/2093742321473065266) announced that from 14 Sep 2026 standard weekly limits in Claude Code rise permanently by 25%, with the temporary 50% increase staying until then. A follow up post in that thread on 29 Aug 2026 says this "works out to a 17% reduction in weekly limits on Claude Code" against the boosted limit.++## Which model should you use on a Max plan?++Match the model to the job, because model and effort both change how fast you use the limit. Claude Code starts Max accounts on Opus 5, while Anthropic's cost docs say Sonnet handles most coding tasks well and costs less. Reserve Opus for architecture and hard debugging, or set `/model opusplan` so Opus plans and Sonnet executes, though each plan mode toggle then starts a fresh cache. Lower `/effort` for routine work; asking Opus at `max` effort to rename a variable is a very thorough way to spend a morning.++Fable needs a budget of its own. Anthropic's [Fable help article](https://support.claude.com/en/articles/15424964-claude-fable-models-on-your-plan), updated 2 Sep 2026, says Max can spend up to 50% of its weekly limit on Fable 5 and 5.1, and those models use limits faster than the others. Save Fable for the long, ambiguous task, not the quick fix.++## How do you stop context from eating the plan?++Keep the conversation short, because Claude Code resends it with every request. Anthropic's [cost management page](https://code.claude.com/docs/en/costs) gives the levers:++* `/clear` when you switch to unrelated work.+* `/compact Focus on the failing tests` at a natural break. Compaction reads the whole conversation, so on a cold cache it is a large request itself.+* Keep `CLAUDE.md` under 200 lines and move workflow instructions into skills, which load only when used.+* Run `/context` to see what is loaded, and disable MCP servers you are not using.++Plan before editing. Shift+Tab into plan mode for anything that touches several files, press Escape the moment Claude heads the wrong way, and use `/rewind` instead of stacking "try again" on a bad attempt. Each retry rereads everything before it.++## Does prompt caching help on a subscription?++Yes, while the cache is warm. Claude Code's prompt caching page says the main conversation gets a one hour cache on a subscription within plan usage, dropping to five minutes once you draw on usage credits, and subagents get five minutes. We checked by reading the `usage` fields Claude Code 2.1.270 writes to its session transcripts on our machine, with no cache settings changed. Across 27 requests in an orchestrating session, all 121,041 cache write tokens were one hour writes; a subagent it started wrote only five minute entries over 69 requests, and both read 96% to 98% of input from cache on 14 Sep 2026. To check yours, run `claude -p "hello" --output-format json` and read `usage.cache_creation`.++So come back inside the hour, or `/clear` and start fresh, rather than reheating a huge stale context. Switching model mid task rebuilds the cache, and on most models so does changing effort, so choose both at the start. Our guide to [prompt caching for AI agents](/blog/prompt-caching-for-ai-agents/) explains why a stable prefix matters.++## Are subagents cheaper than doing it yourself?++Not automatically. Unless Claude or the subagent's definition names a model, a subagent runs on your session's model, which on Max is Opus 5 by default. Put `model: haiku` or `model: sonnet` in subagents that search, run tests or read logs. They still help: verbose output stays in the subagent and only a summary returns. Open `/usage` and press `w` to see how much of the last week went to subagents, skills and MCP servers.++## Can Claude Code keep working while you are away?++Yes, within limits. Since version 2.1.234, an interactive session signed in with a subscription waits out a usage limit and continues the task on its own. It still stops on permission prompts, re-arms at most twice in a row, and does not start a wait by itself for a reset more than 24 hours away, which a weekly limit often is. `/rate-limit-options` starts or cancels that wait.++Background sessions and `/loop` tasks draw on the same subscription, and each scheduled fire resends the full context. Claude Code's agent view docs put it plainly: ten agents in parallel use quota roughly ten times as fast as one.++{% img "note-2" %}++If you run several agents anyway, Munder Difflin, which we build, runs them from one desktop app. Each Claude Code agent is the real CLI in its own terminal on the login you already use, and you can give every agent its own model and token cap and put prompts on a schedule. One warning for Max users: in 0.5.2 the default agent model is Fable 5, so change it under Settings > Agents & Models if your weekly limit matters. It does not raise Anthropic's limits either.++## Can you share a Max plan or use it in other apps?++No to sharing, and be careful with other apps. Anthropic's Consumer Terms bar sharing your login, and its [Claude Code legal page](https://code.claude.com/docs/en/legal-and-compliance) says advertised Pro and Max limits assume ordinary, individual use. The same page bars third party developers from routing requests through Pro or Max credentials for their users, and says that does not stop you signing in to the unmodified Claude Code binary with your own subscription. If you are building a product on Claude, it points you to an API key.diff --git a/blog/src/posts/codex-cli-vs-claude-code.md b/blog/src/posts/codex-cli-vs-claude-code.mdindex d7ebcfe5..baf29511 100644--- a/blog/src/posts/codex-cli-vs-claude-code.md+++ b/blog/src/posts/codex-cli-vs-claude-code.md@@ -43,7 +43,7 @@ The two overlap heavily in practice: coding standards, architecture notes, a rev## Is Codex CLI free to use?-There's a real free tier, but it's capped. OpenAI's Codex pricing page lists a Free plan at $0 a month for exploring Codex "on quick coding tasks," a Go plan at $8 a month, and a Plus plan at $20 a month that adds cloud-based runs and the GPT-5.6 model family ([developers.openai.com/codex/pricing](https://developers.openai.com/codex/pricing), checked 10 Sep 2026). Claude Code has no equivalent free tier of its own: it authenticates against a paid Claude subscription or an Anthropic API key from the first session.+There's a real free tier, but it's capped. OpenAI's Codex pricing page lists a Free plan at $0 a month for exploring Codex "on quick coding tasks," a Go plan at $8 a month, and a Plus plan at $20 a month that adds cloud-based runs and the GPT-5.6 model family ([developers.openai.com/codex/pricing](https://developers.openai.com/codex/pricing), checked 10 Sep 2026). Claude Code has no equivalent free tier of its own: it authenticates against a paid Claude subscription or an Anthropic API key from the first session. If you already pay for ChatGPT Pro, see [how to make the most of your Codex Max plan](/blog/codex-max-plan-tips/).## Where does Codex CLI actually win?diff --git a/blog/src/posts/codex-max-plan-tips.md b/blog/src/posts/codex-max-plan-tips.mdnew file mode 100644index 00000000..22c9842d--- /dev/null+++ b/blog/src/posts/codex-max-plan-tips.md@@ -0,0 +1,88 @@+---+title: "How to Make the Most of Your Codex Max Plan"+description: "There is no Codex Max plan. What ChatGPT Pro 5x and 20x give you in Codex, how the weekly limit works, and how to stretch it."+date: 2026-09-14+category: guides+categoryLabel: Guides+type: Technical+primaryKeyword: "codex max plan"+secondaryKeywords: ["how to make the most of codex", "codex max plan usage", "chatgpt pro codex usage limits", "does codex have weekly limits", "how to check codex limit usage", "how to reduce codex token usage"]+tags: ["Guides", "Codex", "Cost", "Model Routing"]+faq:+ - q: "Can I still buy ChatGPT Pro 20x for Codex?"+ a: "Not as a new subscriber right now. OpenAI paused new sign-ups and upgrades to Pro $200, also called Pro 20x, on 10 Sep 2026, and existing subscriptions keep renewing. Pro $100 (Pro 5x) is still on sale. If your Pro $200 subscription lapses, you cannot buy it again until the pause lifts."+ - q: "Is there a five hour limit on ChatGPT Pro for Codex?"+ a: "No. OpenAI dropped the five hour window on 12 Jul 2026. On 25 Aug 2026 Thibault Sottiaux of the Codex team said it was coming back for Plus while Pro $100 and Pro $200 stay without it for the upcoming months, and on 31 Aug he said the Pro multiples apply to weekly limits. The weekly limit still applies, so check the usage dashboard for your reset time."+ - q: "Does Codex code review count against my usage limit?"+ a: "It depends on where the review runs. OpenAI's pricing page says reviews Codex runs through GitHub, such as tagging @codex on a pull request, count as Code Review usage, while reviews run locally or outside GitHub count toward your general limits. For local reviews, set review_model in config.toml to a smaller model."+ - q: "What happens when I hit my Codex usage limit in the middle of a task?"+ a: "Codex keeps working on the turn already in progress, subject to fair use limits, per OpenAI's pricing page checked 14 Sep 2026. After that, Plus and Pro users can buy credits without upgrading, use an available reset, or wait for the reset time shown on the usage page."+ - q: "Does switching to a smaller model give me my Codex limit back?"+ a: "No. OpenAI's help article on managing usage with GPT-6 Astra says switching models does not restore allowance in a shared usage pool. A smaller model only makes what is left go further, so switch while you are approaching the limit, not after you hit it."+---++OpenAI has no plan called Codex Max. The plan people mean is ChatGPT Pro, which comes as Pro 5x at $100 a month or Pro 20x at $200 (OpenAI pricing, checked 14 Sep 2026). To make the most of it, run the smallest model and effort that works, keep one chat per task, and check `/status` before big jobs.++Three things muddy the name: Anthropic's Claude Max plan, OpenAI's older GPT-5.1-Codex-Max model, and Codex's **Max** reasoning setting, which gives a model more time on one task ([OpenAI, Models](https://learn.chatgpt.com/docs/models)). None is a Codex plan. Still choosing between tools? Our [Codex CLI vs Claude Code comparison](/blog/codex-cli-vs-claude-code/) covers that. The habits in [managing several Claude Code sessions](/blog/manage-multiple-claude-code-sessions/), like one scope per session, carry straight over to Codex.++## Is there a Codex max plan?++No, but ChatGPT Pro is the closest thing, and its bigger tier just got harder to buy. OpenAI split Pro in two on 9 Apr 2026, adding a $100 tier with 5x the Codex usage of Plus and a launch boost to up to 10x that ran through 31 May 2026 ([OpenAI on X](https://x.com/OpenAI/status/2042295688323875316)), so that boost is over.++Pro $200, labelled Pro 20x, is still the highest usage tier, but since 10 Sep 2026 OpenAI has paused new sign-ups and upgrades to it ([About ChatGPT Pro tiers](https://help.openai.com/en/articles/9793128)). Existing subscriptions renew as usual. If you have Pro 20x, think before you cancel or downgrade: once it lapses, you cannot buy it back until the pause lifts.++## Does Codex have weekly limits?++Yes, and on Pro right now the weekly limit is the one that matters. OpenAI's [pricing page](https://learn.chatgpt.com/docs/pricing) says local messages and cloud chats share one allowance and that weekly limits may also apply. The same pool covers the Codex CLI, the IDE extension, the ChatGPT desktop app and ChatGPT Work.++Plus got its five hour window back in late August. On 25 Aug 2026, Thibault Sottiaux of OpenAI's Codex team said Pro $100 and Pro $200 would keep running without one "for the upcoming months" ([post on X](https://x.com/thsottiaux/status/2092058556707344708)). Nothing refills after five hours, so a long unattended run keeps drawing down the whole week. Budget by the week, not by the sitting.++## Do cloud tasks use more than local ones?++Often, yes. Cloud chats on ChatGPT plans run on GPT-5.6 Sol and may use more of your allowance than local messages, per OpenAI, and for now you can't change their default model. Local work in the CLI or IDE runs whichever model you pick, including the cheaper Terra and Luna. Code review follows the same split: reviews Codex runs through GitHub count as Code Review usage, while a local `/review` counts toward your general limits.++{% img "note-1" %}++So send work to the cloud because you want it off your laptop and running in parallel, not to save usage. From the terminal, `codex cloud exec` needs an environment id and makes one attempt unless you ask for more. Checked on 14 Sep 2026 (output trimmed):++```+$ codex --version+codex-cli 0.153.4+$ codex cloud exec --help+Usage: codex cloud exec [OPTIONS] --env <ENV_ID> [QUERY]+ --attempts <ATTEMPTS>+ Number of assistant attempts (best-of-N)+ [default: 1]+```++Leave `--attempts` at 1 unless you want to compare versions, since each attempt is its own run.++## How do I check my Codex usage?++Type `/status` in an active Codex CLI session, or open the usage dashboard at `chatgpt.com/codex/settings/usage`. OpenAI's pricing page points to both and suggests checking the dashboard every week or two to learn your pace. In the CLI, `/statusline` can pin rate limits to the footer so you see them without asking.++If you run out mid task, Codex keeps working on that turn, subject to fair use, and Plus and Pro users can buy credits rather than upgrade. Better still, follow OpenAI's advice and switch to a smaller model while you are approaching the limit.++## Which model makes Codex usage last longest?++GPT-5.6 Luna, by a wide margin. OpenAI's Pro 5x estimates, checked 14 Sep 2026, are 25 to 225 local messages per five hours on GPT-6 Astra, 50 to 500 on Sol, 125 to 1,000 on Terra and 1,250 to 10,000 on Luna. Pro 20x is four times each. With no five hour cap on Pro, treat them as pace, not a limit. The models page says to use the lowest effort that gets the result, and that most tasks need neither Max nor Ultra, which splits work across subagents.++A workable split: Luna for clear, repeatable edits, Terra for everyday features, and Sol or Astra at low or medium effort for the bug that has beaten you twice. Switch with `/model` inside a chat, or pass `codex exec -m gpt-5.6-luna` for scripted runs. Fast mode is the quiet drain: on Astra and GPT-5.6 it bills at 2.5x, making replies quicker and your week shorter. If an old `config.toml` still pins `gpt-5.4`, change it to `gpt-5.6-terra`: GPT-5.4 left Codex for ChatGPT accounts on 31 Aug 2026.++{% img "note-2" %}++## How do I reduce Codex token usage?++Cut what every turn has to carry. Your prompt, files, chat history and tool results all spend tokens, so these habits pay off on every message:++* **Keep `AGENTS.md` short.** Codex reads it before any work. Move folder specific rules into nested `AGENTS.md` files, as OpenAI's pricing page suggests.+* **Turn off MCP servers you are not using.** OpenAI says each one adds context to your messages.+* **Use one chat per task.** Start the next task with `/new` instead of stacking it onto a long chat, and use `/compact` when a single task runs long. OpenAI's best practices guide warns that one chat for a whole project bloats context.+* **Stop retry loops early.** If a run misses, interrupt it, fix the prompt or add the missing file, then rerun. OpenAI's Astra usage guide notes that raising effort cannot supply information or access the model never had.+* **Point reviews at a cheaper model.** Set `review_model` in `config.toml` so `/review` does not inherit an expensive session model.++## Can I run several Codex agents at once?++Yes, and that is where a Pro allowance goes fastest. Worktrees, cloud chats and subagents all run in parallel from the same pool, and OpenAI's docs say subagent runs use more tokens than a single agent. Go parallel only when tasks touch separate files and a cheaper model suffices.++If you run Codex beside other CLIs, Munder Difflin runs them together in one desktop app. In 0.5.2 each Codex agent signs in with your own Codex login, so they all spend your Pro allowance, and you pick each agent's model: Astra, Sol, Terra or Luna. One honest limit: its per agent token caps read Claude Code's usage data, so they do not meter Codex agents. For those, `/status` and OpenAI's dashboard stay the meter. The [mixed engine office guide](/blog/run-a-mixed-engine-office/) shows a layout, and the [multi-agent cost playbook](/blog/the-multi-agent-cost-playbook/) covers model tiering across a fleet.diff --git a/blog/src/posts/crewai-autogen-vs-a-local-agent-harness.md b/blog/src/posts/crewai-autogen-vs-a-local-agent-harness.mdindex 0c8b8f5f..acd094e4 100644--- a/blog/src/posts/crewai-autogen-vs-a-local-agent-harness.md+++ b/blog/src/posts/crewai-autogen-vs-a-local-agent-harness.md@@ -62,7 +62,7 @@ A [multi-agent harness](/blog/what-is-a-multi-agent-harness/) is the other answeThe pieces you'd have built around a framework are already there: [human approval gates](/blog/human-in-the-loop-approving-ai-agents/) on spend, scope, and destructive ops; a circuit breaker with a steer → constrain → stop ladder; per-agent token budgets; OpenTelemetry observability; a Command Center with a kanban board and live fleet monitoring. And because it drives CLIs rather than calling model APIs, it rides the **subscriptions you already pay for** — no mandatory API key, with BYO keys and local LLMs as options.-The honest flip side: you can't `import` Munder Difflin into your SaaS. It won't run your custom document pipeline inside your product. It's an app for a specific job — a team of agents working your repositories, visible on one screen — not a toolkit for arbitrary agent systems.+The honest flip side: you can't `import` Munder Difflin into your SaaS. It won't run your custom document pipeline inside your product. It's an app for a specific job — a team of agents working your repositories, visible on one screen — not a toolkit for arbitrary agent systems. Server based meta harnesses such as Databricks' Omnigent sit in between, which our [OmniAgent alternatives](/blog/omniagent-alternatives/) post covers.{% img "note-2" %}diff --git a/blog/src/posts/grok-bot-alternatives.md b/blog/src/posts/grok-bot-alternatives.mdnew file mode 100644index 00000000..73337ebe--- /dev/null+++ b/blog/src/posts/grok-bot-alternatives.md@@ -0,0 +1,84 @@+---+title: "Grok Bot Alternatives: Six Picks, Grouped by What You Want"+description: "Grok Bot runs every Bot on one shared cloud computer. Six alternatives checked on 14 Sep 2026, grouped by hosting, privacy and model choice."+date: 2026-09-14+category: comparisons+categoryLabel: Comparisons+type: Non-technical+primaryKeyword: "grok bot alternatives"+secondaryKeywords: ["grok bot alternative", "grok bot vs openclaw", "grok bot vs hermes agent", "grok bot vs claude cowork", "is grok bot free", "does grok bot work on linux"]+tags: ["Comparisons", "Local-First", "Security", "Open Source", "Memory"]+faq:+ - q: "Is Grok Bot free?"+ a: "Only as a trial. Cursor's Grok Bot plans page, checked on 14 Sep 2026, describes the free trial as a usage credit with a seven day window that never turns into a paid plan. After that you need a paid individual Cursor plan, Cursor Teams, or a linked SuperGrok, SuperGrok Plus, SuperGrok Heavy or X Premium+ subscription."+ - q: "Does Grok Bot work on Linux?"+ a: "Yes. SpaceXAI's Grok Bot FAQ lists desktop builds for Linux on x64 and Arm64, packaged as deb, rpm or AppImage, next to macOS, Windows, iPhone (iOS 18 or later) and Android 9 or later. The Bots' own computer is still in the cloud, not your Linux machine."+ - q: "Can you choose which model Grok Bot uses?"+ a: "No. SpaceXAI's security docs say Cursor manages model selection, there is no model picker for customers, and the serving mix can change over time. Enterprise teams can set a model allowlist, but the same docs say enforcement is not guaranteed."+ - q: "Is Grok Bot the same as Grok on X?"+ a: "No. Grok on X is the Grok assistant inside the X app. Grok Bot is a separate agent app that works on its own cloud computer, signs into your tools and runs jobs for you, and SpaceXAI lists the two as separate products."+---++The best Grok Bot alternatives depend on why you want out. For another hosted assistant, try ChatGPT Work, Gemini Spark or Claude Cowork. To keep memory and logins on your own hardware and pick the model yourself, try OpenClaw, Hermes Agent or NanoClaw. Everything below was checked on official pages and repos on 14 Sep 2026.++By Grok Bot we mean SpaceXAI's agent app, hosted by Cursor (both SpaceX companies), not the Grok chatbot on X.++## What is Grok Bot?++Grok Bot is a team of AI agents, called Bots, that work on a computer of their own in the cloud. SpaceXAI launched it in beta on 11 Aug 2026. You message a Bot like a colleague, it signs into your tools, works across apps and websites, and comes back when something needs your approval. It keeps going with your laptop shut and can run routines on a schedule.++Inside SpaceXAI, people run several Bots with a chief of staff Bot handing work to specialists. That is the idea behind a [multi-agent harness](/blog/what-is-a-multi-agent-harness/), hosted for you. A marketplace on x.ai lists ready made Bots you can add, such as Credit Card Max.++[Cursor's Grok Bot plans page](https://cursor.com/help/grok-bot/plans) says access comes with every paid individual Cursor plan and Cursor Teams, and Cursor listed Pro at $20 a month on 14 Sep 2026. Linking an individual SuperGrok or X Premium+ subscription also works; SuperGrok Lite doesn't. Usage resets weekly. The desktop app runs on macOS, Windows and Linux, with apps for iPhone and Android.++## Where does Grok Bot run, and who holds your data?++Grok Bot runs only on Cursor's cloud computers, and SpaceXAI's [security FAQ](https://docs.x.ai/grok-bot/security-faq) says those sit in the United States today. Running it on your own servers is not supported. Each user gets a dedicated virtual machine, so other users can't reach yours. It also needs cloud data storage, so Cursor's Legacy Privacy Mode is out. That is the trade for work that carries on after you close the lid. If you'd rather your files and memory stay on your desk, read [why local first matters for AI agents](/blog/why-local-first-matters-for-ai-agents/).++{% img "note-1" %}++## What can a Bot reach and remember?++A Bot can reach anything on the cloud computer it shares with all your other Bots: its files, browser sessions and logins. SpaceXAI's FAQ says plainly not to use separate Bots as a security boundary. SpaceXAI's own Grok Bot 101 guide says that if you log into Amazon on that computer, the agent "can technically buy whatever it wants". So can your recruiting Bot.++You write the guardrails in plain language. Auto Review checks tool calls and computer actions against your Require Approval and Always Allow rules, but SpaceXAI calls it model based and says it doesn't review memory writes. A Bot remembers preferences, role context and summaries of past work, and the docs suggest checking the source before a big decision. There is no model picker either: Cursor chooses, and the mix can change. A helper that reads the open web, holds your logins and can send email is the risky mix called [the lethal trifecta](/blog/the-lethal-trifecta-for-coding-agents/).++{% img "note-2" %}++## What can you use instead of Grok Bot?++Six good options, grouped by why you're looking.++### You want a hosted assistant, just not this one++**ChatGPT Work** is OpenAI's agent inside ChatGPT, announced on 9 Jul 2026. Plugins connect it to Slack, Microsoft Teams, Google Drive, email and calendars, Scheduled Tasks run on a timer or when an event happens, and you decide when it needs your approval. In the Mac and Windows desktop app it can also use your local files, and there OpenAI offers Work on every plan, Free included.++**Gemini Spark** suits you if your life runs on Gmail, Drive and Calendar. Google's page says it keeps working with your phone and laptop off and is designed to check with you before major actions. It is offered to Google AI Pro and Ultra subscribers in select countries, plus select business users.++### Your work lives in files on your computer++**[Claude Cowork](https://support.claude.com/en/articles/13345190-get-started-with-cowork)** needs a paid Claude plan. In the macOS or Windows desktop app, Claude works in the folders you choose, and Anthropic says it can't reach anything else and asks before deleting. By default the work, local files included, runs on Anthropic's servers (in beta), so it is closer to Grok Bot than it looks, with a tighter fence around your files.++### You want the memory, logins and model on your side++These three are open source and you run them yourself. You bring the model, paid or local, and security becomes your job. We pulled each one's licence and latest release from GitHub on 14 Sep 2026:++| Project | Licence | Latest release (UTC) |+| --- | --- | --- |+| OpenClaw | MIT | v2026.9.4, 11 Sep 2026 |+| Hermes Agent | MIT | v2026.9.11, 11 Sep 2026 |+| NanoClaw | MIT | v2.3.0, 24 Aug 2026 |++**[OpenClaw](https://github.com/openclaw/openclaw)** is the closest thing to a personal assistant you own. It runs on your computer, replies in WhatsApp, Telegram, Slack, iMessage and 20+ other channels, and keeps state, memory and credentials on your hardware. Models are swappable plugins, local ones included, and there is no paid tier. The catch: tools run straight on your machine in the main session unless you set up sandboxing.++**[Hermes Agent](https://github.com/NousResearch/hermes-agent)** from Nous Research is the one to try if memory matters most. It curates its own memory, writes skills after complex tasks, runs scheduled jobs, and talks to you over Telegram, Discord, Slack, WhatsApp or Signal. It can live on your laptop or a cheap server, and `hermes model` switches between providers such as OpenRouter, OpenAI or your own endpoint.++**NanoClaw** is the cautious pick. Each agent runs in its own Linux container and sees only the folders you mount. It is built on Anthropic's Claude Agent SDK and needs Docker.++### You want coding agents on your own machine++Munder Difflin, which we make, is not a personal assistant for your inbox and calendar. It fits a narrower need: a team of coding agents (Claude Code, Codex, Gemini CLI and nine others) working on your own computer. A Slack message can start an agent, missions can run on a schedule, and with your own OpenAI API key you can direct the agents by voice, with a spoken confirmation before anything destructive. The agents stop when your machine does. If you want errands and email handled, pick an assistant above.++## Is Grok Bot worth it?++Grok Bot is worth it if you want almost no setup and are fine with the cloud. A helper that works with the lid shut and hands you the screen for a password or two factor code is hard to build yourself, and a paid individual Cursor plan already includes it. Look elsewhere if you need your data outside the United States, a model you choose, or a wall between one helper and the next.diff --git a/blog/src/posts/herdr-alternatives.md b/blog/src/posts/herdr-alternatives.mdnew file mode 100644index 00000000..38344542--- /dev/null+++ b/blog/src/posts/herdr-alternatives.md@@ -0,0 +1,79 @@+---+title: "Herdr Alternatives: What to Pick and Who Each One Fits"+description: "Herdr alternatives checked on 14 Sep 2026: tmux, Claude Squad, cmux, Orca, Conductor, Superset, Emdash and Munder Difflin, and who each fits."+date: 2026-09-14+category: comparisons+categoryLabel: Comparisons+type: Technical+primaryKeyword: "herdr alternatives"+secondaryKeywords: ["herdr tmux alternative", "herdr alternatives for windows", "herdr vs tmux", "herdr vs zellij", "is herdr open source"]+tags: ["Comparisons", "Multi-Agent", "Claude Code", "Tools", "Open Source"]+faq:+ - q: "Is herdr open source?"+ a: "Yes. Herdr is licensed under Apache 2.0, per its GitHub repository checked on 14 Sep 2026. It launched under AGPL 3.0 in March 2026, added a commercial license option on 26 May 2026, and was relicensed to Apache 2.0 on 22 Jul 2026, so reviews that still call it AGPL are out of date."+ - q: "Does herdr work on Windows?"+ a: "Yes. Herdr's changelog marks Windows support as generally available in 0.8.2 on 19 Aug 2026, and the 0.9.0 release on 7 Sep 2026 ships a Windows x86_64 build next to the Linux and macOS builds. Early August posts that call Windows a beta predate that change."+ - q: "Does herdr replace tmux?"+ a: "For agent work, it can. Herdr keeps panes alive in a background server the way tmux does, uses tmux style prefix keys, and adds agent states on top. Without coding agents, plain tmux does the job and has years more use behind it."+ - q: "What is the difference between herdr and Claude Squad?"+ a: "Herdr owns the terminals and tracks each agent's state, while Claude Squad is a terminal UI that sits on top of tmux and gives every task its own git worktree and branch. Claude Squad needs tmux and the GitHub CLI installed, per its README checked on 14 Sep 2026."+ - q: "Can herdr agents share memory or a task board?"+ a: "Not out of the box. Herdr's English docs, checked on 14 Sep 2026, have no page about shared memory, a task board or scheduling, and coordination happens through its CLI and socket API instead. If you want those parts built in, an orchestrated desktop app is the closer fit."+---++The main herdr alternatives are plain tmux or Zellij, Claude Squad, cmux, Orca, Conductor, Superset, Emdash and Munder Difflin. Stay on herdr if you live in a terminal or work over SSH. Switch when you want a desktop window, agents that share memory, or something that hands out the work so you don't have to.++Herdr is good at its job, so this post sorts the options by why you are leaving. For the wider field, see our roundup of [multi-agent tools built around Claude Code](/blog/best-claude-code-multi-agent-tools/).++## What is herdr, exactly?++Herdr is an open source terminal multiplexer, written in Rust, that runs coding agents such as Claude Code, Codex and OpenCode in panes and labels each pane with the agent's state. It is one binary that runs inside the terminal you already use. A background server owns the terminals, so closing the client or dropping an SSH connection does not stop the work: `ctrl+b q` detaches and `herdr` reattaches, per the [herdr README](https://github.com/herdrdev/herdr).++Search results mix in forks such as codeaudit/herdr; the upstream project is herdrdev/herdr. We pulled its latest release on 14 Sep 2026:++```+$ gh api repos/herdrdev/herdr/releases/latest --jq '.tag_name, .published_at, (.assets[].name)'+v0.9.0+2026-09-07T19:21:31Z+herdr-linux-aarch64+herdr-linux-x86_64+herdr-macos-aarch64+herdr-macos-x86_64+herdr-windows-x86_64.zip+```++The repo also corrects two things older reviews still say. Windows is a normal build now: the changelog marked Windows support generally available in 0.8.2 on 19 Aug 2026. And the history of the `LICENSE` file (`gh api 'repos/herdrdev/herdr/commits?path=LICENSE'`) shows a relicense to Apache 2.0 on 22 Jul 2026, replacing the AGPL 3.0 license it launched with.++## Why look for a herdr alternative?++You might leave herdr for one of four reasons: you want a desktop window, memory shared between agents, a built-in orchestrator, or simply less software. None of the 21 English doc pages for herdr 0.9.0 covers shared memory, a task board or scheduling (checked 14 Sep 2026). Coordination comes as primitives: a script or an agent can run `herdr agent prompt reviewer "Review the current diff" --wait` and then `herdr agent wait reviewer --until blocked`. That is flexible if you enjoy writing the glue, and a weekend you won't get back if you don't.++The real split is terminal tools versus task tools. In herdr, tmux or Claude Squad the unit is a terminal, and you read every one and decide what happens next. In a desktop app with an orchestrator the unit is a task: something assigns it, tracks it and asks you when it is stuck. Herdr's own [compare page](https://herdr.dev/compare/) argues the other side, and fairly: "quit their app and the agents stop; detach every Herdr client and they don't."++{% img "note-1" %}++## Is plain tmux enough instead of herdr?++Plain tmux is enough if you run two or three agents and check on them often. It keeps sessions alive over SSH, it is one package install away on any Linux or macOS machine, and it adds nothing between you and your shells. Zellij sits in the same category. Neither knows what runs inside a pane, so a Claude Code session that is thinking looks the same as one parked on a permission prompt. Where a hand built tmux setup starts to creak is covered in [running agents in tmux vs an agent harness](/blog/tmux-and-scripts-vs-an-agent-harness/).++What herdr adds is knowing which agent needs you right now. Herdr's [concepts docs](https://herdr.dev/docs/concepts/) define the states: blocked means the agent needs input, approval or a decision; working means it is running; done means it finished and you have not looked yet; idle means finished and seen; unknown means herdr cannot tell. For agents it reads from the screen, the [supported agents page](https://herdr.dev/docs/agents/) calls blocked detection deliberately strict: when no rule matches a prompt, herdr falls back to idle rather than guessing. Any replacement should answer that as fast, or you are back to cycling panes.++{% img "note-2" %}++## Which herdr alternatives are worth trying?++Seven are active, each checked on its own repo or site on 14 Sep 2026. Pick by your reason for leaving.++* **Claude Squad, for something smaller on top of the tmux you already have.** [Claude Squad](https://github.com/smtg-ai/claude-squad) is a terminal UI for Claude Code, Codex, OpenCode and Amp that gives each agent its own tmux session and git worktree. It needs tmux and the GitHub CLI, is AGPL 3.0 licensed, and shipped v1.0.20 on 20 Aug 2026.+* **cmux, for a native Mac window.** cmux is a Ghostty based macOS terminal with vertical tabs and notification rings for coding agents. It is Mac only, so no help on a headless Linux box.+* **Orca, for a full GUI on any desktop.** Orca is an MIT licensed app for macOS, Windows and Linux that runs each agent in its own worktree, with a built-in browser and SSH remote worktrees. It shipped v1.4.201 on 13 Sep 2026, and our [Orca vs Munder Difflin](/blog/orca-vs-munder-difflin/) post goes further.+* **Conductor, if agents in the cloud suit you.** Conductor is a Mac app that runs Claude Code, Codex, Cursor and OpenCode agents, and its homepage now leads with Conductor Cloud, where each agent gets an isolated microVM. It was on 0.85.0 as of 9 Sep 2026.+* **Superset, for an IDE built around parallel agents.** Superset brings Claude Code, Codex, OpenCode or any other coding agent into one workspace, isolates each task's changes and lets you review them in one place. Its license is source available (ELv2), not open source.+* **Emdash, for the same idea under Apache 2.0.** Emdash is an open source agentic development environment from a YC W26 company that runs several coding agents in parallel with any provider.+* **Munder Difflin, for agents that work as a team.** This one is ours: a local desktop app for macOS, Windows and Linux where each agent is a real CLI in a real terminal, from any of twelve CLIs. Michael, your clone, hands out the work, the agents share a long-term memory, and anything waiting on you lands on the ASK ME board. The honest limit: as of 0.5.2, quitting the app stops every agent terminal, so there is no detach and walk away.++Three names from older lists need a note. On 10 Apr 2026 Vibe Kanban announced it is [sunsetting](https://www.vibekanban.com/blog/shutdown); the code lives on as a community maintained project. Crystal's repo now says it is Nimbalyst. YC's qm is a multiplayer harness a company deploys for Slack and the web, a different job from a multiplexer.++## When should you stay on herdr?++Stay on herdr if you live in the terminal, work on remote machines over SSH, or want agents running after you close the client. Its 0.9.0 release manages local and saved SSH machines from one window, and its docs show it running from an ordinary SSH client on a phone with no mobile app. If what you really want is a crew that plans, remembers and asks before it guesses, a task tool saves you writing that layer yourself.diff --git a/blog/src/posts/how-much-does-claude-code-cost.md b/blog/src/posts/how-much-does-claude-code-cost.mdindex 3d013b74..3b18b21b 100644--- a/blog/src/posts/how-much-does-claude-code-cost.md+++ b/blog/src/posts/how-much-does-claude-code-cost.md@@ -33,7 +33,7 @@ No. Anthropic's free Claude plan covers chat, web search, memory, file creation,## How much does Claude Code cost with a Claude subscription?-Claude Pro is $20 a month billed monthly, or $17 a month on the annual plan billed up front, and Claude Code comes included at no extra charge (Anthropic, claude.com/pricing, checked 10 Sep 2026). Claude Max sits above it at $100 a month for a five times usage tier and $200 a month for a twenty times tier, with both figures set against Pro's own usage, and both plans meter Claude Code and Claude chat together rather than as two separate allowances ([support.claude.com](https://support.claude.com/en/articles/11145838-use-claude-code-with-your-pro-or-max-plan), checked 10 Sep 2026).+Claude Pro is $20 a month billed monthly, or $17 a month on the annual plan billed up front, and Claude Code comes included at no extra charge (Anthropic, claude.com/pricing, checked 10 Sep 2026). Claude Max sits above it at $100 a month for a five times usage tier and $200 a month for a twenty times tier, with both figures set against Pro's own usage, and both plans meter Claude Code and Claude chat together rather than as two separate allowances ([support.claude.com](https://support.claude.com/en/articles/11145838-use-claude-code-with-your-pro-or-max-plan), checked 10 Sep 2026). Already on Max? Our guide on [how to get the most out of your Claude Code Max plan](/blog/claude-code-max-plan-tips/) covers stretching that allowance.{% img "note-1" %}diff --git a/blog/src/posts/omniagent-alternatives.md b/blog/src/posts/omniagent-alternatives.mdnew file mode 100644index 00000000..b06b4091--- /dev/null+++ b/blog/src/posts/omniagent-alternatives.md@@ -0,0 +1,76 @@+---+title: "OmniAgent Alternatives: What to Use Instead of Databricks Omnigent"+description: "OmniAgent is really Omnigent, the open source meta harness from Databricks. Alternatives checked on 14 Sep 2026, and who each one fits."+date: 2026-09-14+category: comparisons+categoryLabel: Comparisons+type: Technical+primaryKeyword: "omniagent alternatives"+secondaryKeywords: ["omnigent alternatives", "omnigent databricks", "omnigent meta harness", "omniagent harness", "omnigent vs opencode"]+tags: ["Comparisons", "Multi-Agent", "Claude Code", "Tools", "Open Source"]+faq:+ - q: "Is OmniAgent the same as Omnigent?"+ a: "If you mean the Databricks agent harness, yes: the project is called Omnigent and lives in the omnigent-ai/omnigent repository on GitHub. OmniAgent is also the name of unrelated projects, such as a personal assistant that answers across chat apps (plexusone/omniagent) and a terminal for CLI agents on remote servers (sbyoun/OmniAgent)."+ - q: "Is Omnigent open source?"+ a: "Yes. Omnigent is licensed under Apache 2.0, and its NOTICE file carries a Databricks copyright, checked on 14 Sep 2026. Databricks also runs a managed version called Omnigent on Databricks, which its docs listed as Beta on 11 Sep 2026."+ - q: "Do you need Databricks to use Omnigent?"+ a: "No. The open source release runs on your own machine or any server, and its README lists four kinds of model credentials: a vendor API key, a Claude or ChatGPT subscription through the official CLIs, a compatible gateway such as OpenRouter or Ollama, or a Databricks workspace. Databricks is one option, not a requirement."+ - q: "Does Omnigent work on Windows?"+ a: "Partly. The README says Omnigent runs natively on Windows in a degraded mode: the server, the web UI and the SDK based harnesses work, but the native Claude, Codex and Cursor terminal wrappers and the filesystem and network sandbox do not. For those it points you to Linux, macOS or WSL."+---++The OmniAgent harness people search for is Omnigent, an Apache 2.0 meta harness from Databricks. Good alternatives: Claude Code agent teams for a lighter setup, Orca or Munder Difflin for a local desktop app, Paperclip for company style governance, and LangGraph or the OpenAI Agents SDK if you'd rather write the orchestration yourself.++The name is crowded. On GitHub, plexusone/omniagent is a personal assistant that replies for you across chat apps, and sbyoun/OmniAgent is a terminal for running CLI agents across servers. CallMiner also sells an unrelated customer service OmniAgent. If "harness" is a new word here, start with [what a multi-agent harness is](/blog/what-is-a-multi-agent-harness/). Everything below was checked on 14 Sep 2026.++## Is it called OmniAgent or Omnigent?++It is called Omnigent. Databricks announced it on 13 Jun 2026 in a [post by Matei Zaharia, Kasey Uhlenhuth and Corey Zumar](https://www.databricks.com/blog/introducing-omnigent-meta-harness-combine-control-and-share-your-agents) and released it under Apache 2.0; the repo's `NOTICE` file reads "Copyright (2026) Databricks, Inc." A couple of explainers spell it OmniAgent, and Google autocomplete for "omniagent" suggests "omnigent databrick", so both spellings lead to the same project. We pulled the basics from GitHub:++```+$ gh api repos/omnigent-ai/omnigent --jq '.license.spdx_id, .language, .created_at'+Apache-2.0+Python+2026-06-11T12:18:13Z+$ gh api repos/omnigent-ai/omnigent/releases/latest --jq '.tag_name, .published_at'+v0.13.0+2026-09-09T14:56:32Z+```++Omnigent does not replace Claude Code or Codex; it runs them under one server. Per its [README](https://github.com/omnigent-ai/omnigent), it puts Claude Code, Codex, Cursor, OpenCode, Hermes, Pi and your own YAML defined agents behind one layer: mix them in a single session, ask one to review another's work, or swap the harness by changing one line. A server stores every session and serves a web UI (`http://localhost:6767` when it runs locally), so the same session opens in your terminal, a browser, the desktop app or a phone. Teammates can watch it live, co-drive it on your machine or fork it.++{% img "note-1" %}++## Why look for an Omnigent alternative?++Four things can push you elsewhere: the setup, the server at the centre, the style of governance, or a wish to write the orchestration themselves. None of them makes Omnigent a bad tool.++The setup is more than one download. The README lists Python 3.12 or newer, `uv`, `git`, Node 22 with `npm` and `pnpm`, `tmux` for the native Claude and Codex wrappers, and `bubblewrap` on Linux, though the one line installer offers uv, tmux and bubblewrap. On Windows it runs "in a degraded mode", without the native terminal wrappers or the filesystem and network sandbox. The project still wears an alpha badge, and releases went from v0.9.0 on 11 Aug to v0.13.0 on 9 Sep 2026, so expect things to move under you.++Everything goes through a server. Even solo, you run one on your laptop and every client attaches to it. That is what makes shared sessions possible, and it is more moving parts than one person at one desk needs. Our piece on [local first vs cloud agent SDKs](/blog/local-first-vs-cloud-agent-sdks/) covers that trade in general.++Governance is written as code. Omnigent policies return allow, deny or ask, and they stack at three levels: server wide for admins, per agent in the YAML, and per session in the UI, with session rules checked first. Built-in handlers ask before file and shell tool calls, cap tool calls per session and block expensive models past a spend limit, with optional warnings before that. You can toggle the built-ins in the UI, but a rule beyond them means writing a Python handler, which is either a relief or a chore depending on who owns Python on your team. On the managed service, [Databricks' docs](https://docs.databricks.com/aws/en/omnigent/) (updated 11 Sep 2026) say only the built-in contextual policies are supported.++{% img "note-2" %}++## Which Omnigent alternatives are worth trying?++Five are worth a look, each checked on its own repo or docs on 14 Sep 2026.++| Alternative | What it is | Fits you if |+| --- | --- | --- |+| Claude Code agent teams | Built into Claude Code, experimental, switched on with `CLAUDE_CODE_EXPERIMENTAL_AGENT_TEAMS=1`. A lead session spawns teammates that share a task list and message each other ([docs](https://code.claude.com/docs/en/agent-teams)). | You only run Claude and want nothing new installed. It will not mix in Codex or Cursor. |+| [Orca](https://github.com/stablyai/orca) | MIT licensed desktop app for macOS, Windows and Linux that runs Codex, Claude Code, OpenCode or Pi side by side, each in its own git worktree, with a mobile companion. | You want parallel agents in a GUI and you compare their results yourself. |+| Munder Difflin | Our local desktop app, described below. | You want many CLIs working as one team on your own machine. |+| Paperclip | MIT licensed, self hosted Node server and React UI that runs agents as a company, with an org chart, monthly budgets per agent and approval for new hires ([repo](https://github.com/paperclipai/paperclip)). | Your governance question is who reports to whom and what each agent may spend, rather than rules on every tool call. |+| LangGraph, OpenAI Agents SDK, Claude Agent SDK | Libraries you build agents on. | You are shipping an agent product, not supervising coding agents. See [frameworks vs a local harness](/blog/crewai-autogen-vs-a-local-agent-harness/). |++Munder Difflin is ours, so weigh this entry with that in mind. It is a desktop app for macOS, Windows and Linux where every agent is a real CLI in a real terminal, across twelve providers including Claude Code, Codex, Gemini CLI, Copilot and Cursor. Michael, your clone, is the orchestrator you brief. Each agent keeps durable notes in its own `memory.md` that every other agent can read. You can set a token budget for the whole floor and a cap per agent, and a circuit breaker steers an agent that loops or burns tokens too fast.++It is not a like for like swap. It has nothing like Omnigent's layered policies, with rules set server wide, per agent and per session, and your laptop has to stay on because the agents run there. Auto Mode, which skips each CLI's own permission prompts, is on by default in 0.5.2, so turn it off if you want to approve tool calls yourself. The classic office is open source under MIT, and the paid plans are on the [pricing page](https://munderdiffl.in/#pricing).++## When is Omnigent the better choice?++Omnigent is the better pick when a team needs one policy layer and one audit story across agents from several vendors. That case is strongest inside Databricks. The managed service runs the server for you, tied to your workspace's identity provider, with model access through Foundation Model APIs and AI Gateway. The repo's `docs/databricks.md` guide for self managed installs adds audit logs and per key cost tracking at the gateway, with traces kept in MLflow Tracing in Unity Catalog.++It also wins when people need to share, co-drive or fork a live session, or run agents in cloud sandboxes such as Modal or E2B with no laptop left open. A desktop app on one machine cannot stand in for that.diff --git a/blog/src/posts/tmux-and-scripts-vs-an-agent-harness.md b/blog/src/posts/tmux-and-scripts-vs-an-agent-harness.mdindex ba93405a..62070c43 100644--- a/blog/src/posts/tmux-and-scripts-vs-an-agent-harness.md+++ b/blog/src/posts/tmux-and-scripts-vs-an-agent-harness.md@@ -48,7 +48,7 @@ If you're running two agents on two branches and reviewing everything yourself,**Cron is a trigger with no feedback loop.** Cron can start a session on a schedule, but it can't watch the result, retry a failure, or route the output anywhere. And there's no path at all from "a teammate posted in Slack" or "a webhook fired" to "an agent picked it up."-None of these are tmux's fault. tmux is a terminal multiplexer, and it's excellent at multiplexing terminals. Everything above is a *coordination* problem, and coordination is a different program — one you end up writing yourself, script by script, incident by incident.+None of these are tmux's fault. tmux is a terminal multiplexer, and it's excellent at multiplexing terminals. Everything above is a *coordination* problem, and coordination is a different program — one you end up writing yourself, script by script, incident by incident. Agent aware multiplexers such as herdr sit in between, and our [herdr alternatives](/blog/herdr-alternatives/) post compares them with the rest.{% img "note-1" %}diff --git a/blog/src/posts/why-local-first-matters-for-ai-agents.md b/blog/src/posts/why-local-first-matters-for-ai-agents.mdindex eecf4939..5663cdac 100644--- a/blog/src/posts/why-local-first-matters-for-ai-agents.md+++ b/blog/src/posts/why-local-first-matters-for-ai-agents.md@@ -67,7 +67,7 @@ agents to a team, that difference compounds.It's only fair to name the trade. Cloud platforms can offer zero-setup onboarding, managed scaling,and team features out of the box. If you need a hosted, shared, always-on service for a distributed-team, that convenience is real.+team, that convenience is real. The same trade shows up in personal assistants, as our look at [Grok Bot alternatives](/blog/grok-bot-alternatives/) shows.But for an individual developer or a small team running agents against their own code, theconvenience rarely outweighs handing over control, privacy, and predictable cost. You can have thediff --git a/docs/blog/agent-security-and-sandboxing/index.html b/docs/blog/agent-security-and-sandboxing/index.htmlindex b991f5f7..d1505134 100644--- a/docs/blog/agent-security-and-sandboxing/index.html+++ b/docs/blog/agent-security-and-sandboxing/index.html@@ -308,50 +308,50 @@ git, lifecycle hooks, and an audit trail — so safe-by-default is the path of l<h2>Related in Guides</h2><div class="post-grid"><article class="card t-guides">- <a class="thumb t-guides" href="/blog/how-to-use-claude-code-plan-mode/" aria-hidden="true" tabindex="-1"><img src="/blog/assets/media/how-to-use-claude-code-plan-mode/hero.png" alt="" loading="lazy" decoding="async" /></a>+ <a class="thumb t-guides" href="/blog/claude-code-max-plan-tips/" aria-hidden="true" tabindex="-1"><img src="/blog/assets/media/claude-code-max-plan-tips/hero.png" alt="" loading="lazy" decoding="async" /></a><div class="body"><div class="meta">- <time datetime="2026-09-11">Sep 11, 2026</time>+ <time datetime="2026-09-14">Sep 14, 2026</time><span class="dot" aria-hidden="true"></span><span>5 min</span></div>- <h3><a href="/blog/how-to-use-claude-code-plan-mode/">How to Use Claude Code Plan Mode</a></h3>- <p class="dek">How Claude Code's plan mode works: turning it on, what it blocks, what a real headless plan mode run prints, and how to leave it.</p>+ <h3><a href="/blog/claude-code-max-plan-tips/">How to Get the Most Out of Your Claude Code Max Plan</a></h3>+ <p class="dek">Stretch a Claude Code Max plan: model choice, context hygiene, prompt caching, subagents and unattended runs, checked against Anthropic's own pages.</p><div class="foot"><span class="tag kind">Guides</span>- <a class="more" href="/blog/how-to-use-claude-code-plan-mode/" aria-label="Read: How to Use Claude Code Plan Mode">Read →</a>+ <a class="more" href="/blog/claude-code-max-plan-tips/" aria-label="Read: How to Get the Most Out of Your Claude Code Max Plan">Read →</a></div></div></article><article class="card t-guides">- <a class="thumb t-guides" href="/blog/how-to-add-an-mcp-server-to-claude-code/" aria-hidden="true" tabindex="-1"><img src="/blog/assets/media/how-to-add-an-mcp-server-to-claude-code/hero.png" alt="" loading="lazy" decoding="async" /></a>+ <a class="thumb t-guides" href="/blog/codex-max-plan-tips/" aria-hidden="true" tabindex="-1"><img src="/blog/assets/media/codex-max-plan-tips/hero.png" alt="" loading="lazy" decoding="async" /></a><div class="body"><div class="meta">- <time datetime="2026-09-10">Sep 10, 2026</time>+ <time datetime="2026-09-14">Sep 14, 2026</time><span class="dot" aria-hidden="true"></span><span>5 min</span></div>- <h3><a href="/blog/how-to-add-an-mcp-server-to-claude-code/">How to Add an MCP Server to Claude Code</a></h3>- <p class="dek">The claude mcp add command, its scope flag, editing .mcp.json by hand, and how Munder Difflin's Capabilities screen grants an MCP server to one agent at a time.</p>+ <h3><a href="/blog/codex-max-plan-tips/">How to Make the Most of Your Codex Max Plan</a></h3>+ <p class="dek">There is no Codex Max plan. What ChatGPT Pro 5x and 20x give you in Codex, how the weekly limit works, and how to stretch it.</p><div class="foot"><span class="tag kind">Guides</span>- <a class="more" href="/blog/how-to-add-an-mcp-server-to-claude-code/" aria-label="Read: How to Add an MCP Server to Claude Code">Read →</a>+ <a class="more" href="/blog/codex-max-plan-tips/" aria-label="Read: How to Make the Most of Your Codex Max Plan">Read →</a></div></div></article><article class="card t-guides">- <a class="thumb t-guides" href="/blog/command-center-guide/" aria-hidden="true" tabindex="-1"><img src="/blog/assets/media/command-center-guide/hero.png" alt="" loading="lazy" decoding="async" /></a>+ <a class="thumb t-guides" href="/blog/how-to-use-claude-code-plan-mode/" aria-hidden="true" tabindex="-1"><img src="/blog/assets/media/how-to-use-claude-code-plan-mode/hero.png" alt="" loading="lazy" decoding="async" /></a><div class="body"><div class="meta">- <time datetime="2026-07-03">Jul 3, 2026</time>+ <time datetime="2026-09-11">Sep 11, 2026</time><span class="dot" aria-hidden="true"></span>- <span>4 min</span>+ <span>5 min</span></div>- <h3><a href="/blog/command-center-guide/">The Command Center: Kanban, Fleet and Budgets in One Place</a></h3>- <p class="dek">A guide to Munder Difflin's Command Center in 0.5.2: the kanban with task dependencies, the ask me tab, triggers, memory, live token use against each agent's budget, and when to watch the board instead of the floor.</p>+ <h3><a href="/blog/how-to-use-claude-code-plan-mode/">How to Use Claude Code Plan Mode</a></h3>+ <p class="dek">How Claude Code's plan mode works: turning it on, what it blocks, what a real headless plan mode run prints, and how to leave it.</p><div class="foot"><span class="tag kind">Guides</span>- <a class="more" href="/blog/command-center-guide/" aria-label="Read: The Command Center: Kanban, Fleet and Budgets in One Place">Read →</a>+ <a class="more" href="/blog/how-to-use-claude-code-plan-mode/" aria-label="Read: How to Use Claude Code Plan Mode">Read →</a></div></div></article>diff --git a/docs/blog/assets/media/claude-code-max-plan-tips/hero.png b/docs/blog/assets/media/claude-code-max-plan-tips/hero.pngnew file mode 100644index 00000000..3a5fac77Binary files /dev/null and b/docs/blog/assets/media/claude-code-max-plan-tips/hero.png differdiff --git a/docs/blog/assets/media/claude-code-max-plan-tips/note-1.png b/docs/blog/assets/media/claude-code-max-plan-tips/note-1.pngnew file mode 100644index 00000000..ead298c0Binary files /dev/null and b/docs/blog/assets/media/claude-code-max-plan-tips/note-1.png differdiff --git a/docs/blog/assets/media/claude-code-max-plan-tips/note-2.png b/docs/blog/assets/media/claude-code-max-plan-tips/note-2.pngnew file mode 100644index 00000000..c2a4c450Binary files /dev/null and b/docs/blog/assets/media/claude-code-max-plan-tips/note-2.png differdiff --git a/docs/blog/assets/media/codex-max-plan-tips/hero.png b/docs/blog/assets/media/codex-max-plan-tips/hero.pngnew file mode 100644index 00000000..b3a91c61Binary files /dev/null and b/docs/blog/assets/media/codex-max-plan-tips/hero.png differdiff --git a/docs/blog/assets/media/codex-max-plan-tips/note-1.png b/docs/blog/assets/media/codex-max-plan-tips/note-1.pngnew file mode 100644index 00000000..592d073aBinary files /dev/null and b/docs/blog/assets/media/codex-max-plan-tips/note-1.png differdiff --git a/docs/blog/assets/media/codex-max-plan-tips/note-2.png b/docs/blog/assets/media/codex-max-plan-tips/note-2.pngnew file mode 100644index 00000000..dabcf63aBinary files /dev/null and b/docs/blog/assets/media/codex-max-plan-tips/note-2.png differdiff --git a/docs/blog/assets/media/grok-bot-alternatives/hero.png b/docs/blog/assets/media/grok-bot-alternatives/hero.pngnew file mode 100644index 00000000..dcd5c077Binary files /dev/null and b/docs/blog/assets/media/grok-bot-alternatives/hero.png differdiff --git a/docs/blog/assets/media/grok-bot-alternatives/note-1.png b/docs/blog/assets/media/grok-bot-alternatives/note-1.pngnew file mode 100644index 00000000..fc22af92Binary files /dev/null and b/docs/blog/assets/media/grok-bot-alternatives/note-1.png differdiff --git a/docs/blog/assets/media/grok-bot-alternatives/note-2.png b/docs/blog/assets/media/grok-bot-alternatives/note-2.pngnew file mode 100644index 00000000..b54c2b20Binary files /dev/null and b/docs/blog/assets/media/grok-bot-alternatives/note-2.png differdiff --git a/docs/blog/assets/media/herdr-alternatives/hero.png b/docs/blog/assets/media/herdr-alternatives/hero.pngnew file mode 100644index 00000000..8d258ea5Binary files /dev/null and b/docs/blog/assets/media/herdr-alternatives/hero.png differdiff --git a/docs/blog/assets/media/herdr-alternatives/note-1.png b/docs/blog/assets/media/herdr-alternatives/note-1.pngnew file mode 100644index 00000000..acb115cfBinary files /dev/null and b/docs/blog/assets/media/herdr-alternatives/note-1.png differdiff --git a/docs/blog/assets/media/herdr-alternatives/note-2.png b/docs/blog/assets/media/herdr-alternatives/note-2.pngnew file mode 100644index 00000000..01c20d93Binary files /dev/null and b/docs/blog/assets/media/herdr-alternatives/note-2.png differdiff --git a/docs/blog/best-ai-coding-agents/index.html b/docs/blog/best-ai-coding-agents/index.htmlindex 83c0eb81..f59a2c44 100644--- a/docs/blog/best-ai-coding-agents/index.html+++ b/docs/blog/best-ai-coding-agents/index.html@@ -358,50 +358,50 @@ source.</p><h2>Related in Comparisons</h2><div class="post-grid"><article class="card t-comparisons">- <a class="thumb t-comparisons" href="/blog/codex-cli-vs-claude-code/" aria-hidden="true" tabindex="-1"><img src="/blog/assets/media/codex-cli-vs-claude-code/hero.png" alt="" loading="lazy" decoding="async" /></a>+ <a class="thumb t-comparisons" href="/blog/grok-bot-alternatives/" aria-hidden="true" tabindex="-1"><img src="/blog/assets/media/grok-bot-alternatives/hero.png" alt="" loading="lazy" decoding="async" /></a><div class="body"><div class="meta">- <time datetime="2026-09-10">Sep 10, 2026</time>+ <time datetime="2026-09-14">Sep 14, 2026</time><span class="dot" aria-hidden="true"></span><span>5 min</span></div>- <h3><a href="/blog/codex-cli-vs-claude-code/">Codex CLI vs Claude Code</a></h3>- <p class="dek">Codex CLI and Claude Code compared firsthand: sandbox and approval flags, AGENTS.md vs CLAUDE.md, real pricing, and where each terminal agent wins.</p>+ <h3><a href="/blog/grok-bot-alternatives/">Grok Bot Alternatives: Six Picks, Grouped by What You Want</a></h3>+ <p class="dek">Grok Bot runs every Bot on one shared cloud computer. Six alternatives checked on 14 Sep 2026, grouped by hosting, privacy and model choice.</p><div class="foot"><span class="tag kind">Comparisons</span>- <a class="more" href="/blog/codex-cli-vs-claude-code/" aria-label="Read: Codex CLI vs Claude Code">Read →</a>+ <a class="more" href="/blog/grok-bot-alternatives/" aria-label="Read: Grok Bot Alternatives: Six Picks, Grouped by What You Want">Read →</a></div></div></article><article class="card t-comparisons">- <a class="thumb t-comparisons" href="/blog/qm-vs-munder-difflin/" aria-hidden="true" tabindex="-1"><img src="/blog/assets/media/qm-vs-munder-difflin/hero.png" alt="" loading="lazy" decoding="async" /></a>+ <a class="thumb t-comparisons" href="/blog/herdr-alternatives/" aria-hidden="true" tabindex="-1"><img src="/blog/assets/media/herdr-alternatives/hero.png" alt="" loading="lazy" decoding="async" /></a><div class="body"><div class="meta">- <time datetime="2026-08-06">Aug 6, 2026</time>+ <time datetime="2026-09-14">Sep 14, 2026</time><span class="dot" aria-hidden="true"></span>- <span>4 min</span>+ <span>5 min</span></div>- <h3><a href="/blog/qm-vs-munder-difflin/">qm vs Munder Difflin: YC's Multiplayer Harness or an Office of Your Clones?</a></h3>- <p class="dek">An honest September 2026 comparison of YC's qm and Munder Difflin. qm is a multiplayer agent harness a company deploys for Slack and the web. Munder Difflin runs an office of your clones on your own machine, with Teams to connect them.</p>+ <h3><a href="/blog/herdr-alternatives/">Herdr Alternatives: What to Pick and Who Each One Fits</a></h3>+ <p class="dek">Herdr alternatives checked on 14 Sep 2026: tmux, Claude Squad, cmux, Orca, Conductor, Superset, Emdash and Munder Difflin, and who each fits.</p><div class="foot"><span class="tag kind">Comparisons</span>- <a class="more" href="/blog/qm-vs-munder-difflin/" aria-label="Read: qm vs Munder Difflin: YC's Multiplayer Harness or an Office of Your Clones?">Read →</a>+ <a class="more" href="/blog/herdr-alternatives/" aria-label="Read: Herdr Alternatives: What to Pick and Who Each One Fits">Read →</a></div></div></article><article class="card t-comparisons">- <a class="thumb t-comparisons" href="/blog/crewai-autogen-vs-a-local-agent-harness/" aria-hidden="true" tabindex="-1"><img src="/blog/assets/media/crewai-autogen-vs-a-local-agent-harness/hero.png" alt="" loading="lazy" decoding="async" /></a>+ <a class="thumb t-comparisons" href="/blog/omniagent-alternatives/" aria-hidden="true" tabindex="-1"><span class="thumb-ph"><em class="ph-glyph" aria-hidden="true">✶</em><span>COMPARISONS</span></span></a><div class="body"><div class="meta">- <time datetime="2026-07-03">Jul 3, 2026</time>+ <time datetime="2026-09-14">Sep 14, 2026</time><span class="dot" aria-hidden="true"></span><span>5 min</span></div>- <h3><a href="/blog/crewai-autogen-vs-a-local-agent-harness/">CrewAI and AutoGen vs a Local Agent Harness: Framework or App?</a></h3>- <p class="dek">CrewAI, AutoGen (now Microsoft Agent Framework), and LangGraph are frameworks — Python you write to build your own agent system. A multi-agent harness is an app you download that runs a team on your repos today. Here's how to tell which one you actually need.</p>+ <h3><a href="/blog/omniagent-alternatives/">OmniAgent Alternatives: What to Use Instead of Databricks Omnigent</a></h3>+ <p class="dek">OmniAgent is really Omnigent, the open source meta harness from Databricks. Alternatives checked on 14 Sep 2026, and who each one fits.</p><div class="foot"><span class="tag kind">Comparisons</span>- <a class="more" href="/blog/crewai-autogen-vs-a-local-agent-harness/" aria-label="Read: CrewAI and AutoGen vs a Local Agent Harness: Framework or App?">Read →</a>+ <a class="more" href="/blog/omniagent-alternatives/" aria-label="Read: OmniAgent Alternatives: What to Use Instead of Databricks Omnigent">Read →</a></div></div></article>diff --git a/docs/blog/best-claude-code-multi-agent-tools/index.html b/docs/blog/best-claude-code-multi-agent-tools/index.htmlindex 7f16b766..e435e696 100644--- a/docs/blog/best-claude-code-multi-agent-tools/index.html+++ b/docs/blog/best-claude-code-multi-agent-tools/index.html@@ -417,50 +417,50 @@ from parallelism to coordination the day you start running a real team of agents<h2>Related in Comparisons</h2><div class="post-grid"><article class="card t-comparisons">- <a class="thumb t-comparisons" href="/blog/codex-cli-vs-claude-code/" aria-hidden="true" tabindex="-1"><img src="/blog/assets/media/codex-cli-vs-claude-code/hero.png" alt="" loading="lazy" decoding="async" /></a>+ <a class="thumb t-comparisons" href="/blog/grok-bot-alternatives/" aria-hidden="true" tabindex="-1"><img src="/blog/assets/media/grok-bot-alternatives/hero.png" alt="" loading="lazy" decoding="async" /></a><div class="body"><div class="meta">- <time datetime="2026-09-10">Sep 10, 2026</time>+ <time datetime="2026-09-14">Sep 14, 2026</time><span class="dot" aria-hidden="true"></span><span>5 min</span></div>- <h3><a href="/blog/codex-cli-vs-claude-code/">Codex CLI vs Claude Code</a></h3>- <p class="dek">Codex CLI and Claude Code compared firsthand: sandbox and approval flags, AGENTS.md vs CLAUDE.md, real pricing, and where each terminal agent wins.</p>+ <h3><a href="/blog/grok-bot-alternatives/">Grok Bot Alternatives: Six Picks, Grouped by What You Want</a></h3>+ <p class="dek">Grok Bot runs every Bot on one shared cloud computer. Six alternatives checked on 14 Sep 2026, grouped by hosting, privacy and model choice.</p><div class="foot"><span class="tag kind">Comparisons</span>- <a class="more" href="/blog/codex-cli-vs-claude-code/" aria-label="Read: Codex CLI vs Claude Code">Read →</a>+ <a class="more" href="/blog/grok-bot-alternatives/" aria-label="Read: Grok Bot Alternatives: Six Picks, Grouped by What You Want">Read →</a></div></div></article><article class="card t-comparisons">- <a class="thumb t-comparisons" href="/blog/qm-vs-munder-difflin/" aria-hidden="true" tabindex="-1"><img src="/blog/assets/media/qm-vs-munder-difflin/hero.png" alt="" loading="lazy" decoding="async" /></a>+ <a class="thumb t-comparisons" href="/blog/herdr-alternatives/" aria-hidden="true" tabindex="-1"><img src="/blog/assets/media/herdr-alternatives/hero.png" alt="" loading="lazy" decoding="async" /></a><div class="body"><div class="meta">- <time datetime="2026-08-06">Aug 6, 2026</time>+ <time datetime="2026-09-14">Sep 14, 2026</time><span class="dot" aria-hidden="true"></span>- <span>4 min</span>+ <span>5 min</span></div>- <h3><a href="/blog/qm-vs-munder-difflin/">qm vs Munder Difflin: YC's Multiplayer Harness or an Office of Your Clones?</a></h3>- <p class="dek">An honest September 2026 comparison of YC's qm and Munder Difflin. qm is a multiplayer agent harness a company deploys for Slack and the web. Munder Difflin runs an office of your clones on your own machine, with Teams to connect them.</p>+ <h3><a href="/blog/herdr-alternatives/">Herdr Alternatives: What to Pick and Who Each One Fits</a></h3>+ <p class="dek">Herdr alternatives checked on 14 Sep 2026: tmux, Claude Squad, cmux, Orca, Conductor, Superset, Emdash and Munder Difflin, and who each fits.</p><div class="foot"><span class="tag kind">Comparisons</span>- <a class="more" href="/blog/qm-vs-munder-difflin/" aria-label="Read: qm vs Munder Difflin: YC's Multiplayer Harness or an Office of Your Clones?">Read →</a>+ <a class="more" href="/blog/herdr-alternatives/" aria-label="Read: Herdr Alternatives: What to Pick and Who Each One Fits">Read →</a></div></div></article><article class="card t-comparisons">- <a class="thumb t-comparisons" href="/blog/crewai-autogen-vs-a-local-agent-harness/" aria-hidden="true" tabindex="-1"><img src="/blog/assets/media/crewai-autogen-vs-a-local-agent-harness/hero.png" alt="" loading="lazy" decoding="async" /></a>+ <a class="thumb t-comparisons" href="/blog/omniagent-alternatives/" aria-hidden="true" tabindex="-1"><span class="thumb-ph"><em class="ph-glyph" aria-hidden="true">✶</em><span>COMPARISONS</span></span></a><div class="body"><div class="meta">- <time datetime="2026-07-03">Jul 3, 2026</time>+ <time datetime="2026-09-14">Sep 14, 2026</time><span class="dot" aria-hidden="true"></span><span>5 min</span></div>- <h3><a href="/blog/crewai-autogen-vs-a-local-agent-harness/">CrewAI and AutoGen vs a Local Agent Harness: Framework or App?</a></h3>- <p class="dek">CrewAI, AutoGen (now Microsoft Agent Framework), and LangGraph are frameworks — Python you write to build your own agent system. A multi-agent harness is an app you download that runs a team on your repos today. Here's how to tell which one you actually need.</p>+ <h3><a href="/blog/omniagent-alternatives/">OmniAgent Alternatives: What to Use Instead of Databricks Omnigent</a></h3>+ <p class="dek">OmniAgent is really Omnigent, the open source meta harness from Databricks. Alternatives checked on 14 Sep 2026, and who each one fits.</p><div class="foot"><span class="tag kind">Comparisons</span>- <a class="more" href="/blog/crewai-autogen-vs-a-local-agent-harness/" aria-label="Read: CrewAI and AutoGen vs a Local Agent Harness: Framework or App?">Read →</a>+ <a class="more" href="/blog/omniagent-alternatives/" aria-label="Read: OmniAgent Alternatives: What to Use Instead of Databricks Omnigent">Read →</a></div></div></article>diff --git a/docs/blog/building-reliable-ai-agents/index.html b/docs/blog/building-reliable-ai-agents/index.htmlindex a643a1ac..c4fa5324 100644--- a/docs/blog/building-reliable-ai-agents/index.html+++ b/docs/blog/building-reliable-ai-agents/index.html@@ -339,50 +339,50 @@ by design; it’s free and open source.</p><h2>Related in Guides</h2><div class="post-grid"><article class="card t-guides">- <a class="thumb t-guides" href="/blog/how-to-use-claude-code-plan-mode/" aria-hidden="true" tabindex="-1"><img src="/blog/assets/media/how-to-use-claude-code-plan-mode/hero.png" alt="" loading="lazy" decoding="async" /></a>+ <a class="thumb t-guides" href="/blog/claude-code-max-plan-tips/" aria-hidden="true" tabindex="-1"><img src="/blog/assets/media/claude-code-max-plan-tips/hero.png" alt="" loading="lazy" decoding="async" /></a><div class="body"><div class="meta">- <time datetime="2026-09-11">Sep 11, 2026</time>+ <time datetime="2026-09-14">Sep 14, 2026</time><span class="dot" aria-hidden="true"></span><span>5 min</span></div>- <h3><a href="/blog/how-to-use-claude-code-plan-mode/">How to Use Claude Code Plan Mode</a></h3>- <p class="dek">How Claude Code's plan mode works: turning it on, what it blocks, what a real headless plan mode run prints, and how to leave it.</p>+ <h3><a href="/blog/claude-code-max-plan-tips/">How to Get the Most Out of Your Claude Code Max Plan</a></h3>+ <p class="dek">Stretch a Claude Code Max plan: model choice, context hygiene, prompt caching, subagents and unattended runs, checked against Anthropic's own pages.</p><div class="foot"><span class="tag kind">Guides</span>- <a class="more" href="/blog/how-to-use-claude-code-plan-mode/" aria-label="Read: How to Use Claude Code Plan Mode">Read →</a>+ <a class="more" href="/blog/claude-code-max-plan-tips/" aria-label="Read: How to Get the Most Out of Your Claude Code Max Plan">Read →</a></div></div></article><article class="card t-guides">- <a class="thumb t-guides" href="/blog/how-to-add-an-mcp-server-to-claude-code/" aria-hidden="true" tabindex="-1"><img src="/blog/assets/media/how-to-add-an-mcp-server-to-claude-code/hero.png" alt="" loading="lazy" decoding="async" /></a>+ <a class="thumb t-guides" href="/blog/codex-max-plan-tips/" aria-hidden="true" tabindex="-1"><img src="/blog/assets/media/codex-max-plan-tips/hero.png" alt="" loading="lazy" decoding="async" /></a><div class="body"><div class="meta">- <time datetime="2026-09-10">Sep 10, 2026</time>+ <time datetime="2026-09-14">Sep 14, 2026</time><span class="dot" aria-hidden="true"></span><span>5 min</span></div>- <h3><a href="/blog/how-to-add-an-mcp-server-to-claude-code/">How to Add an MCP Server to Claude Code</a></h3>- <p class="dek">The claude mcp add command, its scope flag, editing .mcp.json by hand, and how Munder Difflin's Capabilities screen grants an MCP server to one agent at a time.</p>+ <h3><a href="/blog/codex-max-plan-tips/">How to Make the Most of Your Codex Max Plan</a></h3>+ <p class="dek">There is no Codex Max plan. What ChatGPT Pro 5x and 20x give you in Codex, how the weekly limit works, and how to stretch it.</p><div class="foot"><span class="tag kind">Guides</span>- <a class="more" href="/blog/how-to-add-an-mcp-server-to-claude-code/" aria-label="Read: How to Add an MCP Server to Claude Code">Read →</a>+ <a class="more" href="/blog/codex-max-plan-tips/" aria-label="Read: How to Make the Most of Your Codex Max Plan">Read →</a></div></div></article><article class="card t-guides">- <a class="thumb t-guides" href="/blog/command-center-guide/" aria-hidden="true" tabindex="-1"><img src="/blog/assets/media/command-center-guide/hero.png" alt="" loading="lazy" decoding="async" /></a>+ <a class="thumb t-guides" href="/blog/how-to-use-claude-code-plan-mode/" aria-hidden="true" tabindex="-1"><img src="/blog/assets/media/how-to-use-claude-code-plan-mode/hero.png" alt="" loading="lazy" decoding="async" /></a><div class="body"><div class="meta">- <time datetime="2026-07-03">Jul 3, 2026</time>+ <time datetime="2026-09-11">Sep 11, 2026</time><span class="dot" aria-hidden="true"></span>- <span>4 min</span>+ <span>5 min</span></div>- <h3><a href="/blog/command-center-guide/">The Command Center: Kanban, Fleet and Budgets in One Place</a></h3>- <p class="dek">A guide to Munder Difflin's Command Center in 0.5.2: the kanban with task dependencies, the ask me tab, triggers, memory, live token use against each agent's budget, and when to watch the board instead of the floor.</p>+ <h3><a href="/blog/how-to-use-claude-code-plan-mode/">How to Use Claude Code Plan Mode</a></h3>+ <p class="dek">How Claude Code's plan mode works: turning it on, what it blocks, what a real headless plan mode run prints, and how to leave it.</p><div class="foot"><span class="tag kind">Guides</span>- <a class="more" href="/blog/command-center-guide/" aria-label="Read: The Command Center: Kanban, Fleet and Budgets in One Place">Read →</a>+ <a class="more" href="/blog/how-to-use-claude-code-plan-mode/" aria-label="Read: How to Use Claude Code Plan Mode">Read →</a></div></div></article>diff --git a/docs/blog/claude-code-automation-while-you-sleep/index.html b/docs/blog/claude-code-automation-while-you-sleep/index.htmlindex ff2d2caf..a256ade9 100644--- a/docs/blog/claude-code-automation-while-you-sleep/index.html+++ b/docs/blog/claude-code-automation-while-you-sleep/index.html@@ -327,50 +327,50 @@ while you sleep; it’s free and open source.</p><h2>Related in Guides</h2><div class="post-grid"><article class="card t-guides">- <a class="thumb t-guides" href="/blog/how-to-use-claude-code-plan-mode/" aria-hidden="true" tabindex="-1"><img src="/blog/assets/media/how-to-use-claude-code-plan-mode/hero.png" alt="" loading="lazy" decoding="async" /></a>+ <a class="thumb t-guides" href="/blog/claude-code-max-plan-tips/" aria-hidden="true" tabindex="-1"><img src="/blog/assets/media/claude-code-max-plan-tips/hero.png" alt="" loading="lazy" decoding="async" /></a><div class="body"><div class="meta">- <time datetime="2026-09-11">Sep 11, 2026</time>+ <time datetime="2026-09-14">Sep 14, 2026</time><span class="dot" aria-hidden="true"></span><span>5 min</span></div>- <h3><a href="/blog/how-to-use-claude-code-plan-mode/">How to Use Claude Code Plan Mode</a></h3>- <p class="dek">How Claude Code's plan mode works: turning it on, what it blocks, what a real headless plan mode run prints, and how to leave it.</p>+ <h3><a href="/blog/claude-code-max-plan-tips/">How to Get the Most Out of Your Claude Code Max Plan</a></h3>+ <p class="dek">Stretch a Claude Code Max plan: model choice, context hygiene, prompt caching, subagents and unattended runs, checked against Anthropic's own pages.</p><div class="foot"><span class="tag kind">Guides</span>- <a class="more" href="/blog/how-to-use-claude-code-plan-mode/" aria-label="Read: How to Use Claude Code Plan Mode">Read →</a>+ <a class="more" href="/blog/claude-code-max-plan-tips/" aria-label="Read: How to Get the Most Out of Your Claude Code Max Plan">Read →</a></div></div></article><article class="card t-guides">- <a class="thumb t-guides" href="/blog/how-to-add-an-mcp-server-to-claude-code/" aria-hidden="true" tabindex="-1"><img src="/blog/assets/media/how-to-add-an-mcp-server-to-claude-code/hero.png" alt="" loading="lazy" decoding="async" /></a>+ <a class="thumb t-guides" href="/blog/codex-max-plan-tips/" aria-hidden="true" tabindex="-1"><img src="/blog/assets/media/codex-max-plan-tips/hero.png" alt="" loading="lazy" decoding="async" /></a><div class="body"><div class="meta">- <time datetime="2026-09-10">Sep 10, 2026</time>+ <time datetime="2026-09-14">Sep 14, 2026</time><span class="dot" aria-hidden="true"></span><span>5 min</span></div>- <h3><a href="/blog/how-to-add-an-mcp-server-to-claude-code/">How to Add an MCP Server to Claude Code</a></h3>- <p class="dek">The claude mcp add command, its scope flag, editing .mcp.json by hand, and how Munder Difflin's Capabilities screen grants an MCP server to one agent at a time.</p>+ <h3><a href="/blog/codex-max-plan-tips/">How to Make the Most of Your Codex Max Plan</a></h3>+ <p class="dek">There is no Codex Max plan. What ChatGPT Pro 5x and 20x give you in Codex, how the weekly limit works, and how to stretch it.</p><div class="foot"><span class="tag kind">Guides</span>- <a class="more" href="/blog/how-to-add-an-mcp-server-to-claude-code/" aria-label="Read: How to Add an MCP Server to Claude Code">Read →</a>+ <a class="more" href="/blog/codex-max-plan-tips/" aria-label="Read: How to Make the Most of Your Codex Max Plan">Read →</a></div></div></article><article class="card t-guides">- <a class="thumb t-guides" href="/blog/command-center-guide/" aria-hidden="true" tabindex="-1"><img src="/blog/assets/media/command-center-guide/hero.png" alt="" loading="lazy" decoding="async" /></a>+ <a class="thumb t-guides" href="/blog/how-to-use-claude-code-plan-mode/" aria-hidden="true" tabindex="-1"><img src="/blog/assets/media/how-to-use-claude-code-plan-mode/hero.png" alt="" loading="lazy" decoding="async" /></a><div class="body"><div class="meta">- <time datetime="2026-07-03">Jul 3, 2026</time>+ <time datetime="2026-09-11">Sep 11, 2026</time><span class="dot" aria-hidden="true"></span>- <span>4 min</span>+ <span>5 min</span></div>- <h3><a href="/blog/command-center-guide/">The Command Center: Kanban, Fleet and Budgets in One Place</a></h3>- <p class="dek">A guide to Munder Difflin's Command Center in 0.5.2: the kanban with task dependencies, the ask me tab, triggers, memory, live token use against each agent's budget, and when to watch the board instead of the floor.</p>+ <h3><a href="/blog/how-to-use-claude-code-plan-mode/">How to Use Claude Code Plan Mode</a></h3>+ <p class="dek">How Claude Code's plan mode works: turning it on, what it blocks, what a real headless plan mode run prints, and how to leave it.</p><div class="foot"><span class="tag kind">Guides</span>- <a class="more" href="/blog/command-center-guide/" aria-label="Read: The Command Center: Kanban, Fleet and Budgets in One Place">Read →</a>+ <a class="more" href="/blog/how-to-use-claude-code-plan-mode/" aria-label="Read: How to Use Claude Code Plan Mode">Read →</a></div></div></article>diff --git a/docs/blog/claude-code-max-plan-tips/index.html b/docs/blog/claude-code-max-plan-tips/index.htmlnew file mode 100644index 00000000..2456c98c--- /dev/null+++ b/docs/blog/claude-code-max-plan-tips/index.html@@ -0,0 +1,368 @@+<!doctype html>+<html lang="en">+<head>+<meta charset="UTF-8" />+<meta name="viewport" content="width=device-width, initial-scale=1.0" />+<title>How to Get the Most Out of Your Claude Code Max Plan — Munder Difflin Blog</title>+<meta name="description" content="Stretch a Claude Code Max plan: model choice, context hygiene, prompt caching, subagents and unattended runs, checked against Anthropic's own pages." />+<link rel="canonical" href="https://munderdiffl.in/blog/claude-code-max-plan-tips/" />++<link rel="icon" type="image/png" href="https://munderdiffl.in/logo.png" />+<link rel="apple-touch-icon" href="https://munderdiffl.in/logo.png" />+<meta name="theme-color" content="#F5F2E8" />++<!-- Open Graph -->+<meta property="og:site_name" content="Munder Difflin Blog" />+<meta property="og:type" content="article" />+<meta property="og:title" content="How to Get the Most Out of Your Claude Code Max Plan — Munder Difflin Blog" />+<meta property="og:description" content="Stretch a Claude Code Max plan: model choice, context hygiene, prompt caching, subagents and unattended runs, checked against Anthropic's own pages." />+<meta property="og:url" content="https://munderdiffl.in/blog/claude-code-max-plan-tips/" />+<meta property="og:image" content="https://munderdiffl.in/media/og.png" />+<meta property="og:locale" content="en_US" />+<meta property="article:published_time" content="2026-09-14T00:00:00.000Z" />+<meta property="article:author" content="Chaitanya Giri" />+<meta property="article:tag" content="Guides" />+<meta property="article:tag" content="Claude Code" />+<meta property="article:tag" content="Cost" />+<meta property="article:tag" content="Workflow" />+++<!-- Twitter -->+<meta name="twitter:card" content="summary_large_image" />+<meta name="twitter:title" content="How to Get the Most Out of Your Claude Code Max Plan — Munder Difflin Blog" />+<meta name="twitter:description" content="Stretch a Claude Code Max plan: model choice, context hygiene, prompt caching, subagents and unattended runs, checked against Anthropic's own pages." />+<meta name="twitter:image" content="https://munderdiffl.in/media/og.png" />++<link rel="alternate" type="application/atom+xml" title="Munder Difflin Blog" href="https://munderdiffl.in/blog/feed.xml" />+<link rel="preconnect" href="https://fonts.googleapis.com" />+<link rel="preconnect" href="https://fonts.gstatic.com" crossorigin />+<link href="https://fonts.googleapis.com/css2?family=Fraunces:opsz,[email protected],500;9..144,600;9..144,700;9..144,900&family=Source+Serif+4:opsz,[email protected],400;8..60,600;8..60,700&family=Space+Grotesk:wght@500;600;700&family=JetBrains+Mono:wght@400;600&display=swap" rel="stylesheet" />+<link rel="stylesheet" href="/blog/assets/blog-press.css" />++<script type="application/ld+json">+{+ "@context": "https://schema.org",+ "@type": "BlogPosting",+ "headline": "How to Get the Most Out of Your Claude Code Max Plan",+ "description": "Stretch a Claude Code Max plan: model choice, context hygiene, prompt caching, subagents and unattended runs, checked against Anthropic's own pages.",+ "image": ["https://munderdiffl.in/media/og.png"],+ "datePublished": "2026-09-14T00:00:00.000Z",+ "dateModified": "2026-09-14T00:00:00.000Z",+ "author": { "@type": "Person", "name": "Chaitanya Giri" },+ "publisher": {+ "@type": "Organization",+ "name": "Munder Difflin",+ "logo": { "@type": "ImageObject", "url": "https://munderdiffl.in/logo.png" }+ },+ "mainEntityOfPage": { "@type": "WebPage", "@id": "https://munderdiffl.in/blog/claude-code-max-plan-tips/" },+ "keywords": "how to get the most out of claude max, how to make the most of claude max, claude code max plan tips, how to maximize claude code usage, how to reduce claude code token usage, claude code usage limit reset, does claude code max have weekly limits",+ "articleSection": "Guides",+ "inLanguage": "en-US",+ "url": "https://munderdiffl.in/blog/claude-code-max-plan-tips/"+}+</script>+<script type="application/ld+json">+{+ "@context": "https://schema.org",+ "@type": "BreadcrumbList",+ "itemListElement": [+ { "@type": "ListItem", "position": 1, "name": "Home", "item": "https://munderdiffl.in/" },+ { "@type": "ListItem", "position": 2, "name": "Blog", "item": "https://munderdiffl.in/blog/" },+ { "@type": "ListItem", "position": 3, "name": "How to Get the Most Out of Your Claude Code Max Plan", "item": "https://munderdiffl.in/blog/claude-code-max-plan-tips/" }+ ]+}+</script>++<script type="application/ld+json">+{+ "@context": "https://schema.org",+ "@type": "FAQPage",+ "mainEntity": [+ { "@type": "Question", "name": "Does Claude Code Max have weekly limits?", "acceptedAnswer": { "@type": "Answer", "text": "Yes. Every Max plan has a session limit that resets every five hours and a weekly limit across all models that resets at a fixed time assigned to your account, per Anthropic's Max plan article as checked on 14 Sep 2026. Claude chat, Claude Code and the IDE extensions all draw from the same allowance." } },+ { "@type": "Question", "name": "Does Claude Code Max include Fable?", "acceptedAnswer": { "@type": "Answer", "text": "Yes. Anthropic's help article on Fable, updated 2 Sep 2026, says Fable 5 and Fable 5.1 are a standard part of Max, and you can spend up to half of your weekly limit on them at no extra cost. That half is a ceiling inside the same weekly allowance, not extra room. Past it you either pay with usage credits or switch to another model." } },+ { "@type": "Question", "name": "Is Claude Code Max unlimited?", "acceptedAnswer": { "@type": "Answer", "text": "No. Max 5x and Max 20x give five or twenty times Pro's usage per session, and Anthropic says it may limit usage in other ways too. If you turn on usage credits, work past the limit is billed at standard API rates, so decline them if you want to stay inside what the plan includes." } },+ { "@type": "Question", "name": "When does the Claude Code usage limit reset?", "acceptedAnswer": { "@type": "Answer", "text": "The session limit resets every five hours and the weekly limit at a fixed day and time assigned to your account. Run /usage in Claude Code or open Settings > Usage on claude.ai to see both reset times. In an interactive session, Claude Code 2.1.234 and later can wait for a session reset and then continue the task on its own." } },+ { "@type": "Question", "name": "Can you share a Claude Code Max plan?", "acceptedAnswer": { "@type": "Answer", "text": "No. Anthropic's Consumer Terms say you may not share your login or make your account available to anyone else, and its Claude Code legal page says advertised Pro and Max limits assume ordinary, individual use. A team that needs shared capacity should look at Team seats or an API key instead." } }++ ]+}+</script>+++<script>+ // Anonymous blog analytics (PostHog) — same posture as the main site and the+ // app's TELEMETRY.md: public write-only token ('' = inert), anonymous-only+ // (person_profiles 'never'), no autocapture/recording, DNT respected.+ (function () {+ var PH_KEY = 'phc_qJzsokwcbtTGHemnvywR3nSqivNNgMjHeNVEWkZNydFB';+ if (!PH_KEY || navigator.doNotTrack === '1') return;+ var s = document.createElement('script');+ s.async = true;+ s.src = 'https://us-assets.i.posthog.com/static/array.js';+ s.onload = function () {+ if (!window.posthog) return;+ window.posthog.init(PH_KEY, {+ api_host: 'https://us.i.posthog.com',+ person_profiles: 'never',+ autocapture: false,+ before_send: function (event) {+ // PostHog fills $ip from the connection unless the event carries one.+ // Null it here and disable the GeoIP lookup so no IP, city, postal+ // code or lat/long is ever derived or stored for this page view.+ if (event && event.properties) {+ event.properties.$ip = null;+ event.properties.$geoip_disable = true;+ }+ return event;+ },+ disable_session_recording: true,+ respect_dnt: true+ });+ };+ document.head.appendChild(s);+ })();+</script>+</head>+<body class="theme-press">+<a class="skip-link" href="#main">Skip to content</a>+<nav id="nav">+ <a class="brand" href="https://munderdiffl.in" aria-label="Munder Difflin home">+ <img class="brand-logo" src="https://munderdiffl.in/logo.png" width="1318" height="840" alt="Munder Difflin, Inc. — Multi-Agent Harness" />+ </a>+ <span class="spacer"></span>+ <div class="links">+ <a href="/blog/">Latest</a>+ <a href="/blog/topics/">Topics</a>+ <a href="/blog/about/">About</a>+ <a href="https://munderdiffl.in">↗ Product</a>+ </div>+ <div class="nav-actions">+ <a class="btn sm" href="https://munderdiffl.in/blog/feed.xml" aria-label="RSS feed">⤵ RSS</a>+ <a class="btn sm primary" href="https://munderdiffl.in/#install">⤓ Download</a>+ </div>+</nav>++<main id="main">++<article class="t-guides">+ <header class="post-head wrap">+ <nav class="crumbs" aria-label="Breadcrumb">+ <a href="/blog/">Blog</a>+ <span>/</span>+ <a href="/blog/topics/guides/">Guides</a>+ </nav>+ <h1>How to Get the Most Out of Your Claude Code Max Plan</h1>+ <p class="dek">Stretch a Claude Code Max plan: model choice, context hygiene, prompt caching, subagents and unattended runs, checked against Anthropic's own pages.</p>+ <div class="byline">+ <span class="av" aria-hidden="true">MD</span>+ <strong>Chaitanya Giri</strong>+ <span class="dot" aria-hidden="true">·</span>+ <time datetime="2026-09-14">Sep 14, 2026</time>+ <span class="dot" aria-hidden="true">·</span>+ <span>5 min read</span>+ <span class="tag kind">Guides</span>+ </div>+ </header>++ <div class="hero-wrap wrap"><figure class="fig fig-hero"><img src="/blog/assets/media/claude-code-max-plan-tips/hero.png" alt="A yellow cartoon character at a desk with an hourglass, stacked terminal windows, a wall calendar with ticks and a nearly full gauge" loading="lazy" decoding="async" /></figure></div>++ <div class="post-wrap wrap">+ <div class="prose">+ <p>To get the most out of Claude Max in Claude Code, spend the plan on work, not on rereading context. Pick the model per task, <code>/clear</code> between tasks, plan before big edits, keep sessions inside the one hour cache, and watch <code>/usage</code> so the weekly limit never surprises you. Anthropic’s figures below were checked on 14 Sep 2026.</p>+<p>Prices are in our post on <a href="/blog/how-much-does-claude-code-cost/">what Claude Code costs</a>, so this one sticks to using the plan well. If you already run more than one terminal, read <a href="/blog/manage-multiple-claude-code-sessions/">how to manage multiple Claude Code sessions</a> too, because every extra session draws from the same allowance.</p>+<h2 id="how-do-claude-max-usage-limits-work-in-claude-code" tabindex="-1">How do Claude Max usage limits work in Claude Code? <a class="anchor" href="#how-do-claude-max-usage-limits-work-in-claude-code" aria-hidden="true">#</a></h2>+<p>Two meters run at once: a session limit that resets every five hours, and a weekly limit. The weekly one covers all models and resets at a fixed time assigned to your account (<a href="https://support.claude.com/en/articles/11049741-what-is-the-max-plan">Anthropic, What is the Max plan</a>, checked 14 Sep 2026). Max 5x and Max 20x multiply Pro’s usage per session, and chat, Claude Code and the IDE extensions share one pool. Because both meters are shared across models, switching with <code>/model</code> does not bring back a spent session or week. The separate Opus and Sonnet family limits are different: switch outside that family and you keep working (Claude Code errors reference). Run <code>/usage</code> to see both bars and their reset times.</p>+<figure class="fig fig-inline"><img src="/blog/assets/media/claude-code-max-plan-tips/note-1.png" alt="An hourglass beside a seven day strip with some days filled in" loading="lazy" decoding="async" /></figure>+<h2 id="did-claude-code-weekly-limits-change-in-september-2026" tabindex="-1">Did Claude Code weekly limits change in September 2026? <a class="anchor" href="#did-claude-code-weekly-limits-change-in-september-2026" aria-hidden="true">#</a></h2>+<p>Yes, from 14 Sep 2026. On 29 Aug 2026 Anthropic’s <a href="https://x.com/ClaudeDevs/status/2093742321473065266">ClaudeDevs account</a> announced that from 14 Sep 2026 standard weekly limits in Claude Code rise permanently by 25%, with the temporary 50% increase staying until then. A follow up post in that thread on 29 Aug 2026 says this “works out to a 17% reduction in weekly limits on Claude Code” against the boosted limit.</p>+<h2 id="which-model-should-you-use-on-a-max-plan" tabindex="-1">Which model should you use on a Max plan? <a class="anchor" href="#which-model-should-you-use-on-a-max-plan" aria-hidden="true">#</a></h2>+<p>Match the model to the job, because model and effort both change how fast you use the limit. Claude Code starts Max accounts on Opus 5, while Anthropic’s cost docs say Sonnet handles most coding tasks well and costs less. Reserve Opus for architecture and hard debugging, or set <code>/model opusplan</code> so Opus plans and Sonnet executes, though each plan mode toggle then starts a fresh cache. Lower <code>/effort</code> for routine work; asking Opus at <code>max</code> effort to rename a variable is a very thorough way to spend a morning.</p>+<p>Fable needs a budget of its own. Anthropic’s <a href="https://support.claude.com/en/articles/15424964-claude-fable-models-on-your-plan">Fable help article</a>, updated 2 Sep 2026, says Max can spend up to 50% of its weekly limit on Fable 5 and 5.1, and those models use limits faster than the others. Save Fable for the long, ambiguous task, not the quick fix.</p>+<h2 id="how-do-you-stop-context-from-eating-the-plan" tabindex="-1">How do you stop context from eating the plan? <a class="anchor" href="#how-do-you-stop-context-from-eating-the-plan" aria-hidden="true">#</a></h2>+<p>Keep the conversation short, because Claude Code resends it with every request. Anthropic’s <a href="https://code.claude.com/docs/en/costs">cost management page</a> gives the levers:</p>+<ul>+<li><code>/clear</code> when you switch to unrelated work.</li>+<li><code>/compact Focus on the failing tests</code> at a natural break. Compaction reads the whole conversation, so on a cold cache it is a large request itself.</li>+<li>Keep <code>CLAUDE.md</code> under 200 lines and move workflow instructions into skills, which load only when used.</li>+<li>Run <code>/context</code> to see what is loaded, and disable MCP servers you are not using.</li>+</ul>+<p>Plan before editing. Shift+Tab into plan mode for anything that touches several files, press Escape the moment Claude heads the wrong way, and use <code>/rewind</code> instead of stacking “try again” on a bad attempt. Each retry rereads everything before it.</p>+<h2 id="does-prompt-caching-help-on-a-subscription" tabindex="-1">Does prompt caching help on a subscription? <a class="anchor" href="#does-prompt-caching-help-on-a-subscription" aria-hidden="true">#</a></h2>+<p>Yes, while the cache is warm. Claude Code’s prompt caching page says the main conversation gets a one hour cache on a subscription within plan usage, dropping to five minutes once you draw on usage credits, and subagents get five minutes. We checked by reading the <code>usage</code> fields Claude Code 2.1.270 writes to its session transcripts on our machine, with no cache settings changed. Across 27 requests in an orchestrating session, all 121,041 cache write tokens were one hour writes; a subagent it started wrote only five minute entries over 69 requests, and both read 96% to 98% of input from cache on 14 Sep 2026. To check yours, run <code>claude -p "hello" --output-format json</code> and read <code>usage.cache_creation</code>.</p>+<p>So come back inside the hour, or <code>/clear</code> and start fresh, rather than reheating a huge stale context. Switching model mid task rebuilds the cache, and on most models so does changing effort, so choose both at the start. Our guide to <a href="/blog/prompt-caching-for-ai-agents/">prompt caching for AI agents</a> explains why a stable prefix matters.</p>+<h2 id="are-subagents-cheaper-than-doing-it-yourself" tabindex="-1">Are subagents cheaper than doing it yourself? <a class="anchor" href="#are-subagents-cheaper-than-doing-it-yourself" aria-hidden="true">#</a></h2>+<p>Not automatically. Unless Claude or the subagent’s definition names a model, a subagent runs on your session’s model, which on Max is Opus 5 by default. Put <code>model: haiku</code> or <code>model: sonnet</code> in subagents that search, run tests or read logs. They still help: verbose output stays in the subagent and only a summary returns. Open <code>/usage</code> and press <code>w</code> to see how much of the last week went to subagents, skills and MCP servers.</p>+<h2 id="can-claude-code-keep-working-while-you-are-away" tabindex="-1">Can Claude Code keep working while you are away? <a class="anchor" href="#can-claude-code-keep-working-while-you-are-away" aria-hidden="true">#</a></h2>+<p>Yes, within limits. Since version 2.1.234, an interactive session signed in with a subscription waits out a usage limit and continues the task on its own. It still stops on permission prompts, re-arms at most twice in a row, and does not start a wait by itself for a reset more than 24 hours away, which a weekly limit often is. <code>/rate-limit-options</code> starts or cancels that wait.</p>+<p>Background sessions and <code>/loop</code> tasks draw on the same subscription, and each scheduled fire resends the full context. Claude Code’s agent view docs put it plainly: ten agents in parallel use quota roughly ten times as fast as one.</p>+<figure class="fig fig-inline"><img src="/blog/assets/media/claude-code-max-plan-tips/note-2.png" alt="A yellow cartoon character conducting three terminal windows, each with a small bean typing inside" loading="lazy" decoding="async" /></figure>+<p>If you run several agents anyway, Munder Difflin, which we build, runs them from one desktop app. Each Claude Code agent is the real CLI in its own terminal on the login you already use, and you can give every agent its own model and token cap and put prompts on a schedule. One warning for Max users: in 0.5.2 the default agent model is Fable 5, so change it under Settings > Agents & Models if your weekly limit matters. It does not raise Anthropic’s limits either.</p>+<h2 id="can-you-share-a-max-plan-or-use-it-in-other-apps" tabindex="-1">Can you share a Max plan or use it in other apps? <a class="anchor" href="#can-you-share-a-max-plan-or-use-it-in-other-apps" aria-hidden="true">#</a></h2>+<p>No to sharing, and be careful with other apps. Anthropic’s Consumer Terms bar sharing your login, and its <a href="https://code.claude.com/docs/en/legal-and-compliance">Claude Code legal page</a> says advertised Pro and Max limits assume ordinary, individual use. The same page bars third party developers from routing requests through Pro or Max credentials for their users, and says that does not stop you signing in to the unmodified Claude Code binary with your own subscription. If you are building a product on Claude, it points you to an API key.</p>++++ <section class="faq" aria-label="Frequently asked questions">+ <h2 id="faq">FAQ</h2>++ <div class="qa">+ <p class="q">Does Claude Code Max have weekly limits?</p>+ <p class="a">Yes. Every Max plan has a session limit that resets every five hours and a weekly limit across all models that resets at a fixed time assigned to your account, per Anthropic's Max plan article as checked on 14 Sep 2026. Claude chat, Claude Code and the IDE extensions all draw from the same allowance.</p>+ </div>++ <div class="qa">+ <p class="q">Does Claude Code Max include Fable?</p>+ <p class="a">Yes. Anthropic's help article on Fable, updated 2 Sep 2026, says Fable 5 and Fable 5.1 are a standard part of Max, and you can spend up to half of your weekly limit on them at no extra cost. That half is a ceiling inside the same weekly allowance, not extra room. Past it you either pay with usage credits or switch to another model.</p>+ </div>++ <div class="qa">+ <p class="q">Is Claude Code Max unlimited?</p>+ <p class="a">No. Max 5x and Max 20x give five or twenty times Pro's usage per session, and Anthropic says it may limit usage in other ways too. If you turn on usage credits, work past the limit is billed at standard API rates, so decline them if you want to stay inside what the plan includes.</p>+ </div>++ <div class="qa">+ <p class="q">When does the Claude Code usage limit reset?</p>+ <p class="a">The session limit resets every five hours and the weekly limit at a fixed day and time assigned to your account. Run /usage in Claude Code or open Settings > Usage on claude.ai to see both reset times. In an interactive session, Claude Code 2.1.234 and later can wait for a session reset and then continue the task on its own.</p>+ </div>++ <div class="qa">+ <p class="q">Can you share a Claude Code Max plan?</p>+ <p class="a">No. Anthropic's Consumer Terms say you may not share your login or make your account available to anyone else, and its Claude Code legal page says advertised Pro and Max limits assume ordinary, individual use. A team that needs shared capacity should look at Team seats or an API key instead.</p>+ </div>++ </section>++++ <hr />+ <div class="share">+ <span class="lbl">Tags</span>+ <a class="tag" href="/blog/tags/guides/">Guides</a><a class="tag" href="/blog/tags/claude-code/">Claude Code</a><a class="tag" href="/blog/tags/cost/">Cost</a><a class="tag" href="/blog/tags/workflow/">Workflow</a>+ </div>++ </div>+++ <aside class="toc-rail" aria-label="Table of contents">+ <div class="tt">On this page</div>+ <ol>+ <li class="lvl-2"><a href="#how-do-claude-max-usage-limits-work-in-claude-code">How do Claude Max usage limits work in Claude Code?</a></li><li class="lvl-2"><a href="#did-claude-code-weekly-limits-change-in-september-2026">Did Claude Code weekly limits change in September 2026?</a></li><li class="lvl-2"><a href="#which-model-should-you-use-on-a-max-plan">Which model should you use on a Max plan?</a></li><li class="lvl-2"><a href="#how-do-you-stop-context-from-eating-the-plan">How do you stop context from eating the plan?</a></li><li class="lvl-2"><a href="#does-prompt-caching-help-on-a-subscription">Does prompt caching help on a subscription?</a></li><li class="lvl-2"><a href="#are-subagents-cheaper-than-doing-it-yourself">Are subagents cheaper than doing it yourself?</a></li><li class="lvl-2"><a href="#can-claude-code-keep-working-while-you-are-away">Can Claude Code keep working while you are away?</a></li><li class="lvl-2"><a href="#can-you-share-a-max-plan-or-use-it-in-other-apps">Can you share a Max plan or use it in other apps?</a></li>+ </ol>+ </aside>++ </div>++ <footer class="post-foot wrap"><div class="prevnext">+ <a class="pn prev" href="/blog/codex-max-plan-tips/"><span class="k">← Older</span><span class="t">How to Make the Most of Your Codex Max Plan</span></a>+ <span></span>+ </div>+ <section class="related">+ <h2>Related in Guides</h2>+ <div class="post-grid">+ <article class="card t-guides">+ <a class="thumb t-guides" href="/blog/codex-max-plan-tips/" aria-hidden="true" tabindex="-1"><img src="/blog/assets/media/codex-max-plan-tips/hero.png" alt="" loading="lazy" decoding="async" /></a>+ <div class="body">+ <div class="meta">+ <time datetime="2026-09-14">Sep 14, 2026</time>+ <span class="dot" aria-hidden="true"></span>+ <span>5 min</span>+ </div>+ <h3><a href="/blog/codex-max-plan-tips/">How to Make the Most of Your Codex Max Plan</a></h3>+ <p class="dek">There is no Codex Max plan. What ChatGPT Pro 5x and 20x give you in Codex, how the weekly limit works, and how to stretch it.</p>+ <div class="foot">+ <span class="tag kind">Guides</span>+ <a class="more" href="/blog/codex-max-plan-tips/" aria-label="Read: How to Make the Most of Your Codex Max Plan">Read →</a>+ </div>+ </div>+</article>+<article class="card t-guides">+ <a class="thumb t-guides" href="/blog/how-to-use-claude-code-plan-mode/" aria-hidden="true" tabindex="-1"><img src="/blog/assets/media/how-to-use-claude-code-plan-mode/hero.png" alt="" loading="lazy" decoding="async" /></a>+ <div class="body">+ <div class="meta">+ <time datetime="2026-09-11">Sep 11, 2026</time>+ <span class="dot" aria-hidden="true"></span>+ <span>5 min</span>+ </div>+ <h3><a href="/blog/how-to-use-claude-code-plan-mode/">How to Use Claude Code Plan Mode</a></h3>+ <p class="dek">How Claude Code's plan mode works: turning it on, what it blocks, what a real headless plan mode run prints, and how to leave it.</p>+ <div class="foot">+ <span class="tag kind">Guides</span>+ <a class="more" href="/blog/how-to-use-claude-code-plan-mode/" aria-label="Read: How to Use Claude Code Plan Mode">Read →</a>+ </div>+ </div>+</article>+<article class="card t-guides">+ <a class="thumb t-guides" href="/blog/how-to-add-an-mcp-server-to-claude-code/" aria-hidden="true" tabindex="-1"><img src="/blog/assets/media/how-to-add-an-mcp-server-to-claude-code/hero.png" alt="" loading="lazy" decoding="async" /></a>+ <div class="body">+ <div class="meta">+ <time datetime="2026-09-10">Sep 10, 2026</time>+ <span class="dot" aria-hidden="true"></span>+ <span>5 min</span>+ </div>+ <h3><a href="/blog/how-to-add-an-mcp-server-to-claude-code/">How to Add an MCP Server to Claude Code</a></h3>+ <p class="dek">The claude mcp add command, its scope flag, editing .mcp.json by hand, and how Munder Difflin's Capabilities screen grants an MCP server to one agent at a time.</p>+ <div class="foot">+ <span class="tag kind">Guides</span>+ <a class="more" href="/blog/how-to-add-an-mcp-server-to-claude-code/" aria-label="Read: How to Add an MCP Server to Claude Code">Read →</a>+ </div>+ </div>+</article>++ </div>+ </section>++ </footer>+</article>++</main>+<footer class="site-foot">+ <div class="wrap">+ <div class="foot-top">+ <a class="foot-brand brand" href="https://munderdiffl.in" aria-label="Munder Difflin home">+ <img class="brand-logo" src="https://munderdiffl.in/logo.png" width="1318" height="840" alt="Munder Difflin, Inc. — Multi-Agent Harness" />+ </a>+ <div class="foot-links">+ <a href="/blog/">Latest</a>+ <a href="/blog/topics/">Topics</a>+ <a href="/blog/about/">About</a>+ <a href="https://munderdiffl.in/blog/feed.xml">RSS</a>+ <a href="https://github.com/chaitanyagiri/munder-difflin">GitHub</a>+ <a href="https://munderdiffl.in">munderdiffl.in ↗</a>+ </div>+ </div>+ <div class="foot-meta">+ © 2026 Munder Difflin · Local-first · MIT-licensed ·+ Built on <a href="https://munderdiffl.in">Electron, React, Pixi.js, xterm.js & node-pty</a>.+ Run an office of agents while you sleep.+ </div>+ </div>+</footer>++<script>+ // sticky-nav border on scroll+ (function () {+ var nav = document.getElementById('nav');+ if (!nav) return;+ var onScroll = function () { nav.classList.toggle('scrolled', window.scrollY > 8); };+ onScroll(); window.addEventListener('scroll', onScroll, { passive: true });+ })();+ // YouTube click-to-load: thumbnail button → youtube-nocookie iframe+ (function () {+ document.addEventListener('click', function (e) {+ var btn = e.target.closest('.yt-load');+ if (!btn) return;+ var box = btn.closest('.yt');+ var id = box && box.getAttribute('data-yt');+ if (!id) return;+ var frame = document.createElement('iframe');+ frame.src = 'https://www.youtube-nocookie.com/embed/' + id + '?autoplay=1';+ frame.title = box.getAttribute('data-title') || 'YouTube video';+ frame.allow = 'accelerometer; autoplay; clipboard-write; encrypted-media; gyroscope; picture-in-picture; web-share';+ frame.setAttribute('allowfullscreen', '');+ box.replaceChildren(frame);+ });+ })();+</script>++</body>+</html>diff --git a/docs/blog/claude-code-multi-agent-setup-tutorial/index.html b/docs/blog/claude-code-multi-agent-setup-tutorial/index.htmlindex 8af82743..b2a3d7ce 100644--- a/docs/blog/claude-code-multi-agent-setup-tutorial/index.html+++ b/docs/blog/claude-code-multi-agent-setup-tutorial/index.html@@ -316,50 +316,50 @@ coordinated team of Claude Code agents — it’s free, local, and open source.<<h2>Related in Guides</h2><div class="post-grid"><article class="card t-guides">- <a class="thumb t-guides" href="/blog/how-to-use-claude-code-plan-mode/" aria-hidden="true" tabindex="-1"><img src="/blog/assets/media/how-to-use-claude-code-plan-mode/hero.png" alt="" loading="lazy" decoding="async" /></a>+ <a class="thumb t-guides" href="/blog/claude-code-max-plan-tips/" aria-hidden="true" tabindex="-1"><img src="/blog/assets/media/claude-code-max-plan-tips/hero.png" alt="" loading="lazy" decoding="async" /></a><div class="body"><div class="meta">- <time datetime="2026-09-11">Sep 11, 2026</time>+ <time datetime="2026-09-14">Sep 14, 2026</time><span class="dot" aria-hidden="true"></span><span>5 min</span></div>- <h3><a href="/blog/how-to-use-claude-code-plan-mode/">How to Use Claude Code Plan Mode</a></h3>- <p class="dek">How Claude Code's plan mode works: turning it on, what it blocks, what a real headless plan mode run prints, and how to leave it.</p>+ <h3><a href="/blog/claude-code-max-plan-tips/">How to Get the Most Out of Your Claude Code Max Plan</a></h3>+ <p class="dek">Stretch a Claude Code Max plan: model choice, context hygiene, prompt caching, subagents and unattended runs, checked against Anthropic's own pages.</p><div class="foot"><span class="tag kind">Guides</span>- <a class="more" href="/blog/how-to-use-claude-code-plan-mode/" aria-label="Read: How to Use Claude Code Plan Mode">Read →</a>+ <a class="more" href="/blog/claude-code-max-plan-tips/" aria-label="Read: How to Get the Most Out of Your Claude Code Max Plan">Read →</a></div></div></article><article class="card t-guides">- <a class="thumb t-guides" href="/blog/how-to-add-an-mcp-server-to-claude-code/" aria-hidden="true" tabindex="-1"><img src="/blog/assets/media/how-to-add-an-mcp-server-to-claude-code/hero.png" alt="" loading="lazy" decoding="async" /></a>+ <a class="thumb t-guides" href="/blog/codex-max-plan-tips/" aria-hidden="true" tabindex="-1"><img src="/blog/assets/media/codex-max-plan-tips/hero.png" alt="" loading="lazy" decoding="async" /></a><div class="body"><div class="meta">- <time datetime="2026-09-10">Sep 10, 2026</time>+ <time datetime="2026-09-14">Sep 14, 2026</time><span class="dot" aria-hidden="true"></span><span>5 min</span></div>- <h3><a href="/blog/how-to-add-an-mcp-server-to-claude-code/">How to Add an MCP Server to Claude Code</a></h3>- <p class="dek">The claude mcp add command, its scope flag, editing .mcp.json by hand, and how Munder Difflin's Capabilities screen grants an MCP server to one agent at a time.</p>+ <h3><a href="/blog/codex-max-plan-tips/">How to Make the Most of Your Codex Max Plan</a></h3>+ <p class="dek">There is no Codex Max plan. What ChatGPT Pro 5x and 20x give you in Codex, how the weekly limit works, and how to stretch it.</p><div class="foot"><span class="tag kind">Guides</span>- <a class="more" href="/blog/how-to-add-an-mcp-server-to-claude-code/" aria-label="Read: How to Add an MCP Server to Claude Code">Read →</a>+ <a class="more" href="/blog/codex-max-plan-tips/" aria-label="Read: How to Make the Most of Your Codex Max Plan">Read →</a></div></div></article><article class="card t-guides">- <a class="thumb t-guides" href="/blog/command-center-guide/" aria-hidden="true" tabindex="-1"><img src="/blog/assets/media/command-center-guide/hero.png" alt="" loading="lazy" decoding="async" /></a>+ <a class="thumb t-guides" href="/blog/how-to-use-claude-code-plan-mode/" aria-hidden="true" tabindex="-1"><img src="/blog/assets/media/how-to-use-claude-code-plan-mode/hero.png" alt="" loading="lazy" decoding="async" /></a><div class="body"><div class="meta">- <time datetime="2026-07-03">Jul 3, 2026</time>+ <time datetime="2026-09-11">Sep 11, 2026</time><span class="dot" aria-hidden="true"></span>- <span>4 min</span>+ <span>5 min</span></div>- <h3><a href="/blog/command-center-guide/">The Command Center: Kanban, Fleet and Budgets in One Place</a></h3>- <p class="dek">A guide to Munder Difflin's Command Center in 0.5.2: the kanban with task dependencies, the ask me tab, triggers, memory, live token use against each agent's budget, and when to watch the board instead of the floor.</p>+ <h3><a href="/blog/how-to-use-claude-code-plan-mode/">How to Use Claude Code Plan Mode</a></h3>+ <p class="dek">How Claude Code's plan mode works: turning it on, what it blocks, what a real headless plan mode run prints, and how to leave it.</p><div class="foot"><span class="tag kind">Guides</span>- <a class="more" href="/blog/command-center-guide/" aria-label="Read: The Command Center: Kanban, Fleet and Budgets in One Place">Read →</a>+ <a class="more" href="/blog/how-to-use-claude-code-plan-mode/" aria-label="Read: How to Use Claude Code Plan Mode">Read →</a></div></div></article>diff --git a/docs/blog/claude-code-orchestration-tools-compared/index.html b/docs/blog/claude-code-orchestration-tools-compared/index.htmlindex 49aa643a..04a8fc30 100644--- a/docs/blog/claude-code-orchestration-tools-compared/index.html+++ b/docs/blog/claude-code-orchestration-tools-compared/index.html@@ -315,50 +315,50 @@ Linux.</p><h2>Related in Comparisons</h2><div class="post-grid"><article class="card t-comparisons">- <a class="thumb t-comparisons" href="/blog/codex-cli-vs-claude-code/" aria-hidden="true" tabindex="-1"><img src="/blog/assets/media/codex-cli-vs-claude-code/hero.png" alt="" loading="lazy" decoding="async" /></a>+ <a class="thumb t-comparisons" href="/blog/grok-bot-alternatives/" aria-hidden="true" tabindex="-1"><img src="/blog/assets/media/grok-bot-alternatives/hero.png" alt="" loading="lazy" decoding="async" /></a><div class="body"><div class="meta">- <time datetime="2026-09-10">Sep 10, 2026</time>+ <time datetime="2026-09-14">Sep 14, 2026</time><span class="dot" aria-hidden="true"></span><span>5 min</span></div>- <h3><a href="/blog/codex-cli-vs-claude-code/">Codex CLI vs Claude Code</a></h3>- <p class="dek">Codex CLI and Claude Code compared firsthand: sandbox and approval flags, AGENTS.md vs CLAUDE.md, real pricing, and where each terminal agent wins.</p>+ <h3><a href="/blog/grok-bot-alternatives/">Grok Bot Alternatives: Six Picks, Grouped by What You Want</a></h3>+ <p class="dek">Grok Bot runs every Bot on one shared cloud computer. Six alternatives checked on 14 Sep 2026, grouped by hosting, privacy and model choice.</p><div class="foot"><span class="tag kind">Comparisons</span>- <a class="more" href="/blog/codex-cli-vs-claude-code/" aria-label="Read: Codex CLI vs Claude Code">Read →</a>+ <a class="more" href="/blog/grok-bot-alternatives/" aria-label="Read: Grok Bot Alternatives: Six Picks, Grouped by What You Want">Read →</a></div></div></article><article class="card t-comparisons">- <a class="thumb t-comparisons" href="/blog/qm-vs-munder-difflin/" aria-hidden="true" tabindex="-1"><img src="/blog/assets/media/qm-vs-munder-difflin/hero.png" alt="" loading="lazy" decoding="async" /></a>+ <a class="thumb t-comparisons" href="/blog/herdr-alternatives/" aria-hidden="true" tabindex="-1"><img src="/blog/assets/media/herdr-alternatives/hero.png" alt="" loading="lazy" decoding="async" /></a><div class="body"><div class="meta">- <time datetime="2026-08-06">Aug 6, 2026</time>+ <time datetime="2026-09-14">Sep 14, 2026</time><span class="dot" aria-hidden="true"></span>- <span>4 min</span>+ <span>5 min</span></div>- <h3><a href="/blog/qm-vs-munder-difflin/">qm vs Munder Difflin: YC's Multiplayer Harness or an Office of Your Clones?</a></h3>- <p class="dek">An honest September 2026 comparison of YC's qm and Munder Difflin. qm is a multiplayer agent harness a company deploys for Slack and the web. Munder Difflin runs an office of your clones on your own machine, with Teams to connect them.</p>+ <h3><a href="/blog/herdr-alternatives/">Herdr Alternatives: What to Pick and Who Each One Fits</a></h3>+ <p class="dek">Herdr alternatives checked on 14 Sep 2026: tmux, Claude Squad, cmux, Orca, Conductor, Superset, Emdash and Munder Difflin, and who each fits.</p><div class="foot"><span class="tag kind">Comparisons</span>- <a class="more" href="/blog/qm-vs-munder-difflin/" aria-label="Read: qm vs Munder Difflin: YC's Multiplayer Harness or an Office of Your Clones?">Read →</a>+ <a class="more" href="/blog/herdr-alternatives/" aria-label="Read: Herdr Alternatives: What to Pick and Who Each One Fits">Read →</a></div></div></article><article class="card t-comparisons">- <a class="thumb t-comparisons" href="/blog/crewai-autogen-vs-a-local-agent-harness/" aria-hidden="true" tabindex="-1"><img src="/blog/assets/media/crewai-autogen-vs-a-local-agent-harness/hero.png" alt="" loading="lazy" decoding="async" /></a>+ <a class="thumb t-comparisons" href="/blog/omniagent-alternatives/" aria-hidden="true" tabindex="-1"><span class="thumb-ph"><em class="ph-glyph" aria-hidden="true">✶</em><span>COMPARISONS</span></span></a><div class="body"><div class="meta">- <time datetime="2026-07-03">Jul 3, 2026</time>+ <time datetime="2026-09-14">Sep 14, 2026</time><span class="dot" aria-hidden="true"></span><span>5 min</span></div>- <h3><a href="/blog/crewai-autogen-vs-a-local-agent-harness/">CrewAI and AutoGen vs a Local Agent Harness: Framework or App?</a></h3>- <p class="dek">CrewAI, AutoGen (now Microsoft Agent Framework), and LangGraph are frameworks — Python you write to build your own agent system. A multi-agent harness is an app you download that runs a team on your repos today. Here's how to tell which one you actually need.</p>+ <h3><a href="/blog/omniagent-alternatives/">OmniAgent Alternatives: What to Use Instead of Databricks Omnigent</a></h3>+ <p class="dek">OmniAgent is really Omnigent, the open source meta harness from Databricks. Alternatives checked on 14 Sep 2026, and who each one fits.</p><div class="foot"><span class="tag kind">Comparisons</span>- <a class="more" href="/blog/crewai-autogen-vs-a-local-agent-harness/" aria-label="Read: CrewAI and AutoGen vs a Local Agent Harness: Framework or App?">Read →</a>+ <a class="more" href="/blog/omniagent-alternatives/" aria-label="Read: OmniAgent Alternatives: What to Use Instead of Databricks Omnigent">Read →</a></div></div></article>diff --git a/docs/blog/claude-code-subagents-vs-multi-agent-harness/index.html b/docs/blog/claude-code-subagents-vs-multi-agent-harness/index.htmlindex a5a81b27..160006f4 100644--- a/docs/blog/claude-code-subagents-vs-multi-agent-harness/index.html+++ b/docs/blog/claude-code-subagents-vs-multi-agent-harness/index.html@@ -358,50 +358,50 @@ open source.</p><h2>Related in Guides</h2><div class="post-grid"><article class="card t-guides">- <a class="thumb t-guides" href="/blog/how-to-use-claude-code-plan-mode/" aria-hidden="true" tabindex="-1"><img src="/blog/assets/media/how-to-use-claude-code-plan-mode/hero.png" alt="" loading="lazy" decoding="async" /></a>+ <a class="thumb t-guides" href="/blog/claude-code-max-plan-tips/" aria-hidden="true" tabindex="-1"><img src="/blog/assets/media/claude-code-max-plan-tips/hero.png" alt="" loading="lazy" decoding="async" /></a><div class="body"><div class="meta">- <time datetime="2026-09-11">Sep 11, 2026</time>+ <time datetime="2026-09-14">Sep 14, 2026</time><span class="dot" aria-hidden="true"></span><span>5 min</span></div>- <h3><a href="/blog/how-to-use-claude-code-plan-mode/">How to Use Claude Code Plan Mode</a></h3>- <p class="dek">How Claude Code's plan mode works: turning it on, what it blocks, what a real headless plan mode run prints, and how to leave it.</p>+ <h3><a href="/blog/claude-code-max-plan-tips/">How to Get the Most Out of Your Claude Code Max Plan</a></h3>+ <p class="dek">Stretch a Claude Code Max plan: model choice, context hygiene, prompt caching, subagents and unattended runs, checked against Anthropic's own pages.</p><div class="foot"><span class="tag kind">Guides</span>- <a class="more" href="/blog/how-to-use-claude-code-plan-mode/" aria-label="Read: How to Use Claude Code Plan Mode">Read →</a>+ <a class="more" href="/blog/claude-code-max-plan-tips/" aria-label="Read: How to Get the Most Out of Your Claude Code Max Plan">Read →</a></div></div></article><article class="card t-guides">- <a class="thumb t-guides" href="/blog/how-to-add-an-mcp-server-to-claude-code/" aria-hidden="true" tabindex="-1"><img src="/blog/assets/media/how-to-add-an-mcp-server-to-claude-code/hero.png" alt="" loading="lazy" decoding="async" /></a>+ <a class="thumb t-guides" href="/blog/codex-max-plan-tips/" aria-hidden="true" tabindex="-1"><img src="/blog/assets/media/codex-max-plan-tips/hero.png" alt="" loading="lazy" decoding="async" /></a><div class="body"><div class="meta">- <time datetime="2026-09-10">Sep 10, 2026</time>+ <time datetime="2026-09-14">Sep 14, 2026</time><span class="dot" aria-hidden="true"></span><span>5 min</span></div>- <h3><a href="/blog/how-to-add-an-mcp-server-to-claude-code/">How to Add an MCP Server to Claude Code</a></h3>- <p class="dek">The claude mcp add command, its scope flag, editing .mcp.json by hand, and how Munder Difflin's Capabilities screen grants an MCP server to one agent at a time.</p>+ <h3><a href="/blog/codex-max-plan-tips/">How to Make the Most of Your Codex Max Plan</a></h3>+ <p class="dek">There is no Codex Max plan. What ChatGPT Pro 5x and 20x give you in Codex, how the weekly limit works, and how to stretch it.</p><div class="foot"><span class="tag kind">Guides</span>- <a class="more" href="/blog/how-to-add-an-mcp-server-to-claude-code/" aria-label="Read: How to Add an MCP Server to Claude Code">Read →</a>+ <a class="more" href="/blog/codex-max-plan-tips/" aria-label="Read: How to Make the Most of Your Codex Max Plan">Read →</a></div></div></article><article class="card t-guides">- <a class="thumb t-guides" href="/blog/command-center-guide/" aria-hidden="true" tabindex="-1"><img src="/blog/assets/media/command-center-guide/hero.png" alt="" loading="lazy" decoding="async" /></a>+ <a class="thumb t-guides" href="/blog/how-to-use-claude-code-plan-mode/" aria-hidden="true" tabindex="-1"><img src="/blog/assets/media/how-to-use-claude-code-plan-mode/hero.png" alt="" loading="lazy" decoding="async" /></a><div class="body"><div class="meta">- <time datetime="2026-07-03">Jul 3, 2026</time>+ <time datetime="2026-09-11">Sep 11, 2026</time><span class="dot" aria-hidden="true"></span>- <span>4 min</span>+ <span>5 min</span></div>- <h3><a href="/blog/command-center-guide/">The Command Center: Kanban, Fleet and Budgets in One Place</a></h3>- <p class="dek">A guide to Munder Difflin's Command Center in 0.5.2: the kanban with task dependencies, the ask me tab, triggers, memory, live token use against each agent's budget, and when to watch the board instead of the floor.</p>+ <h3><a href="/blog/how-to-use-claude-code-plan-mode/">How to Use Claude Code Plan Mode</a></h3>+ <p class="dek">How Claude Code's plan mode works: turning it on, what it blocks, what a real headless plan mode run prints, and how to leave it.</p><div class="foot"><span class="tag kind">Guides</span>- <a class="more" href="/blog/command-center-guide/" aria-label="Read: The Command Center: Kanban, Fleet and Budgets in One Place">Read →</a>+ <a class="more" href="/blog/how-to-use-claude-code-plan-mode/" aria-label="Read: How to Use Claude Code Plan Mode">Read →</a></div></div></article>diff --git a/docs/blog/claude-squad-alternative/index.html b/docs/blog/claude-squad-alternative/index.htmlindex 917f0ca9..f43c0339 100644--- a/docs/blog/claude-squad-alternative/index.html+++ b/docs/blog/claude-squad-alternative/index.html@@ -251,50 +251,50 @@ on macOS, Windows, and Linux.</p><h2>Related in Comparisons</h2><div class="post-grid"><article class="card t-comparisons">- <a class="thumb t-comparisons" href="/blog/codex-cli-vs-claude-code/" aria-hidden="true" tabindex="-1"><img src="/blog/assets/media/codex-cli-vs-claude-code/hero.png" alt="" loading="lazy" decoding="async" /></a>+ <a class="thumb t-comparisons" href="/blog/grok-bot-alternatives/" aria-hidden="true" tabindex="-1"><img src="/blog/assets/media/grok-bot-alternatives/hero.png" alt="" loading="lazy" decoding="async" /></a><div class="body"><div class="meta">- <time datetime="2026-09-10">Sep 10, 2026</time>+ <time datetime="2026-09-14">Sep 14, 2026</time><span class="dot" aria-hidden="true"></span><span>5 min</span></div>- <h3><a href="/blog/codex-cli-vs-claude-code/">Codex CLI vs Claude Code</a></h3>- <p class="dek">Codex CLI and Claude Code compared firsthand: sandbox and approval flags, AGENTS.md vs CLAUDE.md, real pricing, and where each terminal agent wins.</p>+ <h3><a href="/blog/grok-bot-alternatives/">Grok Bot Alternatives: Six Picks, Grouped by What You Want</a></h3>+ <p class="dek">Grok Bot runs every Bot on one shared cloud computer. Six alternatives checked on 14 Sep 2026, grouped by hosting, privacy and model choice.</p><div class="foot"><span class="tag kind">Comparisons</span>- <a class="more" href="/blog/codex-cli-vs-claude-code/" aria-label="Read: Codex CLI vs Claude Code">Read →</a>+ <a class="more" href="/blog/grok-bot-alternatives/" aria-label="Read: Grok Bot Alternatives: Six Picks, Grouped by What You Want">Read →</a></div></div></article><article class="card t-comparisons">- <a class="thumb t-comparisons" href="/blog/qm-vs-munder-difflin/" aria-hidden="true" tabindex="-1"><img src="/blog/assets/media/qm-vs-munder-difflin/hero.png" alt="" loading="lazy" decoding="async" /></a>+ <a class="thumb t-comparisons" href="/blog/herdr-alternatives/" aria-hidden="true" tabindex="-1"><img src="/blog/assets/media/herdr-alternatives/hero.png" alt="" loading="lazy" decoding="async" /></a><div class="body"><div class="meta">- <time datetime="2026-08-06">Aug 6, 2026</time>+ <time datetime="2026-09-14">Sep 14, 2026</time><span class="dot" aria-hidden="true"></span>- <span>4 min</span>+ <span>5 min</span></div>- <h3><a href="/blog/qm-vs-munder-difflin/">qm vs Munder Difflin: YC's Multiplayer Harness or an Office of Your Clones?</a></h3>- <p class="dek">An honest September 2026 comparison of YC's qm and Munder Difflin. qm is a multiplayer agent harness a company deploys for Slack and the web. Munder Difflin runs an office of your clones on your own machine, with Teams to connect them.</p>+ <h3><a href="/blog/herdr-alternatives/">Herdr Alternatives: What to Pick and Who Each One Fits</a></h3>+ <p class="dek">Herdr alternatives checked on 14 Sep 2026: tmux, Claude Squad, cmux, Orca, Conductor, Superset, Emdash and Munder Difflin, and who each fits.</p><div class="foot"><span class="tag kind">Comparisons</span>- <a class="more" href="/blog/qm-vs-munder-difflin/" aria-label="Read: qm vs Munder Difflin: YC's Multiplayer Harness or an Office of Your Clones?">Read →</a>+ <a class="more" href="/blog/herdr-alternatives/" aria-label="Read: Herdr Alternatives: What to Pick and Who Each One Fits">Read →</a></div></div></article><article class="card t-comparisons">- <a class="thumb t-comparisons" href="/blog/crewai-autogen-vs-a-local-agent-harness/" aria-hidden="true" tabindex="-1"><img src="/blog/assets/media/crewai-autogen-vs-a-local-agent-harness/hero.png" alt="" loading="lazy" decoding="async" /></a>+ <a class="thumb t-comparisons" href="/blog/omniagent-alternatives/" aria-hidden="true" tabindex="-1"><span class="thumb-ph"><em class="ph-glyph" aria-hidden="true">✶</em><span>COMPARISONS</span></span></a><div class="body"><div class="meta">- <time datetime="2026-07-03">Jul 3, 2026</time>+ <time datetime="2026-09-14">Sep 14, 2026</time><span class="dot" aria-hidden="true"></span><span>5 min</span></div>- <h3><a href="/blog/crewai-autogen-vs-a-local-agent-harness/">CrewAI and AutoGen vs a Local Agent Harness: Framework or App?</a></h3>- <p class="dek">CrewAI, AutoGen (now Microsoft Agent Framework), and LangGraph are frameworks — Python you write to build your own agent system. A multi-agent harness is an app you download that runs a team on your repos today. Here's how to tell which one you actually need.</p>+ <h3><a href="/blog/omniagent-alternatives/">OmniAgent Alternatives: What to Use Instead of Databricks Omnigent</a></h3>+ <p class="dek">OmniAgent is really Omnigent, the open source meta harness from Databricks. Alternatives checked on 14 Sep 2026, and who each one fits.</p><div class="foot"><span class="tag kind">Comparisons</span>- <a class="more" href="/blog/crewai-autogen-vs-a-local-agent-harness/" aria-label="Read: CrewAI and AutoGen vs a Local Agent Harness: Framework or App?">Read →</a>+ <a class="more" href="/blog/omniagent-alternatives/" aria-label="Read: OmniAgent Alternatives: What to Use Instead of Databricks Omnigent">Read →</a></div></div></article>diff --git a/docs/blog/claude-squad-vs-munder-difflin/index.html b/docs/blog/claude-squad-vs-munder-difflin/index.htmlindex bd760024..d96ff8da 100644--- a/docs/blog/claude-squad-vs-munder-difflin/index.html+++ b/docs/blog/claude-squad-vs-munder-difflin/index.html@@ -340,50 +340,50 @@ local-first.</p><h2>Related in Comparisons</h2><div class="post-grid"><article class="card t-comparisons">- <a class="thumb t-comparisons" href="/blog/codex-cli-vs-claude-code/" aria-hidden="true" tabindex="-1"><img src="/blog/assets/media/codex-cli-vs-claude-code/hero.png" alt="" loading="lazy" decoding="async" /></a>+ <a class="thumb t-comparisons" href="/blog/grok-bot-alternatives/" aria-hidden="true" tabindex="-1"><img src="/blog/assets/media/grok-bot-alternatives/hero.png" alt="" loading="lazy" decoding="async" /></a><div class="body"><div class="meta">- <time datetime="2026-09-10">Sep 10, 2026</time>+ <time datetime="2026-09-14">Sep 14, 2026</time><span class="dot" aria-hidden="true"></span><span>5 min</span></div>- <h3><a href="/blog/codex-cli-vs-claude-code/">Codex CLI vs Claude Code</a></h3>- <p class="dek">Codex CLI and Claude Code compared firsthand: sandbox and approval flags, AGENTS.md vs CLAUDE.md, real pricing, and where each terminal agent wins.</p>+ <h3><a href="/blog/grok-bot-alternatives/">Grok Bot Alternatives: Six Picks, Grouped by What You Want</a></h3>+ <p class="dek">Grok Bot runs every Bot on one shared cloud computer. Six alternatives checked on 14 Sep 2026, grouped by hosting, privacy and model choice.</p><div class="foot"><span class="tag kind">Comparisons</span>- <a class="more" href="/blog/codex-cli-vs-claude-code/" aria-label="Read: Codex CLI vs Claude Code">Read →</a>+ <a class="more" href="/blog/grok-bot-alternatives/" aria-label="Read: Grok Bot Alternatives: Six Picks, Grouped by What You Want">Read →</a></div></div></article><article class="card t-comparisons">- <a class="thumb t-comparisons" href="/blog/qm-vs-munder-difflin/" aria-hidden="true" tabindex="-1"><img src="/blog/assets/media/qm-vs-munder-difflin/hero.png" alt="" loading="lazy" decoding="async" /></a>+ <a class="thumb t-comparisons" href="/blog/herdr-alternatives/" aria-hidden="true" tabindex="-1"><img src="/blog/assets/media/herdr-alternatives/hero.png" alt="" loading="lazy" decoding="async" /></a><div class="body"><div class="meta">- <time datetime="2026-08-06">Aug 6, 2026</time>+ <time datetime="2026-09-14">Sep 14, 2026</time><span class="dot" aria-hidden="true"></span>- <span>4 min</span>+ <span>5 min</span></div>- <h3><a href="/blog/qm-vs-munder-difflin/">qm vs Munder Difflin: YC's Multiplayer Harness or an Office of Your Clones?</a></h3>- <p class="dek">An honest September 2026 comparison of YC's qm and Munder Difflin. qm is a multiplayer agent harness a company deploys for Slack and the web. Munder Difflin runs an office of your clones on your own machine, with Teams to connect them.</p>+ <h3><a href="/blog/herdr-alternatives/">Herdr Alternatives: What to Pick and Who Each One Fits</a></h3>+ <p class="dek">Herdr alternatives checked on 14 Sep 2026: tmux, Claude Squad, cmux, Orca, Conductor, Superset, Emdash and Munder Difflin, and who each fits.</p><div class="foot"><span class="tag kind">Comparisons</span>- <a class="more" href="/blog/qm-vs-munder-difflin/" aria-label="Read: qm vs Munder Difflin: YC's Multiplayer Harness or an Office of Your Clones?">Read →</a>+ <a class="more" href="/blog/herdr-alternatives/" aria-label="Read: Herdr Alternatives: What to Pick and Who Each One Fits">Read →</a></div></div></article><article class="card t-comparisons">- <a class="thumb t-comparisons" href="/blog/crewai-autogen-vs-a-local-agent-harness/" aria-hidden="true" tabindex="-1"><img src="/blog/assets/media/crewai-autogen-vs-a-local-agent-harness/hero.png" alt="" loading="lazy" decoding="async" /></a>+ <a class="thumb t-comparisons" href="/blog/omniagent-alternatives/" aria-hidden="true" tabindex="-1"><span class="thumb-ph"><em class="ph-glyph" aria-hidden="true">✶</em><span>COMPARISONS</span></span></a><div class="body"><div class="meta">- <time datetime="2026-07-03">Jul 3, 2026</time>+ <time datetime="2026-09-14">Sep 14, 2026</time><span class="dot" aria-hidden="true"></span><span>5 min</span></div>- <h3><a href="/blog/crewai-autogen-vs-a-local-agent-harness/">CrewAI and AutoGen vs a Local Agent Harness: Framework or App?</a></h3>- <p class="dek">CrewAI, AutoGen (now Microsoft Agent Framework), and LangGraph are frameworks — Python you write to build your own agent system. A multi-agent harness is an app you download that runs a team on your repos today. Here's how to tell which one you actually need.</p>+ <h3><a href="/blog/omniagent-alternatives/">OmniAgent Alternatives: What to Use Instead of Databricks Omnigent</a></h3>+ <p class="dek">OmniAgent is really Omnigent, the open source meta harness from Databricks. Alternatives checked on 14 Sep 2026, and who each one fits.</p><div class="foot"><span class="tag kind">Comparisons</span>- <a class="more" href="/blog/crewai-autogen-vs-a-local-agent-harness/" aria-label="Read: CrewAI and AutoGen vs a Local Agent Harness: Framework or App?">Read →</a>+ <a class="more" href="/blog/omniagent-alternatives/" aria-label="Read: OmniAgent Alternatives: What to Use Instead of Databricks Omnigent">Read →</a></div></div></article>diff --git a/docs/blog/cline-vs-munder-difflin/index.html b/docs/blog/cline-vs-munder-difflin/index.htmlindex 0c69c120..508a9a24 100644--- a/docs/blog/cline-vs-munder-difflin/index.html+++ b/docs/blog/cline-vs-munder-difflin/index.html@@ -331,50 +331,50 @@ licensed.</p><h2>Related in Comparisons</h2><div class="post-grid"><article class="card t-comparisons">- <a class="thumb t-comparisons" href="/blog/codex-cli-vs-claude-code/" aria-hidden="true" tabindex="-1"><img src="/blog/assets/media/codex-cli-vs-claude-code/hero.png" alt="" loading="lazy" decoding="async" /></a>+ <a class="thumb t-comparisons" href="/blog/grok-bot-alternatives/" aria-hidden="true" tabindex="-1"><img src="/blog/assets/media/grok-bot-alternatives/hero.png" alt="" loading="lazy" decoding="async" /></a><div class="body"><div class="meta">- <time datetime="2026-09-10">Sep 10, 2026</time>+ <time datetime="2026-09-14">Sep 14, 2026</time><span class="dot" aria-hidden="true"></span><span>5 min</span></div>- <h3><a href="/blog/codex-cli-vs-claude-code/">Codex CLI vs Claude Code</a></h3>- <p class="dek">Codex CLI and Claude Code compared firsthand: sandbox and approval flags, AGENTS.md vs CLAUDE.md, real pricing, and where each terminal agent wins.</p>+ <h3><a href="/blog/grok-bot-alternatives/">Grok Bot Alternatives: Six Picks, Grouped by What You Want</a></h3>+ <p class="dek">Grok Bot runs every Bot on one shared cloud computer. Six alternatives checked on 14 Sep 2026, grouped by hosting, privacy and model choice.</p><div class="foot"><span class="tag kind">Comparisons</span>- <a class="more" href="/blog/codex-cli-vs-claude-code/" aria-label="Read: Codex CLI vs Claude Code">Read →</a>+ <a class="more" href="/blog/grok-bot-alternatives/" aria-label="Read: Grok Bot Alternatives: Six Picks, Grouped by What You Want">Read →</a></div></div></article><article class="card t-comparisons">- <a class="thumb t-comparisons" href="/blog/qm-vs-munder-difflin/" aria-hidden="true" tabindex="-1"><img src="/blog/assets/media/qm-vs-munder-difflin/hero.png" alt="" loading="lazy" decoding="async" /></a>+ <a class="thumb t-comparisons" href="/blog/herdr-alternatives/" aria-hidden="true" tabindex="-1"><img src="/blog/assets/media/herdr-alternatives/hero.png" alt="" loading="lazy" decoding="async" /></a><div class="body"><div class="meta">- <time datetime="2026-08-06">Aug 6, 2026</time>+ <time datetime="2026-09-14">Sep 14, 2026</time><span class="dot" aria-hidden="true"></span>- <span>4 min</span>+ <span>5 min</span></div>- <h3><a href="/blog/qm-vs-munder-difflin/">qm vs Munder Difflin: YC's Multiplayer Harness or an Office of Your Clones?</a></h3>- <p class="dek">An honest September 2026 comparison of YC's qm and Munder Difflin. qm is a multiplayer agent harness a company deploys for Slack and the web. Munder Difflin runs an office of your clones on your own machine, with Teams to connect them.</p>+ <h3><a href="/blog/herdr-alternatives/">Herdr Alternatives: What to Pick and Who Each One Fits</a></h3>+ <p class="dek">Herdr alternatives checked on 14 Sep 2026: tmux, Claude Squad, cmux, Orca, Conductor, Superset, Emdash and Munder Difflin, and who each fits.</p><div class="foot"><span class="tag kind">Comparisons</span>- <a class="more" href="/blog/qm-vs-munder-difflin/" aria-label="Read: qm vs Munder Difflin: YC's Multiplayer Harness or an Office of Your Clones?">Read →</a>+ <a class="more" href="/blog/herdr-alternatives/" aria-label="Read: Herdr Alternatives: What to Pick and Who Each One Fits">Read →</a></div></div></article><article class="card t-comparisons">- <a class="thumb t-comparisons" href="/blog/crewai-autogen-vs-a-local-agent-harness/" aria-hidden="true" tabindex="-1"><img src="/blog/assets/media/crewai-autogen-vs-a-local-agent-harness/hero.png" alt="" loading="lazy" decoding="async" /></a>+ <a class="thumb t-comparisons" href="/blog/omniagent-alternatives/" aria-hidden="true" tabindex="-1"><span class="thumb-ph"><em class="ph-glyph" aria-hidden="true">✶</em><span>COMPARISONS</span></span></a><div class="body"><div class="meta">- <time datetime="2026-07-03">Jul 3, 2026</time>+ <time datetime="2026-09-14">Sep 14, 2026</time><span class="dot" aria-hidden="true"></span><span>5 min</span></div>- <h3><a href="/blog/crewai-autogen-vs-a-local-agent-harness/">CrewAI and AutoGen vs a Local Agent Harness: Framework or App?</a></h3>- <p class="dek">CrewAI, AutoGen (now Microsoft Agent Framework), and LangGraph are frameworks — Python you write to build your own agent system. A multi-agent harness is an app you download that runs a team on your repos today. Here's how to tell which one you actually need.</p>+ <h3><a href="/blog/omniagent-alternatives/">OmniAgent Alternatives: What to Use Instead of Databricks Omnigent</a></h3>+ <p class="dek">OmniAgent is really Omnigent, the open source meta harness from Databricks. Alternatives checked on 14 Sep 2026, and who each one fits.</p><div class="foot"><span class="tag kind">Comparisons</span>- <a class="more" href="/blog/crewai-autogen-vs-a-local-agent-harness/" aria-label="Read: CrewAI and AutoGen vs a Local Agent Harness: Framework or App?">Read →</a>+ <a class="more" href="/blog/omniagent-alternatives/" aria-label="Read: OmniAgent Alternatives: What to Use Instead of Databricks Omnigent">Read →</a></div></div></article>diff --git a/docs/blog/codex-cli-vs-claude-code/index.html b/docs/blog/codex-cli-vs-claude-code/index.htmlindex 26b4e325..f8b8cc8e 100644--- a/docs/blog/codex-cli-vs-claude-code/index.html+++ b/docs/blog/codex-cli-vs-claude-code/index.html@@ -180,7 +180,7 @@<p>The two overlap heavily in practice: coding standards, architecture notes, a review checklist. What differs is delivery. Neither CLI’s docs promise to read the other’s file, so a repo that runs both engines usually keeps both <code>AGENTS.md</code> and <code>CLAUDE.md</code>, or keeps one and symlinks the other to it.</p><figure class="fig fig-inline"><img src="/blog/assets/media/codex-cli-vs-claude-code/note-1.png" alt="Hand-drawn sketch from “Codex CLI vs Claude Code”" loading="lazy" decoding="async" /></figure><h2 id="is-codex-cli-free-to-use" tabindex="-1">Is Codex CLI free to use? <a class="anchor" href="#is-codex-cli-free-to-use" aria-hidden="true">#</a></h2>-<p>There’s a real free tier, but it’s capped. OpenAI’s Codex pricing page lists a Free plan at $0 a month for exploring Codex “on quick coding tasks,” a Go plan at $8 a month, and a Plus plan at $20 a month that adds cloud-based runs and the GPT-5.6 model family (<a href="https://developers.openai.com/codex/pricing">developers.openai.com/codex/pricing</a>, checked 10 Sep 2026). Claude Code has no equivalent free tier of its own: it authenticates against a paid Claude subscription or an Anthropic API key from the first session.</p>+<p>There’s a real free tier, but it’s capped. OpenAI’s Codex pricing page lists a Free plan at $0 a month for exploring Codex “on quick coding tasks,” a Go plan at $8 a month, and a Plus plan at $20 a month that adds cloud-based runs and the GPT-5.6 model family (<a href="https://developers.openai.com/codex/pricing">developers.openai.com/codex/pricing</a>, checked 10 Sep 2026). Claude Code has no equivalent free tier of its own: it authenticates against a paid Claude subscription or an Anthropic API key from the first session. If you already pay for ChatGPT Pro, see <a href="/blog/codex-max-plan-tips/">how to make the most of your Codex Max plan</a>.</p><h2 id="where-does-codex-cli-actually-win" tabindex="-1">Where does Codex CLI actually win? <a class="anchor" href="#where-does-codex-cli-actually-win" aria-hidden="true">#</a></h2><p>Two places: openness and cost of entry. The CLI itself is Apache-2.0 licensed and public on GitHub, so you can read exactly what the sandbox and approval code does instead of trusting a closed binary (<a href="https://github.com/openai/codex">github.com/openai/codex</a>, checked 10 Sep 2026), and the free plan above gets a curious developer to a real sandboxed agent at no cost. If you want a run that never pauses to ask, <code>--ask-for-approval never</code> is also a cleaner single flag than composing Claude Code’s mode and its skip flag together. None of that makes Codex CLI the better tool in general. It makes it the better tool when auditability and a no-cost start matter most.</p><figure class="fig fig-inline"><img src="/blog/assets/media/codex-cli-vs-claude-code/note-2.png" alt="Hand-drawn sketch from “Codex CLI vs Claude Code”" loading="lazy" decoding="async" /></figure>@@ -255,50 +255,50 @@ rereads. If you already pay for Claude, that is a lot of control for no extra se<h2>Related in Comparisons</h2><div class="post-grid"><article class="card t-comparisons">- <a class="thumb t-comparisons" href="/blog/qm-vs-munder-difflin/" aria-hidden="true" tabindex="-1"><img src="/blog/assets/media/qm-vs-munder-difflin/hero.png" alt="" loading="lazy" decoding="async" /></a>+ <a class="thumb t-comparisons" href="/blog/grok-bot-alternatives/" aria-hidden="true" tabindex="-1"><img src="/blog/assets/media/grok-bot-alternatives/hero.png" alt="" loading="lazy" decoding="async" /></a><div class="body"><div class="meta">- <time datetime="2026-08-06">Aug 6, 2026</time>+ <time datetime="2026-09-14">Sep 14, 2026</time><span class="dot" aria-hidden="true"></span>- <span>4 min</span>+ <span>5 min</span></div>- <h3><a href="/blog/qm-vs-munder-difflin/">qm vs Munder Difflin: YC's Multiplayer Harness or an Office of Your Clones?</a></h3>- <p class="dek">An honest September 2026 comparison of YC's qm and Munder Difflin. qm is a multiplayer agent harness a company deploys for Slack and the web. Munder Difflin runs an office of your clones on your own machine, with Teams to connect them.</p>+ <h3><a href="/blog/grok-bot-alternatives/">Grok Bot Alternatives: Six Picks, Grouped by What You Want</a></h3>+ <p class="dek">Grok Bot runs every Bot on one shared cloud computer. Six alternatives checked on 14 Sep 2026, grouped by hosting, privacy and model choice.</p><div class="foot"><span class="tag kind">Comparisons</span>- <a class="more" href="/blog/qm-vs-munder-difflin/" aria-label="Read: qm vs Munder Difflin: YC's Multiplayer Harness or an Office of Your Clones?">Read →</a>+ <a class="more" href="/blog/grok-bot-alternatives/" aria-label="Read: Grok Bot Alternatives: Six Picks, Grouped by What You Want">Read →</a></div></div></article><article class="card t-comparisons">- <a class="thumb t-comparisons" href="/blog/crewai-autogen-vs-a-local-agent-harness/" aria-hidden="true" tabindex="-1"><img src="/blog/assets/media/crewai-autogen-vs-a-local-agent-harness/hero.png" alt="" loading="lazy" decoding="async" /></a>+ <a class="thumb t-comparisons" href="/blog/herdr-alternatives/" aria-hidden="true" tabindex="-1"><img src="/blog/assets/media/herdr-alternatives/hero.png" alt="" loading="lazy" decoding="async" /></a><div class="body"><div class="meta">- <time datetime="2026-07-03">Jul 3, 2026</time>+ <time datetime="2026-09-14">Sep 14, 2026</time><span class="dot" aria-hidden="true"></span><span>5 min</span></div>- <h3><a href="/blog/crewai-autogen-vs-a-local-agent-harness/">CrewAI and AutoGen vs a Local Agent Harness: Framework or App?</a></h3>- <p class="dek">CrewAI, AutoGen (now Microsoft Agent Framework), and LangGraph are frameworks — Python you write to build your own agent system. A multi-agent harness is an app you download that runs a team on your repos today. Here's how to tell which one you actually need.</p>+ <h3><a href="/blog/herdr-alternatives/">Herdr Alternatives: What to Pick and Who Each One Fits</a></h3>+ <p class="dek">Herdr alternatives checked on 14 Sep 2026: tmux, Claude Squad, cmux, Orca, Conductor, Superset, Emdash and Munder Difflin, and who each fits.</p><div class="foot"><span class="tag kind">Comparisons</span>- <a class="more" href="/blog/crewai-autogen-vs-a-local-agent-harness/" aria-label="Read: CrewAI and AutoGen vs a Local Agent Harness: Framework or App?">Read →</a>+ <a class="more" href="/blog/herdr-alternatives/" aria-label="Read: Herdr Alternatives: What to Pick and Who Each One Fits">Read →</a></div></div></article><article class="card t-comparisons">- <a class="thumb t-comparisons" href="/blog/github-copilot-cli-vs-claude-code-for-hive-work/" aria-hidden="true" tabindex="-1"><img src="/blog/assets/media/github-copilot-cli-vs-claude-code-for-hive-work/hero.png" alt="" loading="lazy" decoding="async" /></a>+ <a class="thumb t-comparisons" href="/blog/omniagent-alternatives/" aria-hidden="true" tabindex="-1"><span class="thumb-ph"><em class="ph-glyph" aria-hidden="true">✶</em><span>COMPARISONS</span></span></a><div class="body"><div class="meta">- <time datetime="2026-07-03">Jul 3, 2026</time>+ <time datetime="2026-09-14">Sep 14, 2026</time><span class="dot" aria-hidden="true"></span><span>5 min</span></div>- <h3><a href="/blog/github-copilot-cli-vs-claude-code-for-hive-work/">GitHub Copilot CLI vs Claude Code as Hive Workers</a></h3>- <p class="dek">How GitHub Copilot CLI and Claude Code behave as agent engines inside a multi-agent harness: hooks, inbox mail, orchestration, session lifecycle — and why the right answer is to run both.</p>+ <h3><a href="/blog/omniagent-alternatives/">OmniAgent Alternatives: What to Use Instead of Databricks Omnigent</a></h3>+ <p class="dek">OmniAgent is really Omnigent, the open source meta harness from Databricks. Alternatives checked on 14 Sep 2026, and who each one fits.</p><div class="foot"><span class="tag kind">Comparisons</span>- <a class="more" href="/blog/github-copilot-cli-vs-claude-code-for-hive-work/" aria-label="Read: GitHub Copilot CLI vs Claude Code as Hive Workers">Read →</a>+ <a class="more" href="/blog/omniagent-alternatives/" aria-label="Read: OmniAgent Alternatives: What to Use Instead of Databricks Omnigent">Read →</a></div></div></article>diff --git a/docs/blog/codex-max-plan-tips/index.html b/docs/blog/codex-max-plan-tips/index.htmlnew file mode 100644index 00000000..f4647220--- /dev/null+++ b/docs/blog/codex-max-plan-tips/index.html@@ -0,0 +1,377 @@+<!doctype html>+<html lang="en">+<head>+<meta charset="UTF-8" />+<meta name="viewport" content="width=device-width, initial-scale=1.0" />+<title>How to Make the Most of Your Codex Max Plan — Munder Difflin Blog</title>+<meta name="description" content="There is no Codex Max plan. What ChatGPT Pro 5x and 20x give you in Codex, how the weekly limit works, and how to stretch it." />+<link rel="canonical" href="https://munderdiffl.in/blog/codex-max-plan-tips/" />++<link rel="icon" type="image/png" href="https://munderdiffl.in/logo.png" />+<link rel="apple-touch-icon" href="https://munderdiffl.in/logo.png" />+<meta name="theme-color" content="#F5F2E8" />++<!-- Open Graph -->+<meta property="og:site_name" content="Munder Difflin Blog" />+<meta property="og:type" content="article" />+<meta property="og:title" content="How to Make the Most of Your Codex Max Plan — Munder Difflin Blog" />+<meta property="og:description" content="There is no Codex Max plan. What ChatGPT Pro 5x and 20x give you in Codex, how the weekly limit works, and how to stretch it." />+<meta property="og:url" content="https://munderdiffl.in/blog/codex-max-plan-tips/" />+<meta property="og:image" content="https://munderdiffl.in/media/og.png" />+<meta property="og:locale" content="en_US" />+<meta property="article:published_time" content="2026-09-14T00:00:00.000Z" />+<meta property="article:author" content="Chaitanya Giri" />+<meta property="article:tag" content="Guides" />+<meta property="article:tag" content="Codex" />+<meta property="article:tag" content="Cost" />+<meta property="article:tag" content="Model Routing" />+++<!-- Twitter -->+<meta name="twitter:card" content="summary_large_image" />+<meta name="twitter:title" content="How to Make the Most of Your Codex Max Plan — Munder Difflin Blog" />+<meta name="twitter:description" content="There is no Codex Max plan. What ChatGPT Pro 5x and 20x give you in Codex, how the weekly limit works, and how to stretch it." />+<meta name="twitter:image" content="https://munderdiffl.in/media/og.png" />++<link rel="alternate" type="application/atom+xml" title="Munder Difflin Blog" href="https://munderdiffl.in/blog/feed.xml" />+<link rel="preconnect" href="https://fonts.googleapis.com" />+<link rel="preconnect" href="https://fonts.gstatic.com" crossorigin />+<link href="https://fonts.googleapis.com/css2?family=Fraunces:opsz,[email protected],500;9..144,600;9..144,700;9..144,900&family=Source+Serif+4:opsz,[email protected],400;8..60,600;8..60,700&family=Space+Grotesk:wght@500;600;700&family=JetBrains+Mono:wght@400;600&display=swap" rel="stylesheet" />+<link rel="stylesheet" href="/blog/assets/blog-press.css" />++<script type="application/ld+json">+{+ "@context": "https://schema.org",+ "@type": "BlogPosting",+ "headline": "How to Make the Most of Your Codex Max Plan",+ "description": "There is no Codex Max plan. What ChatGPT Pro 5x and 20x give you in Codex, how the weekly limit works, and how to stretch it.",+ "image": ["https://munderdiffl.in/media/og.png"],+ "datePublished": "2026-09-14T00:00:00.000Z",+ "dateModified": "2026-09-14T00:00:00.000Z",+ "author": { "@type": "Person", "name": "Chaitanya Giri" },+ "publisher": {+ "@type": "Organization",+ "name": "Munder Difflin",+ "logo": { "@type": "ImageObject", "url": "https://munderdiffl.in/logo.png" }+ },+ "mainEntityOfPage": { "@type": "WebPage", "@id": "https://munderdiffl.in/blog/codex-max-plan-tips/" },+ "keywords": "codex max plan, how to make the most of codex, codex max plan usage, chatgpt pro codex usage limits, does codex have weekly limits, how to check codex limit usage, how to reduce codex token usage",+ "articleSection": "Guides",+ "inLanguage": "en-US",+ "url": "https://munderdiffl.in/blog/codex-max-plan-tips/"+}+</script>+<script type="application/ld+json">+{+ "@context": "https://schema.org",+ "@type": "BreadcrumbList",+ "itemListElement": [+ { "@type": "ListItem", "position": 1, "name": "Home", "item": "https://munderdiffl.in/" },+ { "@type": "ListItem", "position": 2, "name": "Blog", "item": "https://munderdiffl.in/blog/" },+ { "@type": "ListItem", "position": 3, "name": "How to Make the Most of Your Codex Max Plan", "item": "https://munderdiffl.in/blog/codex-max-plan-tips/" }+ ]+}+</script>++<script type="application/ld+json">+{+ "@context": "https://schema.org",+ "@type": "FAQPage",+ "mainEntity": [+ { "@type": "Question", "name": "Can I still buy ChatGPT Pro 20x for Codex?", "acceptedAnswer": { "@type": "Answer", "text": "Not as a new subscriber right now. OpenAI paused new sign-ups and upgrades to Pro $200, also called Pro 20x, on 10 Sep 2026, and existing subscriptions keep renewing. Pro $100 (Pro 5x) is still on sale. If your Pro $200 subscription lapses, you cannot buy it again until the pause lifts." } },+ { "@type": "Question", "name": "Is there a five hour limit on ChatGPT Pro for Codex?", "acceptedAnswer": { "@type": "Answer", "text": "No. OpenAI dropped the five hour window on 12 Jul 2026. On 25 Aug 2026 Thibault Sottiaux of the Codex team said it was coming back for Plus while Pro $100 and Pro $200 stay without it for the upcoming months, and on 31 Aug he said the Pro multiples apply to weekly limits. The weekly limit still applies, so check the usage dashboard for your reset time." } },+ { "@type": "Question", "name": "Does Codex code review count against my usage limit?", "acceptedAnswer": { "@type": "Answer", "text": "It depends on where the review runs. OpenAI's pricing page says reviews Codex runs through GitHub, such as tagging @codex on a pull request, count as Code Review usage, while reviews run locally or outside GitHub count toward your general limits. For local reviews, set review_model in config.toml to a smaller model." } },+ { "@type": "Question", "name": "What happens when I hit my Codex usage limit in the middle of a task?", "acceptedAnswer": { "@type": "Answer", "text": "Codex keeps working on the turn already in progress, subject to fair use limits, per OpenAI's pricing page checked 14 Sep 2026. After that, Plus and Pro users can buy credits without upgrading, use an available reset, or wait for the reset time shown on the usage page." } },+ { "@type": "Question", "name": "Does switching to a smaller model give me my Codex limit back?", "acceptedAnswer": { "@type": "Answer", "text": "No. OpenAI's help article on managing usage with GPT-6 Astra says switching models does not restore allowance in a shared usage pool. A smaller model only makes what is left go further, so switch while you are approaching the limit, not after you hit it." } }++ ]+}+</script>+++<script>+ // Anonymous blog analytics (PostHog) — same posture as the main site and the+ // app's TELEMETRY.md: public write-only token ('' = inert), anonymous-only+ // (person_profiles 'never'), no autocapture/recording, DNT respected.+ (function () {+ var PH_KEY = 'phc_qJzsokwcbtTGHemnvywR3nSqivNNgMjHeNVEWkZNydFB';+ if (!PH_KEY || navigator.doNotTrack === '1') return;+ var s = document.createElement('script');+ s.async = true;+ s.src = 'https://us-assets.i.posthog.com/static/array.js';+ s.onload = function () {+ if (!window.posthog) return;+ window.posthog.init(PH_KEY, {+ api_host: 'https://us.i.posthog.com',+ person_profiles: 'never',+ autocapture: false,+ before_send: function (event) {+ // PostHog fills $ip from the connection unless the event carries one.+ // Null it here and disable the GeoIP lookup so no IP, city, postal+ // code or lat/long is ever derived or stored for this page view.+ if (event && event.properties) {+ event.properties.$ip = null;+ event.properties.$geoip_disable = true;+ }+ return event;+ },+ disable_session_recording: true,+ respect_dnt: true+ });+ };+ document.head.appendChild(s);+ })();+</script>+</head>+<body class="theme-press">+<a class="skip-link" href="#main">Skip to content</a>+<nav id="nav">+ <a class="brand" href="https://munderdiffl.in" aria-label="Munder Difflin home">+ <img class="brand-logo" src="https://munderdiffl.in/logo.png" width="1318" height="840" alt="Munder Difflin, Inc. — Multi-Agent Harness" />+ </a>+ <span class="spacer"></span>+ <div class="links">+ <a href="/blog/">Latest</a>+ <a href="/blog/topics/">Topics</a>+ <a href="/blog/about/">About</a>+ <a href="https://munderdiffl.in">↗ Product</a>+ </div>+ <div class="nav-actions">+ <a class="btn sm" href="https://munderdiffl.in/blog/feed.xml" aria-label="RSS feed">⤵ RSS</a>+ <a class="btn sm primary" href="https://munderdiffl.in/#install">⤓ Download</a>+ </div>+</nav>++<main id="main">++<article class="t-guides">+ <header class="post-head wrap">+ <nav class="crumbs" aria-label="Breadcrumb">+ <a href="/blog/">Blog</a>+ <span>/</span>+ <a href="/blog/topics/guides/">Guides</a>+ </nav>+ <h1>How to Make the Most of Your Codex Max Plan</h1>+ <p class="dek">There is no Codex Max plan. What ChatGPT Pro 5x and 20x give you in Codex, how the weekly limit works, and how to stretch it.</p>+ <div class="byline">+ <span class="av" aria-hidden="true">MD</span>+ <strong>Chaitanya Giri</strong>+ <span class="dot" aria-hidden="true">·</span>+ <time datetime="2026-09-14">Sep 14, 2026</time>+ <span class="dot" aria-hidden="true">·</span>+ <span>5 min read</span>+ <span class="tag kind">Guides</span>+ </div>+ </header>++ <div class="hero-wrap wrap"><figure class="fig fig-hero"><img src="/blog/assets/media/codex-max-plan-tips/hero.png" alt="A yellow cartoon character turning a big dial all the way up at a workbench while paper planes fly from a laptop to a cloud" loading="lazy" decoding="async" /></figure></div>++ <div class="post-wrap wrap">+ <div class="prose">+ <p>OpenAI has no plan called Codex Max. The plan people mean is ChatGPT Pro, which comes as Pro 5x at $100 a month or Pro 20x at $200 (OpenAI pricing, checked 14 Sep 2026). To make the most of it, run the smallest model and effort that works, keep one chat per task, and check <code>/status</code> before big jobs.</p>+<p>Three things muddy the name: Anthropic’s Claude Max plan, OpenAI’s older GPT-5.1-Codex-Max model, and Codex’s <strong>Max</strong> reasoning setting, which gives a model more time on one task (<a href="https://learn.chatgpt.com/docs/models">OpenAI, Models</a>). None is a Codex plan. Still choosing between tools? Our <a href="/blog/codex-cli-vs-claude-code/">Codex CLI vs Claude Code comparison</a> covers that. The habits in <a href="/blog/manage-multiple-claude-code-sessions/">managing several Claude Code sessions</a>, like one scope per session, carry straight over to Codex.</p>+<h2 id="is-there-a-codex-max-plan" tabindex="-1">Is there a Codex max plan? <a class="anchor" href="#is-there-a-codex-max-plan" aria-hidden="true">#</a></h2>+<p>No, but ChatGPT Pro is the closest thing, and its bigger tier just got harder to buy. OpenAI split Pro in two on 9 Apr 2026, adding a $100 tier with 5x the Codex usage of Plus and a launch boost to up to 10x that ran through 31 May 2026 (<a href="https://x.com/OpenAI/status/2042295688323875316">OpenAI on X</a>), so that boost is over.</p>+<p>Pro $200, labelled Pro 20x, is still the highest usage tier, but since 10 Sep 2026 OpenAI has paused new sign-ups and upgrades to it (<a href="https://help.openai.com/en/articles/9793128">About ChatGPT Pro tiers</a>). Existing subscriptions renew as usual. If you have Pro 20x, think before you cancel or downgrade: once it lapses, you cannot buy it back until the pause lifts.</p>+<h2 id="does-codex-have-weekly-limits" tabindex="-1">Does Codex have weekly limits? <a class="anchor" href="#does-codex-have-weekly-limits" aria-hidden="true">#</a></h2>+<p>Yes, and on Pro right now the weekly limit is the one that matters. OpenAI’s <a href="https://learn.chatgpt.com/docs/pricing">pricing page</a> says local messages and cloud chats share one allowance and that weekly limits may also apply. The same pool covers the Codex CLI, the IDE extension, the ChatGPT desktop app and ChatGPT Work.</p>+<p>Plus got its five hour window back in late August. On 25 Aug 2026, Thibault Sottiaux of OpenAI’s Codex team said Pro $100 and Pro $200 would keep running without one “for the upcoming months” (<a href="https://x.com/thsottiaux/status/2092058556707344708">post on X</a>). Nothing refills after five hours, so a long unattended run keeps drawing down the whole week. Budget by the week, not by the sitting.</p>+<h2 id="do-cloud-tasks-use-more-than-local-ones" tabindex="-1">Do cloud tasks use more than local ones? <a class="anchor" href="#do-cloud-tasks-use-more-than-local-ones" aria-hidden="true">#</a></h2>+<p>Often, yes. Cloud chats on ChatGPT plans run on GPT-5.6 Sol and may use more of your allowance than local messages, per OpenAI, and for now you can’t change their default model. Local work in the CLI or IDE runs whichever model you pick, including the cheaper Terra and Luna. Code review follows the same split: reviews Codex runs through GitHub count as Code Review usage, while a local <code>/review</code> counts toward your general limits.</p>+<figure class="fig fig-inline"><img src="/blog/assets/media/codex-max-plan-tips/note-1.png" alt="Parcels travelling between a laptop and a cloud along a dotted path, past a small meter" loading="lazy" decoding="async" /></figure>+<p>So send work to the cloud because you want it off your laptop and running in parallel, not to save usage. From the terminal, <code>codex cloud exec</code> needs an environment id and makes one attempt unless you ask for more. Checked on 14 Sep 2026 (output trimmed):</p>+<pre><code>$ codex --version+codex-cli 0.153.4+$ codex cloud exec --help+Usage: codex cloud exec [OPTIONS] --env <ENV_ID> [QUERY]+ --attempts <ATTEMPTS>+ Number of assistant attempts (best-of-N)+ [default: 1]+</code></pre>+<p>Leave <code>--attempts</code> at 1 unless you want to compare versions, since each attempt is its own run.</p>+<h2 id="how-do-i-check-my-codex-usage" tabindex="-1">How do I check my Codex usage? <a class="anchor" href="#how-do-i-check-my-codex-usage" aria-hidden="true">#</a></h2>+<p>Type <code>/status</code> in an active Codex CLI session, or open the usage dashboard at <code>chatgpt.com/codex/settings/usage</code>. OpenAI’s pricing page points to both and suggests checking the dashboard every week or two to learn your pace. In the CLI, <code>/statusline</code> can pin rate limits to the footer so you see them without asking.</p>+<p>If you run out mid task, Codex keeps working on that turn, subject to fair use, and Plus and Pro users can buy credits rather than upgrade. Better still, follow OpenAI’s advice and switch to a smaller model while you are approaching the limit.</p>+<h2 id="which-model-makes-codex-usage-last-longest" tabindex="-1">Which model makes Codex usage last longest? <a class="anchor" href="#which-model-makes-codex-usage-last-longest" aria-hidden="true">#</a></h2>+<p>GPT-5.6 Luna, by a wide margin. OpenAI’s Pro 5x estimates, checked 14 Sep 2026, are 25 to 225 local messages per five hours on GPT-6 Astra, 50 to 500 on Sol, 125 to 1,000 on Terra and 1,250 to 10,000 on Luna. Pro 20x is four times each. With no five hour cap on Pro, treat them as pace, not a limit. The models page says to use the lowest effort that gets the result, and that most tasks need neither Max nor Ultra, which splits work across subagents.</p>+<p>A workable split: Luna for clear, repeatable edits, Terra for everyday features, and Sol or Astra at low or medium effort for the bug that has beaten you twice. Switch with <code>/model</code> inside a chat, or pass <code>codex exec -m gpt-5.6-luna</code> for scripted runs. Fast mode is the quiet drain: on Astra and GPT-5.6 it bills at 2.5x, making replies quicker and your week shorter. If an old <code>config.toml</code> still pins <code>gpt-5.4</code>, change it to <code>gpt-5.6-terra</code>: GPT-5.4 left Codex for ChatGPT accounts on 31 Aug 2026.</p>+<figure class="fig fig-inline"><img src="/blog/assets/media/codex-max-plan-tips/note-2.png" alt="A yellow cartoon character reaching for a small screwdriver on a pegboard that also holds a wrench and a sledgehammer" loading="lazy" decoding="async" /></figure>+<h2 id="how-do-i-reduce-codex-token-usage" tabindex="-1">How do I reduce Codex token usage? <a class="anchor" href="#how-do-i-reduce-codex-token-usage" aria-hidden="true">#</a></h2>+<p>Cut what every turn has to carry. Your prompt, files, chat history and tool results all spend tokens, so these habits pay off on every message:</p>+<ul>+<li><strong>Keep <code>AGENTS.md</code> short.</strong> Codex reads it before any work. Move folder specific rules into nested <code>AGENTS.md</code> files, as OpenAI’s pricing page suggests.</li>+<li><strong>Turn off MCP servers you are not using.</strong> OpenAI says each one adds context to your messages.</li>+<li><strong>Use one chat per task.</strong> Start the next task with <code>/new</code> instead of stacking it onto a long chat, and use <code>/compact</code> when a single task runs long. OpenAI’s best practices guide warns that one chat for a whole project bloats context.</li>+<li><strong>Stop retry loops early.</strong> If a run misses, interrupt it, fix the prompt or add the missing file, then rerun. OpenAI’s Astra usage guide notes that raising effort cannot supply information or access the model never had.</li>+<li><strong>Point reviews at a cheaper model.</strong> Set <code>review_model</code> in <code>config.toml</code> so <code>/review</code> does not inherit an expensive session model.</li>+</ul>+<h2 id="can-i-run-several-codex-agents-at-once" tabindex="-1">Can I run several Codex agents at once? <a class="anchor" href="#can-i-run-several-codex-agents-at-once" aria-hidden="true">#</a></h2>+<p>Yes, and that is where a Pro allowance goes fastest. Worktrees, cloud chats and subagents all run in parallel from the same pool, and OpenAI’s docs say subagent runs use more tokens than a single agent. Go parallel only when tasks touch separate files and a cheaper model suffices.</p>+<p>If you run Codex beside other CLIs, Munder Difflin runs them together in one desktop app. In 0.5.2 each Codex agent signs in with your own Codex login, so they all spend your Pro allowance, and you pick each agent’s model: Astra, Sol, Terra or Luna. One honest limit: its per agent token caps read Claude Code’s usage data, so they do not meter Codex agents. For those, <code>/status</code> and OpenAI’s dashboard stay the meter. The <a href="/blog/run-a-mixed-engine-office/">mixed engine office guide</a> shows a layout, and the <a href="/blog/the-multi-agent-cost-playbook/">multi-agent cost playbook</a> covers model tiering across a fleet.</p>++++ <section class="faq" aria-label="Frequently asked questions">+ <h2 id="faq">FAQ</h2>++ <div class="qa">+ <p class="q">Can I still buy ChatGPT Pro 20x for Codex?</p>+ <p class="a">Not as a new subscriber right now. OpenAI paused new sign-ups and upgrades to Pro $200, also called Pro 20x, on 10 Sep 2026, and existing subscriptions keep renewing. Pro $100 (Pro 5x) is still on sale. If your Pro $200 subscription lapses, you cannot buy it again until the pause lifts.</p>+ </div>++ <div class="qa">+ <p class="q">Is there a five hour limit on ChatGPT Pro for Codex?</p>+ <p class="a">No. OpenAI dropped the five hour window on 12 Jul 2026. On 25 Aug 2026 Thibault Sottiaux of the Codex team said it was coming back for Plus while Pro $100 and Pro $200 stay without it for the upcoming months, and on 31 Aug he said the Pro multiples apply to weekly limits. The weekly limit still applies, so check the usage dashboard for your reset time.</p>+ </div>++ <div class="qa">+ <p class="q">Does Codex code review count against my usage limit?</p>+ <p class="a">It depends on where the review runs. OpenAI's pricing page says reviews Codex runs through GitHub, such as tagging @codex on a pull request, count as Code Review usage, while reviews run locally or outside GitHub count toward your general limits. For local reviews, set review_model in config.toml to a smaller model.</p>+ </div>++ <div class="qa">+ <p class="q">What happens when I hit my Codex usage limit in the middle of a task?</p>+ <p class="a">Codex keeps working on the turn already in progress, subject to fair use limits, per OpenAI's pricing page checked 14 Sep 2026. After that, Plus and Pro users can buy credits without upgrading, use an available reset, or wait for the reset time shown on the usage page.</p>+ </div>++ <div class="qa">+ <p class="q">Does switching to a smaller model give me my Codex limit back?</p>+ <p class="a">No. OpenAI's help article on managing usage with GPT-6 Astra says switching models does not restore allowance in a shared usage pool. A smaller model only makes what is left go further, so switch while you are approaching the limit, not after you hit it.</p>+ </div>++ </section>++++ <hr />+ <div class="share">+ <span class="lbl">Tags</span>+ <a class="tag" href="/blog/tags/guides/">Guides</a><a class="tag" href="/blog/tags/codex/">Codex</a><a class="tag" href="/blog/tags/cost/">Cost</a><a class="tag" href="/blog/tags/model-routing/">Model Routing</a>+ </div>++ </div>+++ <aside class="toc-rail" aria-label="Table of contents">+ <div class="tt">On this page</div>+ <ol>+ <li class="lvl-2"><a href="#is-there-a-codex-max-plan">Is there a Codex max plan?</a></li><li class="lvl-2"><a href="#does-codex-have-weekly-limits">Does Codex have weekly limits?</a></li><li class="lvl-2"><a href="#do-cloud-tasks-use-more-than-local-ones">Do cloud tasks use more than local ones?</a></li><li class="lvl-2"><a href="#how-do-i-check-my-codex-usage">How do I check my Codex usage?</a></li><li class="lvl-2"><a href="#which-model-makes-codex-usage-last-longest">Which model makes Codex usage last longest?</a></li><li class="lvl-2"><a href="#how-do-i-reduce-codex-token-usage">How do I reduce Codex token usage?</a></li><li class="lvl-2"><a href="#can-i-run-several-codex-agents-at-once">Can I run several Codex agents at once?</a></li>+ </ol>+ </aside>++ </div>++ <footer class="post-foot wrap"><div class="prevnext">+ <a class="pn prev" href="/blog/grok-bot-alternatives/"><span class="k">← Older</span><span class="t">Grok Bot Alternatives: Six Picks, Grouped by What You Want</span></a>+ <a class="pn next" href="/blog/claude-code-max-plan-tips/"><span class="k">Newer →</span><span class="t">How to Get the Most Out of Your Claude Code Max Plan</span></a>+ </div>+ <section class="related">+ <h2>Related in Guides</h2>+ <div class="post-grid">+ <article class="card t-guides">+ <a class="thumb t-guides" href="/blog/claude-code-max-plan-tips/" aria-hidden="true" tabindex="-1"><img src="/blog/assets/media/claude-code-max-plan-tips/hero.png" alt="" loading="lazy" decoding="async" /></a>+ <div class="body">+ <div class="meta">+ <time datetime="2026-09-14">Sep 14, 2026</time>+ <span class="dot" aria-hidden="true"></span>+ <span>5 min</span>+ </div>+ <h3><a href="/blog/claude-code-max-plan-tips/">How to Get the Most Out of Your Claude Code Max Plan</a></h3>+ <p class="dek">Stretch a Claude Code Max plan: model choice, context hygiene, prompt caching, subagents and unattended runs, checked against Anthropic's own pages.</p>+ <div class="foot">+ <span class="tag kind">Guides</span>+ <a class="more" href="/blog/claude-code-max-plan-tips/" aria-label="Read: How to Get the Most Out of Your Claude Code Max Plan">Read →</a>+ </div>+ </div>+</article>+<article class="card t-guides">+ <a class="thumb t-guides" href="/blog/how-to-use-claude-code-plan-mode/" aria-hidden="true" tabindex="-1"><img src="/blog/assets/media/how-to-use-claude-code-plan-mode/hero.png" alt="" loading="lazy" decoding="async" /></a>+ <div class="body">+ <div class="meta">+ <time datetime="2026-09-11">Sep 11, 2026</time>+ <span class="dot" aria-hidden="true"></span>+ <span>5 min</span>+ </div>+ <h3><a href="/blog/how-to-use-claude-code-plan-mode/">How to Use Claude Code Plan Mode</a></h3>+ <p class="dek">How Claude Code's plan mode works: turning it on, what it blocks, what a real headless plan mode run prints, and how to leave it.</p>+ <div class="foot">+ <span class="tag kind">Guides</span>+ <a class="more" href="/blog/how-to-use-claude-code-plan-mode/" aria-label="Read: How to Use Claude Code Plan Mode">Read →</a>+ </div>+ </div>+</article>+<article class="card t-guides">+ <a class="thumb t-guides" href="/blog/how-to-add-an-mcp-server-to-claude-code/" aria-hidden="true" tabindex="-1"><img src="/blog/assets/media/how-to-add-an-mcp-server-to-claude-code/hero.png" alt="" loading="lazy" decoding="async" /></a>+ <div class="body">+ <div class="meta">+ <time datetime="2026-09-10">Sep 10, 2026</time>+ <span class="dot" aria-hidden="true"></span>+ <span>5 min</span>+ </div>+ <h3><a href="/blog/how-to-add-an-mcp-server-to-claude-code/">How to Add an MCP Server to Claude Code</a></h3>+ <p class="dek">The claude mcp add command, its scope flag, editing .mcp.json by hand, and how Munder Difflin's Capabilities screen grants an MCP server to one agent at a time.</p>+ <div class="foot">+ <span class="tag kind">Guides</span>+ <a class="more" href="/blog/how-to-add-an-mcp-server-to-claude-code/" aria-label="Read: How to Add an MCP Server to Claude Code">Read →</a>+ </div>+ </div>+</article>++ </div>+ </section>++ </footer>+</article>++</main>+<footer class="site-foot">+ <div class="wrap">+ <div class="foot-top">+ <a class="foot-brand brand" href="https://munderdiffl.in" aria-label="Munder Difflin home">+ <img class="brand-logo" src="https://munderdiffl.in/logo.png" width="1318" height="840" alt="Munder Difflin, Inc. — Multi-Agent Harness" />+ </a>+ <div class="foot-links">+ <a href="/blog/">Latest</a>+ <a href="/blog/topics/">Topics</a>+ <a href="/blog/about/">About</a>+ <a href="https://munderdiffl.in/blog/feed.xml">RSS</a>+ <a href="https://github.com/chaitanyagiri/munder-difflin">GitHub</a>+ <a href="https://munderdiffl.in">munderdiffl.in ↗</a>+ </div>+ </div>+ <div class="foot-meta">+ © 2026 Munder Difflin · Local-first · MIT-licensed ·+ Built on <a href="https://munderdiffl.in">Electron, React, Pixi.js, xterm.js & node-pty</a>.+ Run an office of agents while you sleep.+ </div>+ </div>+</footer>++<script>+ // sticky-nav border on scroll+ (function () {+ var nav = document.getElementById('nav');+ if (!nav) return;+ var onScroll = function () { nav.classList.toggle('scrolled', window.scrollY > 8); };+ onScroll(); window.addEventListener('scroll', onScroll, { passive: true });+ })();+ // YouTube click-to-load: thumbnail button → youtube-nocookie iframe+ (function () {+ document.addEventListener('click', function (e) {+ var btn = e.target.closest('.yt-load');+ if (!btn) return;+ var box = btn.closest('.yt');+ var id = box && box.getAttribute('data-yt');+ if (!id) return;+ var frame = document.createElement('iframe');+ frame.src = 'https://www.youtube-nocookie.com/embed/' + id + '?autoplay=1';+ frame.title = box.getAttribute('data-title') || 'YouTube video';+ frame.allow = 'accelerometer; autoplay; clipboard-write; encrypted-media; gyroscope; picture-in-picture; web-share';+ frame.setAttribute('allowfullscreen', '');+ box.replaceChildren(frame);+ });+ })();+</script>++</body>+</html>diff --git a/docs/blog/command-center-guide/index.html b/docs/blog/command-center-guide/index.htmlindex 5d58fe10..6d5d03a1 100644--- a/docs/blog/command-center-guide/index.html+++ b/docs/blog/command-center-guide/index.html@@ -308,50 +308,50 @@ place in your morning routine, <a href="https://github.com/chaitanyagiri/munder-<h2>Related in Guides</h2><div class="post-grid"><article class="card t-guides">- <a class="thumb t-guides" href="/blog/how-to-use-claude-code-plan-mode/" aria-hidden="true" tabindex="-1"><img src="/blog/assets/media/how-to-use-claude-code-plan-mode/hero.png" alt="" loading="lazy" decoding="async" /></a>+ <a class="thumb t-guides" href="/blog/claude-code-max-plan-tips/" aria-hidden="true" tabindex="-1"><img src="/blog/assets/media/claude-code-max-plan-tips/hero.png" alt="" loading="lazy" decoding="async" /></a><div class="body"><div class="meta">- <time datetime="2026-09-11">Sep 11, 2026</time>+ <time datetime="2026-09-14">Sep 14, 2026</time><span class="dot" aria-hidden="true"></span><span>5 min</span></div>- <h3><a href="/blog/how-to-use-claude-code-plan-mode/">How to Use Claude Code Plan Mode</a></h3>- <p class="dek">How Claude Code's plan mode works: turning it on, what it blocks, what a real headless plan mode run prints, and how to leave it.</p>+ <h3><a href="/blog/claude-code-max-plan-tips/">How to Get the Most Out of Your Claude Code Max Plan</a></h3>+ <p class="dek">Stretch a Claude Code Max plan: model choice, context hygiene, prompt caching, subagents and unattended runs, checked against Anthropic's own pages.</p><div class="foot"><span class="tag kind">Guides</span>- <a class="more" href="/blog/how-to-use-claude-code-plan-mode/" aria-label="Read: How to Use Claude Code Plan Mode">Read →</a>+ <a class="more" href="/blog/claude-code-max-plan-tips/" aria-label="Read: How to Get the Most Out of Your Claude Code Max Plan">Read →</a></div></div></article><article class="card t-guides">- <a class="thumb t-guides" href="/blog/how-to-add-an-mcp-server-to-claude-code/" aria-hidden="true" tabindex="-1"><img src="/blog/assets/media/how-to-add-an-mcp-server-to-claude-code/hero.png" alt="" loading="lazy" decoding="async" /></a>+ <a class="thumb t-guides" href="/blog/codex-max-plan-tips/" aria-hidden="true" tabindex="-1"><img src="/blog/assets/media/codex-max-plan-tips/hero.png" alt="" loading="lazy" decoding="async" /></a><div class="body"><div class="meta">- <time datetime="2026-09-10">Sep 10, 2026</time>+ <time datetime="2026-09-14">Sep 14, 2026</time><span class="dot" aria-hidden="true"></span><span>5 min</span></div>- <h3><a href="/blog/how-to-add-an-mcp-server-to-claude-code/">How to Add an MCP Server to Claude Code</a></h3>- <p class="dek">The claude mcp add command, its scope flag, editing .mcp.json by hand, and how Munder Difflin's Capabilities screen grants an MCP server to one agent at a time.</p>+ <h3><a href="/blog/codex-max-plan-tips/">How to Make the Most of Your Codex Max Plan</a></h3>+ <p class="dek">There is no Codex Max plan. What ChatGPT Pro 5x and 20x give you in Codex, how the weekly limit works, and how to stretch it.</p><div class="foot"><span class="tag kind">Guides</span>- <a class="more" href="/blog/how-to-add-an-mcp-server-to-claude-code/" aria-label="Read: How to Add an MCP Server to Claude Code">Read →</a>+ <a class="more" href="/blog/codex-max-plan-tips/" aria-label="Read: How to Make the Most of Your Codex Max Plan">Read →</a></div></div></article><article class="card t-guides">- <a class="thumb t-guides" href="/blog/how-to-add-a-github-copilot-cli-agent/" aria-hidden="true" tabindex="-1"><img src="/blog/assets/media/how-to-add-a-github-copilot-cli-agent/hero.png" alt="" loading="lazy" decoding="async" /></a>+ <a class="thumb t-guides" href="/blog/how-to-use-claude-code-plan-mode/" aria-hidden="true" tabindex="-1"><img src="/blog/assets/media/how-to-use-claude-code-plan-mode/hero.png" alt="" loading="lazy" decoding="async" /></a><div class="body"><div class="meta">- <time datetime="2026-07-03">Jul 3, 2026</time>+ <time datetime="2026-09-11">Sep 11, 2026</time><span class="dot" aria-hidden="true"></span>- <span>4 min</span>+ <span>5 min</span></div>- <h3><a href="/blog/how-to-add-a-github-copilot-cli-agent/">How to Add a GitHub Copilot CLI Agent to Your Floor</a></h3>- <p class="dek">A step-by-step v0.3.3 walkthrough: install GitHub Copilot CLI (or let the harness install it for you), hire a Copilot worker, pick a model, and know exactly what print mode can and can't do.</p>+ <h3><a href="/blog/how-to-use-claude-code-plan-mode/">How to Use Claude Code Plan Mode</a></h3>+ <p class="dek">How Claude Code's plan mode works: turning it on, what it blocks, what a real headless plan mode run prints, and how to leave it.</p><div class="foot"><span class="tag kind">Guides</span>- <a class="more" href="/blog/how-to-add-a-github-copilot-cli-agent/" aria-label="Read: How to Add a GitHub Copilot CLI Agent to Your Floor">Read →</a>+ <a class="more" href="/blog/how-to-use-claude-code-plan-mode/" aria-label="Read: How to Use Claude Code Plan Mode">Read →</a></div></div></article>diff --git a/docs/blog/conductor-claude-code-alternative/index.html b/docs/blog/conductor-claude-code-alternative/index.htmlindex 94846468..34e9104e 100644--- a/docs/blog/conductor-claude-code-alternative/index.html+++ b/docs/blog/conductor-claude-code-alternative/index.html@@ -252,50 +252,50 @@ coordinated team locally — it’s free and open source.</p><h2>Related in Comparisons</h2><div class="post-grid"><article class="card t-comparisons">- <a class="thumb t-comparisons" href="/blog/codex-cli-vs-claude-code/" aria-hidden="true" tabindex="-1"><img src="/blog/assets/media/codex-cli-vs-claude-code/hero.png" alt="" loading="lazy" decoding="async" /></a>+ <a class="thumb t-comparisons" href="/blog/grok-bot-alternatives/" aria-hidden="true" tabindex="-1"><img src="/blog/assets/media/grok-bot-alternatives/hero.png" alt="" loading="lazy" decoding="async" /></a><div class="body"><div class="meta">- <time datetime="2026-09-10">Sep 10, 2026</time>+ <time datetime="2026-09-14">Sep 14, 2026</time><span class="dot" aria-hidden="true"></span><span>5 min</span></div>- <h3><a href="/blog/codex-cli-vs-claude-code/">Codex CLI vs Claude Code</a></h3>- <p class="dek">Codex CLI and Claude Code compared firsthand: sandbox and approval flags, AGENTS.md vs CLAUDE.md, real pricing, and where each terminal agent wins.</p>+ <h3><a href="/blog/grok-bot-alternatives/">Grok Bot Alternatives: Six Picks, Grouped by What You Want</a></h3>+ <p class="dek">Grok Bot runs every Bot on one shared cloud computer. Six alternatives checked on 14 Sep 2026, grouped by hosting, privacy and model choice.</p><div class="foot"><span class="tag kind">Comparisons</span>- <a class="more" href="/blog/codex-cli-vs-claude-code/" aria-label="Read: Codex CLI vs Claude Code">Read →</a>+ <a class="more" href="/blog/grok-bot-alternatives/" aria-label="Read: Grok Bot Alternatives: Six Picks, Grouped by What You Want">Read →</a></div></div></article><article class="card t-comparisons">- <a class="thumb t-comparisons" href="/blog/qm-vs-munder-difflin/" aria-hidden="true" tabindex="-1"><img src="/blog/assets/media/qm-vs-munder-difflin/hero.png" alt="" loading="lazy" decoding="async" /></a>+ <a class="thumb t-comparisons" href="/blog/herdr-alternatives/" aria-hidden="true" tabindex="-1"><img src="/blog/assets/media/herdr-alternatives/hero.png" alt="" loading="lazy" decoding="async" /></a><div class="body"><div class="meta">- <time datetime="2026-08-06">Aug 6, 2026</time>+ <time datetime="2026-09-14">Sep 14, 2026</time><span class="dot" aria-hidden="true"></span>- <span>4 min</span>+ <span>5 min</span></div>- <h3><a href="/blog/qm-vs-munder-difflin/">qm vs Munder Difflin: YC's Multiplayer Harness or an Office of Your Clones?</a></h3>- <p class="dek">An honest September 2026 comparison of YC's qm and Munder Difflin. qm is a multiplayer agent harness a company deploys for Slack and the web. Munder Difflin runs an office of your clones on your own machine, with Teams to connect them.</p>+ <h3><a href="/blog/herdr-alternatives/">Herdr Alternatives: What to Pick and Who Each One Fits</a></h3>+ <p class="dek">Herdr alternatives checked on 14 Sep 2026: tmux, Claude Squad, cmux, Orca, Conductor, Superset, Emdash and Munder Difflin, and who each fits.</p><div class="foot"><span class="tag kind">Comparisons</span>- <a class="more" href="/blog/qm-vs-munder-difflin/" aria-label="Read: qm vs Munder Difflin: YC's Multiplayer Harness or an Office of Your Clones?">Read →</a>+ <a class="more" href="/blog/herdr-alternatives/" aria-label="Read: Herdr Alternatives: What to Pick and Who Each One Fits">Read →</a></div></div></article><article class="card t-comparisons">- <a class="thumb t-comparisons" href="/blog/crewai-autogen-vs-a-local-agent-harness/" aria-hidden="true" tabindex="-1"><img src="/blog/assets/media/crewai-autogen-vs-a-local-agent-harness/hero.png" alt="" loading="lazy" decoding="async" /></a>+ <a class="thumb t-comparisons" href="/blog/omniagent-alternatives/" aria-hidden="true" tabindex="-1"><span class="thumb-ph"><em class="ph-glyph" aria-hidden="true">✶</em><span>COMPARISONS</span></span></a><div class="body"><div class="meta">- <time datetime="2026-07-03">Jul 3, 2026</time>+ <time datetime="2026-09-14">Sep 14, 2026</time><span class="dot" aria-hidden="true"></span><span>5 min</span></div>- <h3><a href="/blog/crewai-autogen-vs-a-local-agent-harness/">CrewAI and AutoGen vs a Local Agent Harness: Framework or App?</a></h3>- <p class="dek">CrewAI, AutoGen (now Microsoft Agent Framework), and LangGraph are frameworks — Python you write to build your own agent system. A multi-agent harness is an app you download that runs a team on your repos today. Here's how to tell which one you actually need.</p>+ <h3><a href="/blog/omniagent-alternatives/">OmniAgent Alternatives: What to Use Instead of Databricks Omnigent</a></h3>+ <p class="dek">OmniAgent is really Omnigent, the open source meta harness from Databricks. Alternatives checked on 14 Sep 2026, and who each one fits.</p><div class="foot"><span class="tag kind">Comparisons</span>- <a class="more" href="/blog/crewai-autogen-vs-a-local-agent-harness/" aria-label="Read: CrewAI and AutoGen vs a Local Agent Harness: Framework or App?">Read →</a>+ <a class="more" href="/blog/omniagent-alternatives/" aria-label="Read: OmniAgent Alternatives: What to Use Instead of Databricks Omnigent">Read →</a></div></div></article>diff --git a/docs/blog/context-engineering-for-ai-agents/index.html b/docs/blog/context-engineering-for-ai-agents/index.htmlindex fa56d74f..c3fb0ba9 100644--- a/docs/blog/context-engineering-for-ai-agents/index.html+++ b/docs/blog/context-engineering-for-ai-agents/index.html@@ -344,50 +344,50 @@ it’s free and open source.</p><h2>Related in Guides</h2><div class="post-grid"><article class="card t-guides">- <a class="thumb t-guides" href="/blog/how-to-use-claude-code-plan-mode/" aria-hidden="true" tabindex="-1"><img src="/blog/assets/media/how-to-use-claude-code-plan-mode/hero.png" alt="" loading="lazy" decoding="async" /></a>+ <a class="thumb t-guides" href="/blog/claude-code-max-plan-tips/" aria-hidden="true" tabindex="-1"><img src="/blog/assets/media/claude-code-max-plan-tips/hero.png" alt="" loading="lazy" decoding="async" /></a><div class="body"><div class="meta">- <time datetime="2026-09-11">Sep 11, 2026</time>+ <time datetime="2026-09-14">Sep 14, 2026</time><span class="dot" aria-hidden="true"></span><span>5 min</span></div>- <h3><a href="/blog/how-to-use-claude-code-plan-mode/">How to Use Claude Code Plan Mode</a></h3>- <p class="dek">How Claude Code's plan mode works: turning it on, what it blocks, what a real headless plan mode run prints, and how to leave it.</p>+ <h3><a href="/blog/claude-code-max-plan-tips/">How to Get the Most Out of Your Claude Code Max Plan</a></h3>+ <p class="dek">Stretch a Claude Code Max plan: model choice, context hygiene, prompt caching, subagents and unattended runs, checked against Anthropic's own pages.</p><div class="foot"><span class="tag kind">Guides</span>- <a class="more" href="/blog/how-to-use-claude-code-plan-mode/" aria-label="Read: How to Use Claude Code Plan Mode">Read →</a>+ <a class="more" href="/blog/claude-code-max-plan-tips/" aria-label="Read: How to Get the Most Out of Your Claude Code Max Plan">Read →</a></div></div></article><article class="card t-guides">- <a class="thumb t-guides" href="/blog/how-to-add-an-mcp-server-to-claude-code/" aria-hidden="true" tabindex="-1"><img src="/blog/assets/media/how-to-add-an-mcp-server-to-claude-code/hero.png" alt="" loading="lazy" decoding="async" /></a>+ <a class="thumb t-guides" href="/blog/codex-max-plan-tips/" aria-hidden="true" tabindex="-1"><img src="/blog/assets/media/codex-max-plan-tips/hero.png" alt="" loading="lazy" decoding="async" /></a><div class="body"><div class="meta">- <time datetime="2026-09-10">Sep 10, 2026</time>+ <time datetime="2026-09-14">Sep 14, 2026</time><span class="dot" aria-hidden="true"></span><span>5 min</span></div>- <h3><a href="/blog/how-to-add-an-mcp-server-to-claude-code/">How to Add an MCP Server to Claude Code</a></h3>- <p class="dek">The claude mcp add command, its scope flag, editing .mcp.json by hand, and how Munder Difflin's Capabilities screen grants an MCP server to one agent at a time.</p>+ <h3><a href="/blog/codex-max-plan-tips/">How to Make the Most of Your Codex Max Plan</a></h3>+ <p class="dek">There is no Codex Max plan. What ChatGPT Pro 5x and 20x give you in Codex, how the weekly limit works, and how to stretch it.</p><div class="foot"><span class="tag kind">Guides</span>- <a class="more" href="/blog/how-to-add-an-mcp-server-to-claude-code/" aria-label="Read: How to Add an MCP Server to Claude Code">Read →</a>+ <a class="more" href="/blog/codex-max-plan-tips/" aria-label="Read: How to Make the Most of Your Codex Max Plan">Read →</a></div></div></article><article class="card t-guides">- <a class="thumb t-guides" href="/blog/command-center-guide/" aria-hidden="true" tabindex="-1"><img src="/blog/assets/media/command-center-guide/hero.png" alt="" loading="lazy" decoding="async" /></a>+ <a class="thumb t-guides" href="/blog/how-to-use-claude-code-plan-mode/" aria-hidden="true" tabindex="-1"><img src="/blog/assets/media/how-to-use-claude-code-plan-mode/hero.png" alt="" loading="lazy" decoding="async" /></a><div class="body"><div class="meta">- <time datetime="2026-07-03">Jul 3, 2026</time>+ <time datetime="2026-09-11">Sep 11, 2026</time><span class="dot" aria-hidden="true"></span>- <span>4 min</span>+ <span>5 min</span></div>- <h3><a href="/blog/command-center-guide/">The Command Center: Kanban, Fleet and Budgets in One Place</a></h3>- <p class="dek">A guide to Munder Difflin's Command Center in 0.5.2: the kanban with task dependencies, the ask me tab, triggers, memory, live token use against each agent's budget, and when to watch the board instead of the floor.</p>+ <h3><a href="/blog/how-to-use-claude-code-plan-mode/">How to Use Claude Code Plan Mode</a></h3>+ <p class="dek">How Claude Code's plan mode works: turning it on, what it blocks, what a real headless plan mode run prints, and how to leave it.</p><div class="foot"><span class="tag kind">Guides</span>- <a class="more" href="/blog/command-center-guide/" aria-label="Read: The Command Center: Kanban, Fleet and Budgets in One Place">Read →</a>+ <a class="more" href="/blog/how-to-use-claude-code-plan-mode/" aria-label="Read: How to Use Claude Code Plan Mode">Read →</a></div></div></article>diff --git a/docs/blog/crewai-autogen-vs-a-local-agent-harness/index.html b/docs/blog/crewai-autogen-vs-a-local-agent-harness/index.htmlindex 3a9c94a5..d2c797ae 100644--- a/docs/blog/crewai-autogen-vs-a-local-agent-harness/index.html+++ b/docs/blog/crewai-autogen-vs-a-local-agent-harness/index.html@@ -192,7 +192,7 @@<h2 id="what-a-harness-is-instead" tabindex="-1">What a harness is instead <a class="anchor" href="#what-a-harness-is-instead" aria-hidden="true">#</a></h2><p>A <a href="/blog/what-is-a-multi-agent-harness/">multi-agent harness</a> is the other answer: the system, already assembled, as an app. Munder Difflin is a free, MIT-licensed, local-first desktop app (macOS/Windows/Linux) where every agent is a <strong>real CLI process</strong> — Claude Code, OpenAI Codex, Antigravity, OpenCode, Crush, pi.dev, GitHub Copilot CLI — running in its own pseudo-terminal and its own isolated git worktree. A <a href="/blog/how-the-god-orchestrator-works/">GOD orchestrator</a> routes work between them; agents share long-term memory; triggers include typing, Slack, webhooks, schedules, and voice.</p><p>The pieces you’d have built around a framework are already there: <a href="/blog/human-in-the-loop-approving-ai-agents/">human approval gates</a> on spend, scope, and destructive ops; a circuit breaker with a steer → constrain → stop ladder; per-agent token budgets; OpenTelemetry observability; a Command Center with a kanban board and live fleet monitoring. And because it drives CLIs rather than calling model APIs, it rides the <strong>subscriptions you already pay for</strong> — no mandatory API key, with BYO keys and local LLMs as options.</p>-<p>The honest flip side: you can’t <code>import</code> Munder Difflin into your SaaS. It won’t run your custom document pipeline inside your product. It’s an app for a specific job — a team of agents working your repositories, visible on one screen — not a toolkit for arbitrary agent systems.</p>+<p>The honest flip side: you can’t <code>import</code> Munder Difflin into your SaaS. It won’t run your custom document pipeline inside your product. It’s an app for a specific job — a team of agents working your repositories, visible on one screen — not a toolkit for arbitrary agent systems. Server based meta harnesses such as Databricks’ Omnigent sit in between, which our <a href="/blog/omniagent-alternatives/">OmniAgent alternatives</a> post covers.</p><figure class="fig fig-inline"><img src="/blog/assets/media/crewai-autogen-vs-a-local-agent-harness/note-2.png" alt="Hand-drawn sketch from “CrewAI and AutoGen vs a Local Agent Harness: Framework or App?”" loading="lazy" decoding="async" /></figure><h2 id="the-honest-decision-rule" tabindex="-1">The honest decision rule <a class="anchor" href="#the-honest-decision-rule" aria-hidden="true">#</a></h2><p><strong>Choose a framework (CrewAI, Agent Framework, LangGraph) when:</strong></p>@@ -277,50 +277,50 @@<h2>Related in Comparisons</h2><div class="post-grid"><article class="card t-comparisons">- <a class="thumb t-comparisons" href="/blog/codex-cli-vs-claude-code/" aria-hidden="true" tabindex="-1"><img src="/blog/assets/media/codex-cli-vs-claude-code/hero.png" alt="" loading="lazy" decoding="async" /></a>+ <a class="thumb t-comparisons" href="/blog/grok-bot-alternatives/" aria-hidden="true" tabindex="-1"><img src="/blog/assets/media/grok-bot-alternatives/hero.png" alt="" loading="lazy" decoding="async" /></a><div class="body"><div class="meta">- <time datetime="2026-09-10">Sep 10, 2026</time>+ <time datetime="2026-09-14">Sep 14, 2026</time><span class="dot" aria-hidden="true"></span><span>5 min</span></div>- <h3><a href="/blog/codex-cli-vs-claude-code/">Codex CLI vs Claude Code</a></h3>- <p class="dek">Codex CLI and Claude Code compared firsthand: sandbox and approval flags, AGENTS.md vs CLAUDE.md, real pricing, and where each terminal agent wins.</p>+ <h3><a href="/blog/grok-bot-alternatives/">Grok Bot Alternatives: Six Picks, Grouped by What You Want</a></h3>+ <p class="dek">Grok Bot runs every Bot on one shared cloud computer. Six alternatives checked on 14 Sep 2026, grouped by hosting, privacy and model choice.</p><div class="foot"><span class="tag kind">Comparisons</span>- <a class="more" href="/blog/codex-cli-vs-claude-code/" aria-label="Read: Codex CLI vs Claude Code">Read →</a>+ <a class="more" href="/blog/grok-bot-alternatives/" aria-label="Read: Grok Bot Alternatives: Six Picks, Grouped by What You Want">Read →</a></div></div></article><article class="card t-comparisons">- <a class="thumb t-comparisons" href="/blog/qm-vs-munder-difflin/" aria-hidden="true" tabindex="-1"><img src="/blog/assets/media/qm-vs-munder-difflin/hero.png" alt="" loading="lazy" decoding="async" /></a>+ <a class="thumb t-comparisons" href="/blog/herdr-alternatives/" aria-hidden="true" tabindex="-1"><img src="/blog/assets/media/herdr-alternatives/hero.png" alt="" loading="lazy" decoding="async" /></a><div class="body"><div class="meta">- <time datetime="2026-08-06">Aug 6, 2026</time>+ <time datetime="2026-09-14">Sep 14, 2026</time><span class="dot" aria-hidden="true"></span>- <span>4 min</span>+ <span>5 min</span></div>- <h3><a href="/blog/qm-vs-munder-difflin/">qm vs Munder Difflin: YC's Multiplayer Harness or an Office of Your Clones?</a></h3>- <p class="dek">An honest September 2026 comparison of YC's qm and Munder Difflin. qm is a multiplayer agent harness a company deploys for Slack and the web. Munder Difflin runs an office of your clones on your own machine, with Teams to connect them.</p>+ <h3><a href="/blog/herdr-alternatives/">Herdr Alternatives: What to Pick and Who Each One Fits</a></h3>+ <p class="dek">Herdr alternatives checked on 14 Sep 2026: tmux, Claude Squad, cmux, Orca, Conductor, Superset, Emdash and Munder Difflin, and who each fits.</p><div class="foot"><span class="tag kind">Comparisons</span>- <a class="more" href="/blog/qm-vs-munder-difflin/" aria-label="Read: qm vs Munder Difflin: YC's Multiplayer Harness or an Office of Your Clones?">Read →</a>+ <a class="more" href="/blog/herdr-alternatives/" aria-label="Read: Herdr Alternatives: What to Pick and Who Each One Fits">Read →</a></div></div></article><article class="card t-comparisons">- <a class="thumb t-comparisons" href="/blog/github-copilot-cli-vs-claude-code-for-hive-work/" aria-hidden="true" tabindex="-1"><img src="/blog/assets/media/github-copilot-cli-vs-claude-code-for-hive-work/hero.png" alt="" loading="lazy" decoding="async" /></a>+ <a class="thumb t-comparisons" href="/blog/omniagent-alternatives/" aria-hidden="true" tabindex="-1"><span class="thumb-ph"><em class="ph-glyph" aria-hidden="true">✶</em><span>COMPARISONS</span></span></a><div class="body"><div class="meta">- <time datetime="2026-07-03">Jul 3, 2026</time>+ <time datetime="2026-09-14">Sep 14, 2026</time><span class="dot" aria-hidden="true"></span><span>5 min</span></div>- <h3><a href="/blog/github-copilot-cli-vs-claude-code-for-hive-work/">GitHub Copilot CLI vs Claude Code as Hive Workers</a></h3>- <p class="dek">How GitHub Copilot CLI and Claude Code behave as agent engines inside a multi-agent harness: hooks, inbox mail, orchestration, session lifecycle — and why the right answer is to run both.</p>+ <h3><a href="/blog/omniagent-alternatives/">OmniAgent Alternatives: What to Use Instead of Databricks Omnigent</a></h3>+ <p class="dek">OmniAgent is really Omnigent, the open source meta harness from Databricks. Alternatives checked on 14 Sep 2026, and who each one fits.</p><div class="foot"><span class="tag kind">Comparisons</span>- <a class="more" href="/blog/github-copilot-cli-vs-claude-code-for-hive-work/" aria-label="Read: GitHub Copilot CLI vs Claude Code as Hive Workers">Read →</a>+ <a class="more" href="/blog/omniagent-alternatives/" aria-label="Read: OmniAgent Alternatives: What to Use Instead of Databricks Omnigent">Read →</a></div></div></article>diff --git a/docs/blog/crystal-claude-code-alternative/index.html b/docs/blog/crystal-claude-code-alternative/index.htmlindex 5e42288b..b6fac1af 100644--- a/docs/blog/crystal-claude-code-alternative/index.html+++ b/docs/blog/crystal-claude-code-alternative/index.html@@ -249,50 +249,50 @@ actually remember — free and open source.</p><h2>Related in Comparisons</h2><div class="post-grid"><article class="card t-comparisons">- <a class="thumb t-comparisons" href="/blog/codex-cli-vs-claude-code/" aria-hidden="true" tabindex="-1"><img src="/blog/assets/media/codex-cli-vs-claude-code/hero.png" alt="" loading="lazy" decoding="async" /></a>+ <a class="thumb t-comparisons" href="/blog/grok-bot-alternatives/" aria-hidden="true" tabindex="-1"><img src="/blog/assets/media/grok-bot-alternatives/hero.png" alt="" loading="lazy" decoding="async" /></a><div class="body"><div class="meta">- <time datetime="2026-09-10">Sep 10, 2026</time>+ <time datetime="2026-09-14">Sep 14, 2026</time><span class="dot" aria-hidden="true"></span><span>5 min</span></div>- <h3><a href="/blog/codex-cli-vs-claude-code/">Codex CLI vs Claude Code</a></h3>- <p class="dek">Codex CLI and Claude Code compared firsthand: sandbox and approval flags, AGENTS.md vs CLAUDE.md, real pricing, and where each terminal agent wins.</p>+ <h3><a href="/blog/grok-bot-alternatives/">Grok Bot Alternatives: Six Picks, Grouped by What You Want</a></h3>+ <p class="dek">Grok Bot runs every Bot on one shared cloud computer. Six alternatives checked on 14 Sep 2026, grouped by hosting, privacy and model choice.</p><div class="foot"><span class="tag kind">Comparisons</span>- <a class="more" href="/blog/codex-cli-vs-claude-code/" aria-label="Read: Codex CLI vs Claude Code">Read →</a>+ <a class="more" href="/blog/grok-bot-alternatives/" aria-label="Read: Grok Bot Alternatives: Six Picks, Grouped by What You Want">Read →</a></div></div></article><article class="card t-comparisons">- <a class="thumb t-comparisons" href="/blog/qm-vs-munder-difflin/" aria-hidden="true" tabindex="-1"><img src="/blog/assets/media/qm-vs-munder-difflin/hero.png" alt="" loading="lazy" decoding="async" /></a>+ <a class="thumb t-comparisons" href="/blog/herdr-alternatives/" aria-hidden="true" tabindex="-1"><img src="/blog/assets/media/herdr-alternatives/hero.png" alt="" loading="lazy" decoding="async" /></a><div class="body"><div class="meta">- <time datetime="2026-08-06">Aug 6, 2026</time>+ <time datetime="2026-09-14">Sep 14, 2026</time><span class="dot" aria-hidden="true"></span>- <span>4 min</span>+ <span>5 min</span></div>- <h3><a href="/blog/qm-vs-munder-difflin/">qm vs Munder Difflin: YC's Multiplayer Harness or an Office of Your Clones?</a></h3>- <p class="dek">An honest September 2026 comparison of YC's qm and Munder Difflin. qm is a multiplayer agent harness a company deploys for Slack and the web. Munder Difflin runs an office of your clones on your own machine, with Teams to connect them.</p>+ <h3><a href="/blog/herdr-alternatives/">Herdr Alternatives: What to Pick and Who Each One Fits</a></h3>+ <p class="dek">Herdr alternatives checked on 14 Sep 2026: tmux, Claude Squad, cmux, Orca, Conductor, Superset, Emdash and Munder Difflin, and who each fits.</p><div class="foot"><span class="tag kind">Comparisons</span>- <a class="more" href="/blog/qm-vs-munder-difflin/" aria-label="Read: qm vs Munder Difflin: YC's Multiplayer Harness or an Office of Your Clones?">Read →</a>+ <a class="more" href="/blog/herdr-alternatives/" aria-label="Read: Herdr Alternatives: What to Pick and Who Each One Fits">Read →</a></div></div></article><article class="card t-comparisons">- <a class="thumb t-comparisons" href="/blog/crewai-autogen-vs-a-local-agent-harness/" aria-hidden="true" tabindex="-1"><img src="/blog/assets/media/crewai-autogen-vs-a-local-agent-harness/hero.png" alt="" loading="lazy" decoding="async" /></a>+ <a class="thumb t-comparisons" href="/blog/omniagent-alternatives/" aria-hidden="true" tabindex="-1"><span class="thumb-ph"><em class="ph-glyph" aria-hidden="true">✶</em><span>COMPARISONS</span></span></a><div class="body"><div class="meta">- <time datetime="2026-07-03">Jul 3, 2026</time>+ <time datetime="2026-09-14">Sep 14, 2026</time><span class="dot" aria-hidden="true"></span><span>5 min</span></div>- <h3><a href="/blog/crewai-autogen-vs-a-local-agent-harness/">CrewAI and AutoGen vs a Local Agent Harness: Framework or App?</a></h3>- <p class="dek">CrewAI, AutoGen (now Microsoft Agent Framework), and LangGraph are frameworks — Python you write to build your own agent system. A multi-agent harness is an app you download that runs a team on your repos today. Here's how to tell which one you actually need.</p>+ <h3><a href="/blog/omniagent-alternatives/">OmniAgent Alternatives: What to Use Instead of Databricks Omnigent</a></h3>+ <p class="dek">OmniAgent is really Omnigent, the open source meta harness from Databricks. Alternatives checked on 14 Sep 2026, and who each one fits.</p><div class="foot"><span class="tag kind">Comparisons</span>- <a class="more" href="/blog/crewai-autogen-vs-a-local-agent-harness/" aria-label="Read: CrewAI and AutoGen vs a Local Agent Harness: Framework or App?">Read →</a>+ <a class="more" href="/blog/omniagent-alternatives/" aria-label="Read: OmniAgent Alternatives: What to Use Instead of Databricks Omnigent">Read →</a></div></div></article>diff --git a/docs/blog/debugging-multi-agent-systems/index.html b/docs/blog/debugging-multi-agent-systems/index.htmlindex 74ff5a6a..c69d52dc 100644--- a/docs/blog/debugging-multi-agent-systems/index.html+++ b/docs/blog/debugging-multi-agent-systems/index.html@@ -307,50 +307,50 @@ to run agents you can actually trace; it’s free and open source.</p><h2>Related in Guides</h2><div class="post-grid"><article class="card t-guides">- <a class="thumb t-guides" href="/blog/how-to-use-claude-code-plan-mode/" aria-hidden="true" tabindex="-1"><img src="/blog/assets/media/how-to-use-claude-code-plan-mode/hero.png" alt="" loading="lazy" decoding="async" /></a>+ <a class="thumb t-guides" href="/blog/claude-code-max-plan-tips/" aria-hidden="true" tabindex="-1"><img src="/blog/assets/media/claude-code-max-plan-tips/hero.png" alt="" loading="lazy" decoding="async" /></a><div class="body"><div class="meta">- <time datetime="2026-09-11">Sep 11, 2026</time>+ <time datetime="2026-09-14">Sep 14, 2026</time><span class="dot" aria-hidden="true"></span><span>5 min</span></div>- <h3><a href="/blog/how-to-use-claude-code-plan-mode/">How to Use Claude Code Plan Mode</a></h3>- <p class="dek">How Claude Code's plan mode works: turning it on, what it blocks, what a real headless plan mode run prints, and how to leave it.</p>+ <h3><a href="/blog/claude-code-max-plan-tips/">How to Get the Most Out of Your Claude Code Max Plan</a></h3>+ <p class="dek">Stretch a Claude Code Max plan: model choice, context hygiene, prompt caching, subagents and unattended runs, checked against Anthropic's own pages.</p><div class="foot"><span class="tag kind">Guides</span>- <a class="more" href="/blog/how-to-use-claude-code-plan-mode/" aria-label="Read: How to Use Claude Code Plan Mode">Read →</a>+ <a class="more" href="/blog/claude-code-max-plan-tips/" aria-label="Read: How to Get the Most Out of Your Claude Code Max Plan">Read →</a></div></div></article><article class="card t-guides">- <a class="thumb t-guides" href="/blog/how-to-add-an-mcp-server-to-claude-code/" aria-hidden="true" tabindex="-1"><img src="/blog/assets/media/how-to-add-an-mcp-server-to-claude-code/hero.png" alt="" loading="lazy" decoding="async" /></a>+ <a class="thumb t-guides" href="/blog/codex-max-plan-tips/" aria-hidden="true" tabindex="-1"><img src="/blog/assets/media/codex-max-plan-tips/hero.png" alt="" loading="lazy" decoding="async" /></a><div class="body"><div class="meta">- <time datetime="2026-09-10">Sep 10, 2026</time>+ <time datetime="2026-09-14">Sep 14, 2026</time><span class="dot" aria-hidden="true"></span><span>5 min</span></div>- <h3><a href="/blog/how-to-add-an-mcp-server-to-claude-code/">How to Add an MCP Server to Claude Code</a></h3>- <p class="dek">The claude mcp add command, its scope flag, editing .mcp.json by hand, and how Munder Difflin's Capabilities screen grants an MCP server to one agent at a time.</p>+ <h3><a href="/blog/codex-max-plan-tips/">How to Make the Most of Your Codex Max Plan</a></h3>+ <p class="dek">There is no Codex Max plan. What ChatGPT Pro 5x and 20x give you in Codex, how the weekly limit works, and how to stretch it.</p><div class="foot"><span class="tag kind">Guides</span>- <a class="more" href="/blog/how-to-add-an-mcp-server-to-claude-code/" aria-label="Read: How to Add an MCP Server to Claude Code">Read →</a>+ <a class="more" href="/blog/codex-max-plan-tips/" aria-label="Read: How to Make the Most of Your Codex Max Plan">Read →</a></div></div></article><article class="card t-guides">- <a class="thumb t-guides" href="/blog/command-center-guide/" aria-hidden="true" tabindex="-1"><img src="/blog/assets/media/command-center-guide/hero.png" alt="" loading="lazy" decoding="async" /></a>+ <a class="thumb t-guides" href="/blog/how-to-use-claude-code-plan-mode/" aria-hidden="true" tabindex="-1"><img src="/blog/assets/media/how-to-use-claude-code-plan-mode/hero.png" alt="" loading="lazy" decoding="async" /></a><div class="body"><div class="meta">- <time datetime="2026-07-03">Jul 3, 2026</time>+ <time datetime="2026-09-11">Sep 11, 2026</time><span class="dot" aria-hidden="true"></span>- <span>4 min</span>+ <span>5 min</span></div>- <h3><a href="/blog/command-center-guide/">The Command Center: Kanban, Fleet and Budgets in One Place</a></h3>- <p class="dek">A guide to Munder Difflin's Command Center in 0.5.2: the kanban with task dependencies, the ask me tab, triggers, memory, live token use against each agent's budget, and when to watch the board instead of the floor.</p>+ <h3><a href="/blog/how-to-use-claude-code-plan-mode/">How to Use Claude Code Plan Mode</a></h3>+ <p class="dek">How Claude Code's plan mode works: turning it on, what it blocks, what a real headless plan mode run prints, and how to leave it.</p><div class="foot"><span class="tag kind">Guides</span>- <a class="more" href="/blog/command-center-guide/" aria-label="Read: The Command Center: Kanban, Fleet and Budgets in One Place">Read →</a>+ <a class="more" href="/blog/how-to-use-claude-code-plan-mode/" aria-label="Read: How to Use Claude Code Plan Mode">Read →</a></div></div></article>diff --git a/docs/blog/does-the-june-2026-agent-sdk-change-affect-munder-difflin/index.html b/docs/blog/does-the-june-2026-agent-sdk-change-affect-munder-difflin/index.htmlindex ce80d1ce..3d8a0791 100644--- a/docs/blog/does-the-june-2026-agent-sdk-change-affect-munder-difflin/index.html+++ b/docs/blog/does-the-june-2026-agent-sdk-change-affect-munder-difflin/index.html@@ -302,50 +302,50 @@ rides your existing Claude subscription. Local-first, on your own plan, no surpr<h2>Related in Guides</h2><div class="post-grid"><article class="card t-guides">- <a class="thumb t-guides" href="/blog/how-to-use-claude-code-plan-mode/" aria-hidden="true" tabindex="-1"><img src="/blog/assets/media/how-to-use-claude-code-plan-mode/hero.png" alt="" loading="lazy" decoding="async" /></a>+ <a class="thumb t-guides" href="/blog/claude-code-max-plan-tips/" aria-hidden="true" tabindex="-1"><img src="/blog/assets/media/claude-code-max-plan-tips/hero.png" alt="" loading="lazy" decoding="async" /></a><div class="body"><div class="meta">- <time datetime="2026-09-11">Sep 11, 2026</time>+ <time datetime="2026-09-14">Sep 14, 2026</time><span class="dot" aria-hidden="true"></span><span>5 min</span></div>- <h3><a href="/blog/how-to-use-claude-code-plan-mode/">How to Use Claude Code Plan Mode</a></h3>- <p class="dek">How Claude Code's plan mode works: turning it on, what it blocks, what a real headless plan mode run prints, and how to leave it.</p>+ <h3><a href="/blog/claude-code-max-plan-tips/">How to Get the Most Out of Your Claude Code Max Plan</a></h3>+ <p class="dek">Stretch a Claude Code Max plan: model choice, context hygiene, prompt caching, subagents and unattended runs, checked against Anthropic's own pages.</p><div class="foot"><span class="tag kind">Guides</span>- <a class="more" href="/blog/how-to-use-claude-code-plan-mode/" aria-label="Read: How to Use Claude Code Plan Mode">Read →</a>+ <a class="more" href="/blog/claude-code-max-plan-tips/" aria-label="Read: How to Get the Most Out of Your Claude Code Max Plan">Read →</a></div></div></article><article class="card t-guides">- <a class="thumb t-guides" href="/blog/how-to-add-an-mcp-server-to-claude-code/" aria-hidden="true" tabindex="-1"><img src="/blog/assets/media/how-to-add-an-mcp-server-to-claude-code/hero.png" alt="" loading="lazy" decoding="async" /></a>+ <a class="thumb t-guides" href="/blog/codex-max-plan-tips/" aria-hidden="true" tabindex="-1"><img src="/blog/assets/media/codex-max-plan-tips/hero.png" alt="" loading="lazy" decoding="async" /></a><div class="body"><div class="meta">- <time datetime="2026-09-10">Sep 10, 2026</time>+ <time datetime="2026-09-14">Sep 14, 2026</time><span class="dot" aria-hidden="true"></span><span>5 min</span></div>- <h3><a href="/blog/how-to-add-an-mcp-server-to-claude-code/">How to Add an MCP Server to Claude Code</a></h3>- <p class="dek">The claude mcp add command, its scope flag, editing .mcp.json by hand, and how Munder Difflin's Capabilities screen grants an MCP server to one agent at a time.</p>+ <h3><a href="/blog/codex-max-plan-tips/">How to Make the Most of Your Codex Max Plan</a></h3>+ <p class="dek">There is no Codex Max plan. What ChatGPT Pro 5x and 20x give you in Codex, how the weekly limit works, and how to stretch it.</p><div class="foot"><span class="tag kind">Guides</span>- <a class="more" href="/blog/how-to-add-an-mcp-server-to-claude-code/" aria-label="Read: How to Add an MCP Server to Claude Code">Read →</a>+ <a class="more" href="/blog/codex-max-plan-tips/" aria-label="Read: How to Make the Most of Your Codex Max Plan">Read →</a></div></div></article><article class="card t-guides">- <a class="thumb t-guides" href="/blog/command-center-guide/" aria-hidden="true" tabindex="-1"><img src="/blog/assets/media/command-center-guide/hero.png" alt="" loading="lazy" decoding="async" /></a>+ <a class="thumb t-guides" href="/blog/how-to-use-claude-code-plan-mode/" aria-hidden="true" tabindex="-1"><img src="/blog/assets/media/how-to-use-claude-code-plan-mode/hero.png" alt="" loading="lazy" decoding="async" /></a><div class="body"><div class="meta">- <time datetime="2026-07-03">Jul 3, 2026</time>+ <time datetime="2026-09-11">Sep 11, 2026</time><span class="dot" aria-hidden="true"></span>- <span>4 min</span>+ <span>5 min</span></div>- <h3><a href="/blog/command-center-guide/">The Command Center: Kanban, Fleet and Budgets in One Place</a></h3>- <p class="dek">A guide to Munder Difflin's Command Center in 0.5.2: the kanban with task dependencies, the ask me tab, triggers, memory, live token use against each agent's budget, and when to watch the board instead of the floor.</p>+ <h3><a href="/blog/how-to-use-claude-code-plan-mode/">How to Use Claude Code Plan Mode</a></h3>+ <p class="dek">How Claude Code's plan mode works: turning it on, what it blocks, what a real headless plan mode run prints, and how to leave it.</p><div class="foot"><span class="tag kind">Guides</span>- <a class="more" href="/blog/command-center-guide/" aria-label="Read: The Command Center: Kanban, Fleet and Budgets in One Place">Read →</a>+ <a class="more" href="/blog/how-to-use-claude-code-plan-mode/" aria-label="Read: How to Use Claude Code Plan Mode">Read →</a></div></div></article>diff --git a/docs/blog/evaluating-ai-agent-reliability/index.html b/docs/blog/evaluating-ai-agent-reliability/index.htmlindex 59c9be63..e5462b84 100644--- a/docs/blog/evaluating-ai-agent-reliability/index.html+++ b/docs/blog/evaluating-ai-agent-reliability/index.html@@ -310,50 +310,50 @@ your bar.</p><h2>Related in Guides</h2><div class="post-grid"><article class="card t-guides">- <a class="thumb t-guides" href="/blog/how-to-use-claude-code-plan-mode/" aria-hidden="true" tabindex="-1"><img src="/blog/assets/media/how-to-use-claude-code-plan-mode/hero.png" alt="" loading="lazy" decoding="async" /></a>+ <a class="thumb t-guides" href="/blog/claude-code-max-plan-tips/" aria-hidden="true" tabindex="-1"><img src="/blog/assets/media/claude-code-max-plan-tips/hero.png" alt="" loading="lazy" decoding="async" /></a><div class="body"><div class="meta">- <time datetime="2026-09-11">Sep 11, 2026</time>+ <time datetime="2026-09-14">Sep 14, 2026</time><span class="dot" aria-hidden="true"></span><span>5 min</span></div>- <h3><a href="/blog/how-to-use-claude-code-plan-mode/">How to Use Claude Code Plan Mode</a></h3>- <p class="dek">How Claude Code's plan mode works: turning it on, what it blocks, what a real headless plan mode run prints, and how to leave it.</p>+ <h3><a href="/blog/claude-code-max-plan-tips/">How to Get the Most Out of Your Claude Code Max Plan</a></h3>+ <p class="dek">Stretch a Claude Code Max plan: model choice, context hygiene, prompt caching, subagents and unattended runs, checked against Anthropic's own pages.</p><div class="foot"><span class="tag kind">Guides</span>- <a class="more" href="/blog/how-to-use-claude-code-plan-mode/" aria-label="Read: How to Use Claude Code Plan Mode">Read →</a>+ <a class="more" href="/blog/claude-code-max-plan-tips/" aria-label="Read: How to Get the Most Out of Your Claude Code Max Plan">Read →</a></div></div></article><article class="card t-guides">- <a class="thumb t-guides" href="/blog/how-to-add-an-mcp-server-to-claude-code/" aria-hidden="true" tabindex="-1"><img src="/blog/assets/media/how-to-add-an-mcp-server-to-claude-code/hero.png" alt="" loading="lazy" decoding="async" /></a>+ <a class="thumb t-guides" href="/blog/codex-max-plan-tips/" aria-hidden="true" tabindex="-1"><img src="/blog/assets/media/codex-max-plan-tips/hero.png" alt="" loading="lazy" decoding="async" /></a><div class="body"><div class="meta">- <time datetime="2026-09-10">Sep 10, 2026</time>+ <time datetime="2026-09-14">Sep 14, 2026</time><span class="dot" aria-hidden="true"></span><span>5 min</span></div>- <h3><a href="/blog/how-to-add-an-mcp-server-to-claude-code/">How to Add an MCP Server to Claude Code</a></h3>- <p class="dek">The claude mcp add command, its scope flag, editing .mcp.json by hand, and how Munder Difflin's Capabilities screen grants an MCP server to one agent at a time.</p>+ <h3><a href="/blog/codex-max-plan-tips/">How to Make the Most of Your Codex Max Plan</a></h3>+ <p class="dek">There is no Codex Max plan. What ChatGPT Pro 5x and 20x give you in Codex, how the weekly limit works, and how to stretch it.</p><div class="foot"><span class="tag kind">Guides</span>- <a class="more" href="/blog/how-to-add-an-mcp-server-to-claude-code/" aria-label="Read: How to Add an MCP Server to Claude Code">Read →</a>+ <a class="more" href="/blog/codex-max-plan-tips/" aria-label="Read: How to Make the Most of Your Codex Max Plan">Read →</a></div></div></article><article class="card t-guides">- <a class="thumb t-guides" href="/blog/command-center-guide/" aria-hidden="true" tabindex="-1"><img src="/blog/assets/media/command-center-guide/hero.png" alt="" loading="lazy" decoding="async" /></a>+ <a class="thumb t-guides" href="/blog/how-to-use-claude-code-plan-mode/" aria-hidden="true" tabindex="-1"><img src="/blog/assets/media/how-to-use-claude-code-plan-mode/hero.png" alt="" loading="lazy" decoding="async" /></a><div class="body"><div class="meta">- <time datetime="2026-07-03">Jul 3, 2026</time>+ <time datetime="2026-09-11">Sep 11, 2026</time><span class="dot" aria-hidden="true"></span>- <span>4 min</span>+ <span>5 min</span></div>- <h3><a href="/blog/command-center-guide/">The Command Center: Kanban, Fleet and Budgets in One Place</a></h3>- <p class="dek">A guide to Munder Difflin's Command Center in 0.5.2: the kanban with task dependencies, the ask me tab, triggers, memory, live token use against each agent's budget, and when to watch the board instead of the floor.</p>+ <h3><a href="/blog/how-to-use-claude-code-plan-mode/">How to Use Claude Code Plan Mode</a></h3>+ <p class="dek">How Claude Code's plan mode works: turning it on, what it blocks, what a real headless plan mode run prints, and how to leave it.</p><div class="foot"><span class="tag kind">Guides</span>- <a class="more" href="/blog/command-center-guide/" aria-label="Read: The Command Center: Kanban, Fleet and Budgets in One Place">Read →</a>+ <a class="more" href="/blog/how-to-use-claude-code-plan-mode/" aria-label="Read: How to Use Claude Code Plan Mode">Read →</a></div></div></article>diff --git a/docs/blog/feed.xml b/docs/blog/feed.xmlindex e42ed618..6aeb82be 100644--- a/docs/blog/feed.xml+++ b/docs/blog/feed.xml@@ -4,9 +4,49 @@<subtitle>Guides, deep dives, and comparisons on running multi-agent Claude Code: orchestration, agent memory, automation, and the tooling landscape.</subtitle><link href="https://munderdiffl.in/blog/feed.xml" rel="self" /><link href="https://munderdiffl.in/blog/" />- <updated>2026-09-11T00:00:00.000Z</updated>+ <updated>2026-09-14T00:00:00.000Z</updated><id>https://munderdiffl.in/blog/</id><author><name>Chaitanya Giri</name><uri>https://munderdiffl.in</uri></author>+ <entry>+ <title>How to Get the Most Out of Your Claude Code Max Plan</title>+ <link href="https://munderdiffl.in/blog/claude-code-max-plan-tips/" />+ <id>https://munderdiffl.in/blog/claude-code-max-plan-tips/</id>+ <published>2026-09-14T00:00:00.000Z</published>+ <updated>2026-09-14T00:00:00.000Z</updated><category term="Guides" />+ <summary>Stretch a Claude Code Max plan: model choice, context hygiene, prompt caching, subagents and unattended runs, checked against Anthropic's own pages.</summary>+ </entry>+ <entry>+ <title>How to Make the Most of Your Codex Max Plan</title>+ <link href="https://munderdiffl.in/blog/codex-max-plan-tips/" />+ <id>https://munderdiffl.in/blog/codex-max-plan-tips/</id>+ <published>2026-09-14T00:00:00.000Z</published>+ <updated>2026-09-14T00:00:00.000Z</updated><category term="Guides" />+ <summary>There is no Codex Max plan. What ChatGPT Pro 5x and 20x give you in Codex, how the weekly limit works, and how to stretch it.</summary>+ </entry>+ <entry>+ <title>Grok Bot Alternatives: Six Picks, Grouped by What You Want</title>+ <link href="https://munderdiffl.in/blog/grok-bot-alternatives/" />+ <id>https://munderdiffl.in/blog/grok-bot-alternatives/</id>+ <published>2026-09-14T00:00:00.000Z</published>+ <updated>2026-09-14T00:00:00.000Z</updated><category term="Comparisons" />+ <summary>Grok Bot runs every Bot on one shared cloud computer. Six alternatives checked on 14 Sep 2026, grouped by hosting, privacy and model choice.</summary>+ </entry>+ <entry>+ <title>Herdr Alternatives: What to Pick and Who Each One Fits</title>+ <link href="https://munderdiffl.in/blog/herdr-alternatives/" />+ <id>https://munderdiffl.in/blog/herdr-alternatives/</id>+ <published>2026-09-14T00:00:00.000Z</published>+ <updated>2026-09-14T00:00:00.000Z</updated><category term="Comparisons" />+ <summary>Herdr alternatives checked on 14 Sep 2026: tmux, Claude Squad, cmux, Orca, Conductor, Superset, Emdash and Munder Difflin, and who each fits.</summary>+ </entry>+ <entry>+ <title>OmniAgent Alternatives: What to Use Instead of Databricks Omnigent</title>+ <link href="https://munderdiffl.in/blog/omniagent-alternatives/" />+ <id>https://munderdiffl.in/blog/omniagent-alternatives/</id>+ <published>2026-09-14T00:00:00.000Z</published>+ <updated>2026-09-14T00:00:00.000Z</updated><category term="Comparisons" />+ <summary>OmniAgent is really Omnigent, the open source meta harness from Databricks. Alternatives checked on 14 Sep 2026, and who each one fits.</summary>+ </entry><entry><title>How to Use Claude Code Plan Mode</title><link href="https://munderdiffl.in/blog/how-to-use-claude-code-plan-mode/" />@@ -447,44 +487,4 @@<updated>2026-06-07T00:00:00.000Z</updated><category term="Story" /><summary>Munder Difflin v0.2.0 is here: a Command Center overhaul, per-agent token budgets, live OpenTelemetry observability, a circuit breaker, durable SQLite persistence, and a big round of community fixes.</summary></entry>- <entry>- <title>One Prompt, Five PR Reviews, and an Hourly Automation — A Dogfooding Story</title>- <link href="https://munderdiffl.in/blog/one-prompt-automated-pr-review/" />- <id>https://munderdiffl.in/blog/one-prompt-automated-pr-review/</id>- <published>2026-06-07T00:00:00.000Z</published>- <updated>2026-06-07T00:00:00.000Z</updated><category term="Story" />- <summary>How a single prompt to the Munder Difflin god agent reviewed all open PRs and set up a recurring hourly PR reviewer — while the repo was blowing up with 400+ stars.</summary>- </entry>- <entry>- <title>Does the June 2026 Agent SDK Change Affect Munder Difflin?</title>- <link href="https://munderdiffl.in/blog/does-the-june-2026-agent-sdk-change-affect-munder-difflin/" />- <id>https://munderdiffl.in/blog/does-the-june-2026-agent-sdk-change-affect-munder-difflin/</id>- <published>2026-06-06T00:00:00.000Z</published>- <updated>2026-06-06T00:00:00.000Z</updated><category term="Guides" />- <summary>From June 15, 2026 the Claude Agent SDK gets a separate credit. Munder Difflin drives the native Claude Code CLI, so your hive runs on your plan as before.</summary>- </entry>- <entry>- <title>The Best AI Coding Agents in 2026: A Field Guide</title>- <link href="https://munderdiffl.in/blog/best-ai-coding-agents/" />- <id>https://munderdiffl.in/blog/best-ai-coding-agents/</id>- <published>2026-06-05T00:00:00.000Z</published>- <updated>2026-06-05T00:00:00.000Z</updated><category term="Comparisons" />- <summary>A fair 2026 field guide to the best AI coding agents — Cursor, Aider, Cline, Devin, Copilot — by category, plus where a local multi-agent hive fits.</summary>- </entry>- <entry>- <title>Cline vs Munder Difflin: In-Editor Agent or Local Hive?</title>- <link href="https://munderdiffl.in/blog/cline-vs-munder-difflin/" />- <id>https://munderdiffl.in/blog/cline-vs-munder-difflin/</id>- <published>2026-06-05T00:00:00.000Z</published>- <updated>2026-06-05T00:00:00.000Z</updated><category term="Comparisons" />- <summary>A fair comparison of Cline and Munder Difflin — an in-editor BYOK coding agent vs a local multi-agent orchestration hive — and when to pick which.</summary>- </entry>- <entry>- <title>Compressing Agent Memory Without Losing the Original</title>- <link href="https://munderdiffl.in/blog/compressing-agent-memory/" />- <id>https://munderdiffl.in/blog/compressing-agent-memory/</id>- <published>2026-06-05T00:00:00.000Z</published>- <updated>2026-06-05T00:00:00.000Z</updated><category term="Internals" />- <summary>How and why to compress an agent's long-term memory: the toolbox, the lossy trap, and keeping a lossless original beside a compact copy.</summary>- </entry></feed>diff --git a/docs/blog/github-copilot-cli-vs-claude-code-for-hive-work/index.html b/docs/blog/github-copilot-cli-vs-claude-code-for-hive-work/index.htmlindex 53fb1d68..7b893863 100644--- a/docs/blog/github-copilot-cli-vs-claude-code-for-hive-work/index.html+++ b/docs/blog/github-copilot-cli-vs-claude-code-for-hive-work/index.html@@ -323,50 +323,50 @@<h2>Related in Comparisons</h2><div class="post-grid"><article class="card t-comparisons">- <a class="thumb t-comparisons" href="/blog/codex-cli-vs-claude-code/" aria-hidden="true" tabindex="-1"><img src="/blog/assets/media/codex-cli-vs-claude-code/hero.png" alt="" loading="lazy" decoding="async" /></a>+ <a class="thumb t-comparisons" href="/blog/grok-bot-alternatives/" aria-hidden="true" tabindex="-1"><img src="/blog/assets/media/grok-bot-alternatives/hero.png" alt="" loading="lazy" decoding="async" /></a><div class="body"><div class="meta">- <time datetime="2026-09-10">Sep 10, 2026</time>+ <time datetime="2026-09-14">Sep 14, 2026</time><span class="dot" aria-hidden="true"></span><span>5 min</span></div>- <h3><a href="/blog/codex-cli-vs-claude-code/">Codex CLI vs Claude Code</a></h3>- <p class="dek">Codex CLI and Claude Code compared firsthand: sandbox and approval flags, AGENTS.md vs CLAUDE.md, real pricing, and where each terminal agent wins.</p>+ <h3><a href="/blog/grok-bot-alternatives/">Grok Bot Alternatives: Six Picks, Grouped by What You Want</a></h3>+ <p class="dek">Grok Bot runs every Bot on one shared cloud computer. Six alternatives checked on 14 Sep 2026, grouped by hosting, privacy and model choice.</p><div class="foot"><span class="tag kind">Comparisons</span>- <a class="more" href="/blog/codex-cli-vs-claude-code/" aria-label="Read: Codex CLI vs Claude Code">Read →</a>+ <a class="more" href="/blog/grok-bot-alternatives/" aria-label="Read: Grok Bot Alternatives: Six Picks, Grouped by What You Want">Read →</a></div></div></article><article class="card t-comparisons">- <a class="thumb t-comparisons" href="/blog/qm-vs-munder-difflin/" aria-hidden="true" tabindex="-1"><img src="/blog/assets/media/qm-vs-munder-difflin/hero.png" alt="" loading="lazy" decoding="async" /></a>+ <a class="thumb t-comparisons" href="/blog/herdr-alternatives/" aria-hidden="true" tabindex="-1"><img src="/blog/assets/media/herdr-alternatives/hero.png" alt="" loading="lazy" decoding="async" /></a><div class="body"><div class="meta">- <time datetime="2026-08-06">Aug 6, 2026</time>+ <time datetime="2026-09-14">Sep 14, 2026</time><span class="dot" aria-hidden="true"></span>- <span>4 min</span>+ <span>5 min</span></div>- <h3><a href="/blog/qm-vs-munder-difflin/">qm vs Munder Difflin: YC's Multiplayer Harness or an Office of Your Clones?</a></h3>- <p class="dek">An honest September 2026 comparison of YC's qm and Munder Difflin. qm is a multiplayer agent harness a company deploys for Slack and the web. Munder Difflin runs an office of your clones on your own machine, with Teams to connect them.</p>+ <h3><a href="/blog/herdr-alternatives/">Herdr Alternatives: What to Pick and Who Each One Fits</a></h3>+ <p class="dek">Herdr alternatives checked on 14 Sep 2026: tmux, Claude Squad, cmux, Orca, Conductor, Superset, Emdash and Munder Difflin, and who each fits.</p><div class="foot"><span class="tag kind">Comparisons</span>- <a class="more" href="/blog/qm-vs-munder-difflin/" aria-label="Read: qm vs Munder Difflin: YC's Multiplayer Harness or an Office of Your Clones?">Read →</a>+ <a class="more" href="/blog/herdr-alternatives/" aria-label="Read: Herdr Alternatives: What to Pick and Who Each One Fits">Read →</a></div></div></article><article class="card t-comparisons">- <a class="thumb t-comparisons" href="/blog/crewai-autogen-vs-a-local-agent-harness/" aria-hidden="true" tabindex="-1"><img src="/blog/assets/media/crewai-autogen-vs-a-local-agent-harness/hero.png" alt="" loading="lazy" decoding="async" /></a>+ <a class="thumb t-comparisons" href="/blog/omniagent-alternatives/" aria-hidden="true" tabindex="-1"><span class="thumb-ph"><em class="ph-glyph" aria-hidden="true">✶</em><span>COMPARISONS</span></span></a><div class="body"><div class="meta">- <time datetime="2026-07-03">Jul 3, 2026</time>+ <time datetime="2026-09-14">Sep 14, 2026</time><span class="dot" aria-hidden="true"></span><span>5 min</span></div>- <h3><a href="/blog/crewai-autogen-vs-a-local-agent-harness/">CrewAI and AutoGen vs a Local Agent Harness: Framework or App?</a></h3>- <p class="dek">CrewAI, AutoGen (now Microsoft Agent Framework), and LangGraph are frameworks — Python you write to build your own agent system. A multi-agent harness is an app you download that runs a team on your repos today. Here's how to tell which one you actually need.</p>+ <h3><a href="/blog/omniagent-alternatives/">OmniAgent Alternatives: What to Use Instead of Databricks Omnigent</a></h3>+ <p class="dek">OmniAgent is really Omnigent, the open source meta harness from Databricks. Alternatives checked on 14 Sep 2026, and who each one fits.</p><div class="foot"><span class="tag kind">Comparisons</span>- <a class="more" href="/blog/crewai-autogen-vs-a-local-agent-harness/" aria-label="Read: CrewAI and AutoGen vs a Local Agent Harness: Framework or App?">Read →</a>+ <a class="more" href="/blog/omniagent-alternatives/" aria-label="Read: OmniAgent Alternatives: What to Use Instead of Databricks Omnigent">Read →</a></div></div></article>diff --git a/docs/blog/grok-bot-alternatives/index.html b/docs/blog/grok-bot-alternatives/index.htmlnew file mode 100644index 00000000..e45ccf43--- /dev/null+++ b/docs/blog/grok-bot-alternatives/index.html@@ -0,0 +1,389 @@+<!doctype html>+<html lang="en">+<head>+<meta charset="UTF-8" />+<meta name="viewport" content="width=device-width, initial-scale=1.0" />+<title>Grok Bot Alternatives: Six Picks, Grouped by What You Want — Munder Difflin Blog</title>+<meta name="description" content="Grok Bot runs every Bot on one shared cloud computer. Six alternatives checked on 14 Sep 2026, grouped by hosting, privacy and model choice." />+<link rel="canonical" href="https://munderdiffl.in/blog/grok-bot-alternatives/" />++<link rel="icon" type="image/png" href="https://munderdiffl.in/logo.png" />+<link rel="apple-touch-icon" href="https://munderdiffl.in/logo.png" />+<meta name="theme-color" content="#F5F2E8" />++<!-- Open Graph -->+<meta property="og:site_name" content="Munder Difflin Blog" />+<meta property="og:type" content="article" />+<meta property="og:title" content="Grok Bot Alternatives: Six Picks, Grouped by What You Want — Munder Difflin Blog" />+<meta property="og:description" content="Grok Bot runs every Bot on one shared cloud computer. Six alternatives checked on 14 Sep 2026, grouped by hosting, privacy and model choice." />+<meta property="og:url" content="https://munderdiffl.in/blog/grok-bot-alternatives/" />+<meta property="og:image" content="https://munderdiffl.in/media/og.png" />+<meta property="og:locale" content="en_US" />+<meta property="article:published_time" content="2026-09-14T00:00:00.000Z" />+<meta property="article:author" content="Chaitanya Giri" />+<meta property="article:tag" content="Comparisons" />+<meta property="article:tag" content="Local-First" />+<meta property="article:tag" content="Security" />+<meta property="article:tag" content="Open Source" />+<meta property="article:tag" content="Memory" />+++<!-- Twitter -->+<meta name="twitter:card" content="summary_large_image" />+<meta name="twitter:title" content="Grok Bot Alternatives: Six Picks, Grouped by What You Want — Munder Difflin Blog" />+<meta name="twitter:description" content="Grok Bot runs every Bot on one shared cloud computer. Six alternatives checked on 14 Sep 2026, grouped by hosting, privacy and model choice." />+<meta name="twitter:image" content="https://munderdiffl.in/media/og.png" />++<link rel="alternate" type="application/atom+xml" title="Munder Difflin Blog" href="https://munderdiffl.in/blog/feed.xml" />+<link rel="preconnect" href="https://fonts.googleapis.com" />+<link rel="preconnect" href="https://fonts.gstatic.com" crossorigin />+<link href="https://fonts.googleapis.com/css2?family=Fraunces:opsz,[email protected],500;9..144,600;9..144,700;9..144,900&family=Source+Serif+4:opsz,[email protected],400;8..60,600;8..60,700&family=Space+Grotesk:wght@500;600;700&family=JetBrains+Mono:wght@400;600&display=swap" rel="stylesheet" />+<link rel="stylesheet" href="/blog/assets/blog-press.css" />++<script type="application/ld+json">+{+ "@context": "https://schema.org",+ "@type": "BlogPosting",+ "headline": "Grok Bot Alternatives: Six Picks, Grouped by What You Want",+ "description": "Grok Bot runs every Bot on one shared cloud computer. Six alternatives checked on 14 Sep 2026, grouped by hosting, privacy and model choice.",+ "image": ["https://munderdiffl.in/media/og.png"],+ "datePublished": "2026-09-14T00:00:00.000Z",+ "dateModified": "2026-09-14T00:00:00.000Z",+ "author": { "@type": "Person", "name": "Chaitanya Giri" },+ "publisher": {+ "@type": "Organization",+ "name": "Munder Difflin",+ "logo": { "@type": "ImageObject", "url": "https://munderdiffl.in/logo.png" }+ },+ "mainEntityOfPage": { "@type": "WebPage", "@id": "https://munderdiffl.in/blog/grok-bot-alternatives/" },+ "keywords": "grok bot alternatives, grok bot alternative, grok bot vs openclaw, grok bot vs hermes agent, grok bot vs claude cowork, is grok bot free, does grok bot work on linux",+ "articleSection": "Comparisons",+ "inLanguage": "en-US",+ "url": "https://munderdiffl.in/blog/grok-bot-alternatives/"+}+</script>+<script type="application/ld+json">+{+ "@context": "https://schema.org",+ "@type": "BreadcrumbList",+ "itemListElement": [+ { "@type": "ListItem", "position": 1, "name": "Home", "item": "https://munderdiffl.in/" },+ { "@type": "ListItem", "position": 2, "name": "Blog", "item": "https://munderdiffl.in/blog/" },+ { "@type": "ListItem", "position": 3, "name": "Grok Bot Alternatives: Six Picks, Grouped by What You Want", "item": "https://munderdiffl.in/blog/grok-bot-alternatives/" }+ ]+}+</script>++<script type="application/ld+json">+{+ "@context": "https://schema.org",+ "@type": "FAQPage",+ "mainEntity": [+ { "@type": "Question", "name": "Is Grok Bot free?", "acceptedAnswer": { "@type": "Answer", "text": "Only as a trial. Cursor's Grok Bot plans page, checked on 14 Sep 2026, describes the free trial as a usage credit with a seven day window that never turns into a paid plan. After that you need a paid individual Cursor plan, Cursor Teams, or a linked SuperGrok, SuperGrok Plus, SuperGrok Heavy or X Premium+ subscription." } },+ { "@type": "Question", "name": "Does Grok Bot work on Linux?", "acceptedAnswer": { "@type": "Answer", "text": "Yes. SpaceXAI's Grok Bot FAQ lists desktop builds for Linux on x64 and Arm64, packaged as deb, rpm or AppImage, next to macOS, Windows, iPhone (iOS 18 or later) and Android 9 or later. The Bots' own computer is still in the cloud, not your Linux machine." } },+ { "@type": "Question", "name": "Can you choose which model Grok Bot uses?", "acceptedAnswer": { "@type": "Answer", "text": "No. SpaceXAI's security docs say Cursor manages model selection, there is no model picker for customers, and the serving mix can change over time. Enterprise teams can set a model allowlist, but the same docs say enforcement is not guaranteed." } },+ { "@type": "Question", "name": "Is Grok Bot the same as Grok on X?", "acceptedAnswer": { "@type": "Answer", "text": "No. Grok on X is the Grok assistant inside the X app. Grok Bot is a separate agent app that works on its own cloud computer, signs into your tools and runs jobs for you, and SpaceXAI lists the two as separate products." } }++ ]+}+</script>+++<script>+ // Anonymous blog analytics (PostHog) — same posture as the main site and the+ // app's TELEMETRY.md: public write-only token ('' = inert), anonymous-only+ // (person_profiles 'never'), no autocapture/recording, DNT respected.+ (function () {+ var PH_KEY = 'phc_qJzsokwcbtTGHemnvywR3nSqivNNgMjHeNVEWkZNydFB';+ if (!PH_KEY || navigator.doNotTrack === '1') return;+ var s = document.createElement('script');+ s.async = true;+ s.src = 'https://us-assets.i.posthog.com/static/array.js';+ s.onload = function () {+ if (!window.posthog) return;+ window.posthog.init(PH_KEY, {+ api_host: 'https://us.i.posthog.com',+ person_profiles: 'never',+ autocapture: false,+ before_send: function (event) {+ // PostHog fills $ip from the connection unless the event carries one.+ // Null it here and disable the GeoIP lookup so no IP, city, postal+ // code or lat/long is ever derived or stored for this page view.+ if (event && event.properties) {+ event.properties.$ip = null;+ event.properties.$geoip_disable = true;+ }+ return event;+ },+ disable_session_recording: true,+ respect_dnt: true+ });+ };+ document.head.appendChild(s);+ })();+</script>+</head>+<body class="theme-press">+<a class="skip-link" href="#main">Skip to content</a>+<nav id="nav">+ <a class="brand" href="https://munderdiffl.in" aria-label="Munder Difflin home">+ <img class="brand-logo" src="https://munderdiffl.in/logo.png" width="1318" height="840" alt="Munder Difflin, Inc. — Multi-Agent Harness" />+ </a>+ <span class="spacer"></span>+ <div class="links">+ <a href="/blog/">Latest</a>+ <a href="/blog/topics/">Topics</a>+ <a href="/blog/about/">About</a>+ <a href="https://munderdiffl.in">↗ Product</a>+ </div>+ <div class="nav-actions">+ <a class="btn sm" href="https://munderdiffl.in/blog/feed.xml" aria-label="RSS feed">⤵ RSS</a>+ <a class="btn sm primary" href="https://munderdiffl.in/#install">⤓ Download</a>+ </div>+</nav>++<main id="main">++<article class="t-comparisons">+ <header class="post-head wrap">+ <nav class="crumbs" aria-label="Breadcrumb">+ <a href="/blog/">Blog</a>+ <span>/</span>+ <a href="/blog/topics/comparisons/">Comparisons</a>+ </nav>+ <h1>Grok Bot Alternatives: Six Picks, Grouped by What You Want</h1>+ <p class="dek">Grok Bot runs every Bot on one shared cloud computer. Six alternatives checked on 14 Sep 2026, grouped by hosting, privacy and model choice.</p>+ <div class="byline">+ <span class="av" aria-hidden="true">MD</span>+ <strong>Chaitanya Giri</strong>+ <span class="dot" aria-hidden="true">·</span>+ <time datetime="2026-09-14">Sep 14, 2026</time>+ <span class="dot" aria-hidden="true">·</span>+ <span>5 min read</span>+ <span class="tag kind">Comparisons</span>+ </div>+ </header>++ <div class="hero-wrap wrap"><figure class="fig fig-hero"><img src="/blog/assets/media/grok-bot-alternatives/hero.png" alt="A yellow cartoon character with a clipboard at a signpost, choosing between a cloud kiosk, a phone, a laptop desk and a small home server" loading="lazy" decoding="async" /></figure></div>++ <div class="post-wrap wrap">+ <div class="prose">+ <p>The best Grok Bot alternatives depend on why you want out. For another hosted assistant, try ChatGPT Work, Gemini Spark or Claude Cowork. To keep memory and logins on your own hardware and pick the model yourself, try OpenClaw, Hermes Agent or NanoClaw. Everything below was checked on official pages and repos on 14 Sep 2026.</p>+<p>By Grok Bot we mean SpaceXAI’s agent app, hosted by Cursor (both SpaceX companies), not the Grok chatbot on X.</p>+<h2 id="what-is-grok-bot" tabindex="-1">What is Grok Bot? <a class="anchor" href="#what-is-grok-bot" aria-hidden="true">#</a></h2>+<p>Grok Bot is a team of AI agents, called Bots, that work on a computer of their own in the cloud. SpaceXAI launched it in beta on 11 Aug 2026. You message a Bot like a colleague, it signs into your tools, works across apps and websites, and comes back when something needs your approval. It keeps going with your laptop shut and can run routines on a schedule.</p>+<p>Inside SpaceXAI, people run several Bots with a chief of staff Bot handing work to specialists. That is the idea behind a <a href="/blog/what-is-a-multi-agent-harness/">multi-agent harness</a>, hosted for you. A marketplace on <a href="http://x.ai">x.ai</a> lists ready made Bots you can add, such as Credit Card Max.</p>+<p><a href="https://cursor.com/help/grok-bot/plans">Cursor’s Grok Bot plans page</a> says access comes with every paid individual Cursor plan and Cursor Teams, and Cursor listed Pro at $20 a month on 14 Sep 2026. Linking an individual SuperGrok or X Premium+ subscription also works; SuperGrok Lite doesn’t. Usage resets weekly. The desktop app runs on macOS, Windows and Linux, with apps for iPhone and Android.</p>+<h2 id="where-does-grok-bot-run-and-who-holds-your-data" tabindex="-1">Where does Grok Bot run, and who holds your data? <a class="anchor" href="#where-does-grok-bot-run-and-who-holds-your-data" aria-hidden="true">#</a></h2>+<p>Grok Bot runs only on Cursor’s cloud computers, and SpaceXAI’s <a href="https://docs.x.ai/grok-bot/security-faq">security FAQ</a> says those sit in the United States today. Running it on your own servers is not supported. Each user gets a dedicated virtual machine, so other users can’t reach yours. It also needs cloud data storage, so Cursor’s Legacy Privacy Mode is out. That is the trade for work that carries on after you close the lid. If you’d rather your files and memory stay on your desk, read <a href="/blog/why-local-first-matters-for-ai-agents/">why local first matters for AI agents</a>.</p>+<figure class="fig fig-inline"><img src="/blog/assets/media/grok-bot-alternatives/note-1.png" alt="Papers locked in a drawer inside a faraway cloud, next to the same papers on a desk beside a laptop" loading="lazy" decoding="async" /></figure>+<h2 id="what-can-a-bot-reach-and-remember" tabindex="-1">What can a Bot reach and remember? <a class="anchor" href="#what-can-a-bot-reach-and-remember" aria-hidden="true">#</a></h2>+<p>A Bot can reach anything on the cloud computer it shares with all your other Bots: its files, browser sessions and logins. SpaceXAI’s FAQ says plainly not to use separate Bots as a security boundary. SpaceXAI’s own Grok Bot 101 guide says that if you log into Amazon on that computer, the agent “can technically buy whatever it wants”. So can your recruiting Bot.</p>+<p>You write the guardrails in plain language. Auto Review checks tool calls and computer actions against your Require Approval and Always Allow rules, but SpaceXAI calls it model based and says it doesn’t review memory writes. A Bot remembers preferences, role context and summaries of past work, and the docs suggest checking the source before a big decision. There is no model picker either: Cursor chooses, and the mix can change. A helper that reads the open web, holds your logins and can send email is the risky mix called <a href="/blog/the-lethal-trifecta-for-coding-agents/">the lethal trifecta</a>.</p>+<figure class="fig fig-inline"><img src="/blog/assets/media/grok-bot-alternatives/note-2.png" alt="A yellow cartoon character hands a ring of keys to a small robot helper while keeping one key back, with an open notebook between them" loading="lazy" decoding="async" /></figure>+<h2 id="what-can-you-use-instead-of-grok-bot" tabindex="-1">What can you use instead of Grok Bot? <a class="anchor" href="#what-can-you-use-instead-of-grok-bot" aria-hidden="true">#</a></h2>+<p>Six good options, grouped by why you’re looking.</p>+<h3 id="you-want-a-hosted-assistant-just-not-this-one" tabindex="-1">You want a hosted assistant, just not this one <a class="anchor" href="#you-want-a-hosted-assistant-just-not-this-one" aria-hidden="true">#</a></h3>+<p><strong>ChatGPT Work</strong> is OpenAI’s agent inside ChatGPT, announced on 9 Jul 2026. Plugins connect it to Slack, Microsoft Teams, Google Drive, email and calendars, Scheduled Tasks run on a timer or when an event happens, and you decide when it needs your approval. In the Mac and Windows desktop app it can also use your local files, and there OpenAI offers Work on every plan, Free included.</p>+<p><strong>Gemini Spark</strong> suits you if your life runs on Gmail, Drive and Calendar. Google’s page says it keeps working with your phone and laptop off and is designed to check with you before major actions. It is offered to Google AI Pro and Ultra subscribers in select countries, plus select business users.</p>+<h3 id="your-work-lives-in-files-on-your-computer" tabindex="-1">Your work lives in files on your computer <a class="anchor" href="#your-work-lives-in-files-on-your-computer" aria-hidden="true">#</a></h3>+<p><strong><a href="https://support.claude.com/en/articles/13345190-get-started-with-cowork">Claude Cowork</a></strong> needs a paid Claude plan. In the macOS or Windows desktop app, Claude works in the folders you choose, and Anthropic says it can’t reach anything else and asks before deleting. By default the work, local files included, runs on Anthropic’s servers (in beta), so it is closer to Grok Bot than it looks, with a tighter fence around your files.</p>+<h3 id="you-want-the-memory-logins-and-model-on-your-side" tabindex="-1">You want the memory, logins and model on your side <a class="anchor" href="#you-want-the-memory-logins-and-model-on-your-side" aria-hidden="true">#</a></h3>+<p>These three are open source and you run them yourself. You bring the model, paid or local, and security becomes your job. We pulled each one’s licence and latest release from GitHub on 14 Sep 2026:</p>+<div class="table-scroll">+<table>+<thead>+<tr>+<th>Project</th>+<th>Licence</th>+<th>Latest release (UTC)</th>+</tr>+</thead>+<tbody>+<tr>+<td>OpenClaw</td>+<td>MIT</td>+<td>v2026.9.4, 11 Sep 2026</td>+</tr>+<tr>+<td>Hermes Agent</td>+<td>MIT</td>+<td>v2026.9.11, 11 Sep 2026</td>+</tr>+<tr>+<td>NanoClaw</td>+<td>MIT</td>+<td>v2.3.0, 24 Aug 2026</td>+</tr>+</tbody>+</table>+</div>+<p><strong><a href="https://github.com/openclaw/openclaw">OpenClaw</a></strong> is the closest thing to a personal assistant you own. It runs on your computer, replies in WhatsApp, Telegram, Slack, iMessage and 20+ other channels, and keeps state, memory and credentials on your hardware. Models are swappable plugins, local ones included, and there is no paid tier. The catch: tools run straight on your machine in the main session unless you set up sandboxing.</p>+<p><strong><a href="https://github.com/NousResearch/hermes-agent">Hermes Agent</a></strong> from Nous Research is the one to try if memory matters most. It curates its own memory, writes skills after complex tasks, runs scheduled jobs, and talks to you over Telegram, Discord, Slack, WhatsApp or Signal. It can live on your laptop or a cheap server, and <code>hermes model</code> switches between providers such as OpenRouter, OpenAI or your own endpoint.</p>+<p><strong>NanoClaw</strong> is the cautious pick. Each agent runs in its own Linux container and sees only the folders you mount. It is built on Anthropic’s Claude Agent SDK and needs Docker.</p>+<h3 id="you-want-coding-agents-on-your-own-machine" tabindex="-1">You want coding agents on your own machine <a class="anchor" href="#you-want-coding-agents-on-your-own-machine" aria-hidden="true">#</a></h3>+<p>Munder Difflin, which we make, is not a personal assistant for your inbox and calendar. It fits a narrower need: a team of coding agents (Claude Code, Codex, Gemini CLI and nine others) working on your own computer. A Slack message can start an agent, missions can run on a schedule, and with your own OpenAI API key you can direct the agents by voice, with a spoken confirmation before anything destructive. The agents stop when your machine does. If you want errands and email handled, pick an assistant above.</p>+<h2 id="is-grok-bot-worth-it" tabindex="-1">Is Grok Bot worth it? <a class="anchor" href="#is-grok-bot-worth-it" aria-hidden="true">#</a></h2>+<p>Grok Bot is worth it if you want almost no setup and are fine with the cloud. A helper that works with the lid shut and hands you the screen for a password or two factor code is hard to build yourself, and a paid individual Cursor plan already includes it. Look elsewhere if you need your data outside the United States, a model you choose, or a wall between one helper and the next.</p>++++ <section class="faq" aria-label="Frequently asked questions">+ <h2 id="faq">FAQ</h2>++ <div class="qa">+ <p class="q">Is Grok Bot free?</p>+ <p class="a">Only as a trial. Cursor's Grok Bot plans page, checked on 14 Sep 2026, describes the free trial as a usage credit with a seven day window that never turns into a paid plan. After that you need a paid individual Cursor plan, Cursor Teams, or a linked SuperGrok, SuperGrok Plus, SuperGrok Heavy or X Premium+ subscription.</p>+ </div>++ <div class="qa">+ <p class="q">Does Grok Bot work on Linux?</p>+ <p class="a">Yes. SpaceXAI's Grok Bot FAQ lists desktop builds for Linux on x64 and Arm64, packaged as deb, rpm or AppImage, next to macOS, Windows, iPhone (iOS 18 or later) and Android 9 or later. The Bots' own computer is still in the cloud, not your Linux machine.</p>+ </div>++ <div class="qa">+ <p class="q">Can you choose which model Grok Bot uses?</p>+ <p class="a">No. SpaceXAI's security docs say Cursor manages model selection, there is no model picker for customers, and the serving mix can change over time. Enterprise teams can set a model allowlist, but the same docs say enforcement is not guaranteed.</p>+ </div>++ <div class="qa">+ <p class="q">Is Grok Bot the same as Grok on X?</p>+ <p class="a">No. Grok on X is the Grok assistant inside the X app. Grok Bot is a separate agent app that works on its own cloud computer, signs into your tools and runs jobs for you, and SpaceXAI lists the two as separate products.</p>+ </div>++ </section>++++ <hr />+ <div class="share">+ <span class="lbl">Tags</span>+ <a class="tag" href="/blog/tags/comparisons/">Comparisons</a><a class="tag" href="/blog/tags/local-first/">Local-First</a><a class="tag" href="/blog/tags/security/">Security</a><a class="tag" href="/blog/tags/open-source/">Open Source</a><a class="tag" href="/blog/tags/memory/">Memory</a>+ </div>++ </div>+++ <aside class="toc-rail" aria-label="Table of contents">+ <div class="tt">On this page</div>+ <ol>+ <li class="lvl-2"><a href="#what-is-grok-bot">What is Grok Bot?</a></li><li class="lvl-2"><a href="#where-does-grok-bot-run-and-who-holds-your-data">Where does Grok Bot run, and who holds your data?</a></li><li class="lvl-2"><a href="#what-can-a-bot-reach-and-remember">What can a Bot reach and remember?</a></li><li class="lvl-2"><a href="#what-can-you-use-instead-of-grok-bot">What can you use instead of Grok Bot?</a></li><li class="lvl-3"><a href="#you-want-a-hosted-assistant-just-not-this-one">You want a hosted assistant, just not this one</a></li><li class="lvl-3"><a href="#your-work-lives-in-files-on-your-computer">Your work lives in files on your computer</a></li><li class="lvl-3"><a href="#you-want-the-memory-logins-and-model-on-your-side">You want the memory, logins and model on your side</a></li><li class="lvl-3"><a href="#you-want-coding-agents-on-your-own-machine">You want coding agents on your own machine</a></li><li class="lvl-2"><a href="#is-grok-bot-worth-it">Is Grok Bot worth it?</a></li>+ </ol>+ </aside>++ </div>++ <footer class="post-foot wrap"><div class="prevnext">+ <a class="pn prev" href="/blog/herdr-alternatives/"><span class="k">← Older</span><span class="t">Herdr Alternatives: What to Pick and Who Each One Fits</span></a>+ <a class="pn next" href="/blog/codex-max-plan-tips/"><span class="k">Newer →</span><span class="t">How to Make the Most of Your Codex Max Plan</span></a>+ </div>+ <section class="related">+ <h2>Related in Comparisons</h2>+ <div class="post-grid">+ <article class="card t-comparisons">+ <a class="thumb t-comparisons" href="/blog/herdr-alternatives/" aria-hidden="true" tabindex="-1"><img src="/blog/assets/media/herdr-alternatives/hero.png" alt="" loading="lazy" decoding="async" /></a>+ <div class="body">+ <div class="meta">+ <time datetime="2026-09-14">Sep 14, 2026</time>+ <span class="dot" aria-hidden="true"></span>+ <span>5 min</span>+ </div>+ <h3><a href="/blog/herdr-alternatives/">Herdr Alternatives: What to Pick and Who Each One Fits</a></h3>+ <p class="dek">Herdr alternatives checked on 14 Sep 2026: tmux, Claude Squad, cmux, Orca, Conductor, Superset, Emdash and Munder Difflin, and who each fits.</p>+ <div class="foot">+ <span class="tag kind">Comparisons</span>+ <a class="more" href="/blog/herdr-alternatives/" aria-label="Read: Herdr Alternatives: What to Pick and Who Each One Fits">Read →</a>+ </div>+ </div>+</article>+<article class="card t-comparisons">+ <a class="thumb t-comparisons" href="/blog/omniagent-alternatives/" aria-hidden="true" tabindex="-1"><span class="thumb-ph"><em class="ph-glyph" aria-hidden="true">✶</em><span>COMPARISONS</span></span></a>+ <div class="body">+ <div class="meta">+ <time datetime="2026-09-14">Sep 14, 2026</time>+ <span class="dot" aria-hidden="true"></span>+ <span>5 min</span>+ </div>+ <h3><a href="/blog/omniagent-alternatives/">OmniAgent Alternatives: What to Use Instead of Databricks Omnigent</a></h3>+ <p class="dek">OmniAgent is really Omnigent, the open source meta harness from Databricks. Alternatives checked on 14 Sep 2026, and who each one fits.</p>+ <div class="foot">+ <span class="tag kind">Comparisons</span>+ <a class="more" href="/blog/omniagent-alternatives/" aria-label="Read: OmniAgent Alternatives: What to Use Instead of Databricks Omnigent">Read →</a>+ </div>+ </div>+</article>+<article class="card t-comparisons">+ <a class="thumb t-comparisons" href="/blog/codex-cli-vs-claude-code/" aria-hidden="true" tabindex="-1"><img src="/blog/assets/media/codex-cli-vs-claude-code/hero.png" alt="" loading="lazy" decoding="async" /></a>+ <div class="body">+ <div class="meta">+ <time datetime="2026-09-10">Sep 10, 2026</time>+ <span class="dot" aria-hidden="true"></span>+ <span>5 min</span>+ </div>+ <h3><a href="/blog/codex-cli-vs-claude-code/">Codex CLI vs Claude Code</a></h3>+ <p class="dek">Codex CLI and Claude Code compared firsthand: sandbox and approval flags, AGENTS.md vs CLAUDE.md, real pricing, and where each terminal agent wins.</p>+ <div class="foot">+ <span class="tag kind">Comparisons</span>+ <a class="more" href="/blog/codex-cli-vs-claude-code/" aria-label="Read: Codex CLI vs Claude Code">Read →</a>+ </div>+ </div>+</article>++ </div>+ </section>++ </footer>+</article>++</main>+<footer class="site-foot">+ <div class="wrap">+ <div class="foot-top">+ <a class="foot-brand brand" href="https://munderdiffl.in" aria-label="Munder Difflin home">+ <img class="brand-logo" src="https://munderdiffl.in/logo.png" width="1318" height="840" alt="Munder Difflin, Inc. — Multi-Agent Harness" />+ </a>+ <div class="foot-links">+ <a href="/blog/">Latest</a>+ <a href="/blog/topics/">Topics</a>+ <a href="/blog/about/">About</a>+ <a href="https://munderdiffl.in/blog/feed.xml">RSS</a>+ <a href="https://github.com/chaitanyagiri/munder-difflin">GitHub</a>+ <a href="https://munderdiffl.in">munderdiffl.in ↗</a>+ </div>+ </div>+ <div class="foot-meta">+ © 2026 Munder Difflin · Local-first · MIT-licensed ·+ Built on <a href="https://munderdiffl.in">Electron, React, Pixi.js, xterm.js & node-pty</a>.+ Run an office of agents while you sleep.+ </div>+ </div>+</footer>++<script>+ // sticky-nav border on scroll+ (function () {+ var nav = document.getElementById('nav');+ if (!nav) return;+ var onScroll = function () { nav.classList.toggle('scrolled', window.scrollY > 8); };+ onScroll(); window.addEventListener('scroll', onScroll, { passive: true });+ })();+ // YouTube click-to-load: thumbnail button → youtube-nocookie iframe+ (function () {+ document.addEventListener('click', function (e) {+ var btn = e.target.closest('.yt-load');+ if (!btn) return;+ var box = btn.closest('.yt');+ var id = box && box.getAttribute('data-yt');+ if (!id) return;+ var frame = document.createElement('iframe');+ frame.src = 'https://www.youtube-nocookie.com/embed/' + id + '?autoplay=1';+ frame.title = box.getAttribute('data-title') || 'YouTube video';+ frame.allow = 'accelerometer; autoplay; clipboard-write; encrypted-media; gyroscope; picture-in-picture; web-share';+ frame.setAttribute('allowfullscreen', '');+ box.replaceChildren(frame);+ });+ })();+</script>++</body>+</html>diff --git a/docs/blog/herdr-alternatives/index.html b/docs/blog/herdr-alternatives/index.htmlnew file mode 100644index 00000000..2e931b6e--- /dev/null+++ b/docs/blog/herdr-alternatives/index.html@@ -0,0 +1,375 @@+<!doctype html>+<html lang="en">+<head>+<meta charset="UTF-8" />+<meta name="viewport" content="width=device-width, initial-scale=1.0" />+<title>Herdr Alternatives: What to Pick and Who Each One Fits — Munder Difflin Blog</title>+<meta name="description" content="Herdr alternatives checked on 14 Sep 2026: tmux, Claude Squad, cmux, Orca, Conductor, Superset, Emdash and Munder Difflin, and who each fits." />+<link rel="canonical" href="https://munderdiffl.in/blog/herdr-alternatives/" />++<link rel="icon" type="image/png" href="https://munderdiffl.in/logo.png" />+<link rel="apple-touch-icon" href="https://munderdiffl.in/logo.png" />+<meta name="theme-color" content="#F5F2E8" />++<!-- Open Graph -->+<meta property="og:site_name" content="Munder Difflin Blog" />+<meta property="og:type" content="article" />+<meta property="og:title" content="Herdr Alternatives: What to Pick and Who Each One Fits — Munder Difflin Blog" />+<meta property="og:description" content="Herdr alternatives checked on 14 Sep 2026: tmux, Claude Squad, cmux, Orca, Conductor, Superset, Emdash and Munder Difflin, and who each fits." />+<meta property="og:url" content="https://munderdiffl.in/blog/herdr-alternatives/" />+<meta property="og:image" content="https://munderdiffl.in/media/og.png" />+<meta property="og:locale" content="en_US" />+<meta property="article:published_time" content="2026-09-14T00:00:00.000Z" />+<meta property="article:author" content="Chaitanya Giri" />+<meta property="article:tag" content="Comparisons" />+<meta property="article:tag" content="Multi-Agent" />+<meta property="article:tag" content="Claude Code" />+<meta property="article:tag" content="Tools" />+<meta property="article:tag" content="Open Source" />+++<!-- Twitter -->+<meta name="twitter:card" content="summary_large_image" />+<meta name="twitter:title" content="Herdr Alternatives: What to Pick and Who Each One Fits — Munder Difflin Blog" />+<meta name="twitter:description" content="Herdr alternatives checked on 14 Sep 2026: tmux, Claude Squad, cmux, Orca, Conductor, Superset, Emdash and Munder Difflin, and who each fits." />+<meta name="twitter:image" content="https://munderdiffl.in/media/og.png" />++<link rel="alternate" type="application/atom+xml" title="Munder Difflin Blog" href="https://munderdiffl.in/blog/feed.xml" />+<link rel="preconnect" href="https://fonts.googleapis.com" />+<link rel="preconnect" href="https://fonts.gstatic.com" crossorigin />+<link href="https://fonts.googleapis.com/css2?family=Fraunces:opsz,[email protected],500;9..144,600;9..144,700;9..144,900&family=Source+Serif+4:opsz,[email protected],400;8..60,600;8..60,700&family=Space+Grotesk:wght@500;600;700&family=JetBrains+Mono:wght@400;600&display=swap" rel="stylesheet" />+<link rel="stylesheet" href="/blog/assets/blog-press.css" />++<script type="application/ld+json">+{+ "@context": "https://schema.org",+ "@type": "BlogPosting",+ "headline": "Herdr Alternatives: What to Pick and Who Each One Fits",+ "description": "Herdr alternatives checked on 14 Sep 2026: tmux, Claude Squad, cmux, Orca, Conductor, Superset, Emdash and Munder Difflin, and who each fits.",+ "image": ["https://munderdiffl.in/media/og.png"],+ "datePublished": "2026-09-14T00:00:00.000Z",+ "dateModified": "2026-09-14T00:00:00.000Z",+ "author": { "@type": "Person", "name": "Chaitanya Giri" },+ "publisher": {+ "@type": "Organization",+ "name": "Munder Difflin",+ "logo": { "@type": "ImageObject", "url": "https://munderdiffl.in/logo.png" }+ },+ "mainEntityOfPage": { "@type": "WebPage", "@id": "https://munderdiffl.in/blog/herdr-alternatives/" },+ "keywords": "herdr alternatives, herdr tmux alternative, herdr alternatives for windows, herdr vs tmux, herdr vs zellij, is herdr open source",+ "articleSection": "Comparisons",+ "inLanguage": "en-US",+ "url": "https://munderdiffl.in/blog/herdr-alternatives/"+}+</script>+<script type="application/ld+json">+{+ "@context": "https://schema.org",+ "@type": "BreadcrumbList",+ "itemListElement": [+ { "@type": "ListItem", "position": 1, "name": "Home", "item": "https://munderdiffl.in/" },+ { "@type": "ListItem", "position": 2, "name": "Blog", "item": "https://munderdiffl.in/blog/" },+ { "@type": "ListItem", "position": 3, "name": "Herdr Alternatives: What to Pick and Who Each One Fits", "item": "https://munderdiffl.in/blog/herdr-alternatives/" }+ ]+}+</script>++<script type="application/ld+json">+{+ "@context": "https://schema.org",+ "@type": "FAQPage",+ "mainEntity": [+ { "@type": "Question", "name": "Is herdr open source?", "acceptedAnswer": { "@type": "Answer", "text": "Yes. Herdr is licensed under Apache 2.0, per its GitHub repository checked on 14 Sep 2026. It launched under AGPL 3.0 in March 2026, added a commercial license option on 26 May 2026, and was relicensed to Apache 2.0 on 22 Jul 2026, so reviews that still call it AGPL are out of date." } },+ { "@type": "Question", "name": "Does herdr work on Windows?", "acceptedAnswer": { "@type": "Answer", "text": "Yes. Herdr's changelog marks Windows support as generally available in 0.8.2 on 19 Aug 2026, and the 0.9.0 release on 7 Sep 2026 ships a Windows x86_64 build next to the Linux and macOS builds. Early August posts that call Windows a beta predate that change." } },+ { "@type": "Question", "name": "Does herdr replace tmux?", "acceptedAnswer": { "@type": "Answer", "text": "For agent work, it can. Herdr keeps panes alive in a background server the way tmux does, uses tmux style prefix keys, and adds agent states on top. Without coding agents, plain tmux does the job and has years more use behind it." } },+ { "@type": "Question", "name": "What is the difference between herdr and Claude Squad?", "acceptedAnswer": { "@type": "Answer", "text": "Herdr owns the terminals and tracks each agent's state, while Claude Squad is a terminal UI that sits on top of tmux and gives every task its own git worktree and branch. Claude Squad needs tmux and the GitHub CLI installed, per its README checked on 14 Sep 2026." } },+ { "@type": "Question", "name": "Can herdr agents share memory or a task board?", "acceptedAnswer": { "@type": "Answer", "text": "Not out of the box. Herdr's English docs, checked on 14 Sep 2026, have no page about shared memory, a task board or scheduling, and coordination happens through its CLI and socket API instead. If you want those parts built in, an orchestrated desktop app is the closer fit." } }++ ]+}+</script>+++<script>+ // Anonymous blog analytics (PostHog) — same posture as the main site and the+ // app's TELEMETRY.md: public write-only token ('' = inert), anonymous-only+ // (person_profiles 'never'), no autocapture/recording, DNT respected.+ (function () {+ var PH_KEY = 'phc_qJzsokwcbtTGHemnvywR3nSqivNNgMjHeNVEWkZNydFB';+ if (!PH_KEY || navigator.doNotTrack === '1') return;+ var s = document.createElement('script');+ s.async = true;+ s.src = 'https://us-assets.i.posthog.com/static/array.js';+ s.onload = function () {+ if (!window.posthog) return;+ window.posthog.init(PH_KEY, {+ api_host: 'https://us.i.posthog.com',+ person_profiles: 'never',+ autocapture: false,+ before_send: function (event) {+ // PostHog fills $ip from the connection unless the event carries one.+ // Null it here and disable the GeoIP lookup so no IP, city, postal+ // code or lat/long is ever derived or stored for this page view.+ if (event && event.properties) {+ event.properties.$ip = null;+ event.properties.$geoip_disable = true;+ }+ return event;+ },+ disable_session_recording: true,+ respect_dnt: true+ });+ };+ document.head.appendChild(s);+ })();+</script>+</head>+<body class="theme-press">+<a class="skip-link" href="#main">Skip to content</a>+<nav id="nav">+ <a class="brand" href="https://munderdiffl.in" aria-label="Munder Difflin home">+ <img class="brand-logo" src="https://munderdiffl.in/logo.png" width="1318" height="840" alt="Munder Difflin, Inc. — Multi-Agent Harness" />+ </a>+ <span class="spacer"></span>+ <div class="links">+ <a href="/blog/">Latest</a>+ <a href="/blog/topics/">Topics</a>+ <a href="/blog/about/">About</a>+ <a href="https://munderdiffl.in">↗ Product</a>+ </div>+ <div class="nav-actions">+ <a class="btn sm" href="https://munderdiffl.in/blog/feed.xml" aria-label="RSS feed">⤵ RSS</a>+ <a class="btn sm primary" href="https://munderdiffl.in/#install">⤓ Download</a>+ </div>+</nav>++<main id="main">++<article class="t-comparisons">+ <header class="post-head wrap">+ <nav class="crumbs" aria-label="Breadcrumb">+ <a href="/blog/">Blog</a>+ <span>/</span>+ <a href="/blog/topics/comparisons/">Comparisons</a>+ </nav>+ <h1>Herdr Alternatives: What to Pick and Who Each One Fits</h1>+ <p class="dek">Herdr alternatives checked on 14 Sep 2026: tmux, Claude Squad, cmux, Orca, Conductor, Superset, Emdash and Munder Difflin, and who each fits.</p>+ <div class="byline">+ <span class="av" aria-hidden="true">MD</span>+ <strong>Chaitanya Giri</strong>+ <span class="dot" aria-hidden="true">·</span>+ <time datetime="2026-09-14">Sep 14, 2026</time>+ <span class="dot" aria-hidden="true">·</span>+ <span>5 min read</span>+ <span class="tag kind">Comparisons</span>+ </div>+ </header>++ <div class="hero-wrap wrap"><figure class="fig fig-hero"><img src="/blog/assets/media/herdr-alternatives/hero.png" alt="A yellow cartoon character as a shepherd with a crook, herding small terminal windows with legs across a hill" loading="lazy" decoding="async" /></figure></div>++ <div class="post-wrap wrap">+ <div class="prose">+ <p>The main herdr alternatives are plain tmux or Zellij, Claude Squad, cmux, Orca, Conductor, Superset, Emdash and Munder Difflin. Stay on herdr if you live in a terminal or work over SSH. Switch when you want a desktop window, agents that share memory, or something that hands out the work so you don’t have to.</p>+<p>Herdr is good at its job, so this post sorts the options by why you are leaving. For the wider field, see our roundup of <a href="/blog/best-claude-code-multi-agent-tools/">multi-agent tools built around Claude Code</a>.</p>+<h2 id="what-is-herdr-exactly" tabindex="-1">What is herdr, exactly? <a class="anchor" href="#what-is-herdr-exactly" aria-hidden="true">#</a></h2>+<p>Herdr is an open source terminal multiplexer, written in Rust, that runs coding agents such as Claude Code, Codex and OpenCode in panes and labels each pane with the agent’s state. It is one binary that runs inside the terminal you already use. A background server owns the terminals, so closing the client or dropping an SSH connection does not stop the work: <code>ctrl+b q</code> detaches and <code>herdr</code> reattaches, per the <a href="https://github.com/herdrdev/herdr">herdr README</a>.</p>+<p>Search results mix in forks such as codeaudit/herdr; the upstream project is herdrdev/herdr. We pulled its latest release on 14 Sep 2026:</p>+<pre><code>$ gh api repos/herdrdev/herdr/releases/latest --jq '.tag_name, .published_at, (.assets[].name)'+v0.9.0+2026-09-07T19:21:31Z+herdr-linux-aarch64+herdr-linux-x86_64+herdr-macos-aarch64+herdr-macos-x86_64+herdr-windows-x86_64.zip+</code></pre>+<p>The repo also corrects two things older reviews still say. Windows is a normal build now: the changelog marked Windows support generally available in 0.8.2 on 19 Aug 2026. And the history of the <code>LICENSE</code> file (<code>gh api 'repos/herdrdev/herdr/commits?path=LICENSE'</code>) shows a relicense to Apache 2.0 on 22 Jul 2026, replacing the AGPL 3.0 license it launched with.</p>+<h2 id="why-look-for-a-herdr-alternative" tabindex="-1">Why look for a herdr alternative? <a class="anchor" href="#why-look-for-a-herdr-alternative" aria-hidden="true">#</a></h2>+<p>You might leave herdr for one of four reasons: you want a desktop window, memory shared between agents, a built-in orchestrator, or simply less software. None of the 21 English doc pages for herdr 0.9.0 covers shared memory, a task board or scheduling (checked 14 Sep 2026). Coordination comes as primitives: a script or an agent can run <code>herdr agent prompt reviewer "Review the current diff" --wait</code> and then <code>herdr agent wait reviewer --until blocked</code>. That is flexible if you enjoy writing the glue, and a weekend you won’t get back if you don’t.</p>+<p>The real split is terminal tools versus task tools. In herdr, tmux or Claude Squad the unit is a terminal, and you read every one and decide what happens next. In a desktop app with an orchestrator the unit is a task: something assigns it, tracks it and asks you when it is stuck. Herdr’s own <a href="https://herdr.dev/compare/">compare page</a> argues the other side, and fairly: “quit their app and the agents stop; detach every Herdr client and they don’t.”</p>+<figure class="fig fig-inline"><img src="/blog/assets/media/herdr-alternatives/note-1.png" alt="A monitor split into terminal panes next to a small office floor with a bean at each desk" loading="lazy" decoding="async" /></figure>+<h2 id="is-plain-tmux-enough-instead-of-herdr" tabindex="-1">Is plain tmux enough instead of herdr? <a class="anchor" href="#is-plain-tmux-enough-instead-of-herdr" aria-hidden="true">#</a></h2>+<p>Plain tmux is enough if you run two or three agents and check on them often. It keeps sessions alive over SSH, it is one package install away on any Linux or macOS machine, and it adds nothing between you and your shells. Zellij sits in the same category. Neither knows what runs inside a pane, so a Claude Code session that is thinking looks the same as one parked on a permission prompt. Where a hand built tmux setup starts to creak is covered in <a href="/blog/tmux-and-scripts-vs-an-agent-harness/">running agents in tmux vs an agent harness</a>.</p>+<p>What herdr adds is knowing which agent needs you right now. Herdr’s <a href="https://herdr.dev/docs/concepts/">concepts docs</a> define the states: blocked means the agent needs input, approval or a decision; working means it is running; done means it finished and you have not looked yet; idle means finished and seen; unknown means herdr cannot tell. For agents it reads from the screen, the <a href="https://herdr.dev/docs/agents/">supported agents page</a> calls blocked detection deliberately strict: when no rule matches a prompt, herdr falls back to idle rather than guessing. Any replacement should answer that as fast, or you are back to cycling panes.</p>+<figure class="fig fig-inline"><img src="/blog/assets/media/herdr-alternatives/note-2.png" alt="Four terminal windows showing an hourglass, a spinning gear, a check mark and a sleeping cloud" loading="lazy" decoding="async" /></figure>+<h2 id="which-herdr-alternatives-are-worth-trying" tabindex="-1">Which herdr alternatives are worth trying? <a class="anchor" href="#which-herdr-alternatives-are-worth-trying" aria-hidden="true">#</a></h2>+<p>Seven are active, each checked on its own repo or site on 14 Sep 2026. Pick by your reason for leaving.</p>+<ul>+<li><strong>Claude Squad, for something smaller on top of the tmux you already have.</strong> <a href="https://github.com/smtg-ai/claude-squad">Claude Squad</a> is a terminal UI for Claude Code, Codex, OpenCode and Amp that gives each agent its own tmux session and git worktree. It needs tmux and the GitHub CLI, is AGPL 3.0 licensed, and shipped v1.0.20 on 20 Aug 2026.</li>+<li><strong>cmux, for a native Mac window.</strong> cmux is a Ghostty based macOS terminal with vertical tabs and notification rings for coding agents. It is Mac only, so no help on a headless Linux box.</li>+<li><strong>Orca, for a full GUI on any desktop.</strong> Orca is an MIT licensed app for macOS, Windows and Linux that runs each agent in its own worktree, with a built-in browser and SSH remote worktrees. It shipped v1.4.201 on 13 Sep 2026, and our <a href="/blog/orca-vs-munder-difflin/">Orca vs Munder Difflin</a> post goes further.</li>+<li><strong>Conductor, if agents in the cloud suit you.</strong> Conductor is a Mac app that runs Claude Code, Codex, Cursor and OpenCode agents, and its homepage now leads with Conductor Cloud, where each agent gets an isolated microVM. It was on 0.85.0 as of 9 Sep 2026.</li>+<li><strong>Superset, for an IDE built around parallel agents.</strong> Superset brings Claude Code, Codex, OpenCode or any other coding agent into one workspace, isolates each task’s changes and lets you review them in one place. Its license is source available (ELv2), not open source.</li>+<li><strong>Emdash, for the same idea under Apache 2.0.</strong> Emdash is an open source agentic development environment from a YC W26 company that runs several coding agents in parallel with any provider.</li>+<li><strong>Munder Difflin, for agents that work as a team.</strong> This one is ours: a local desktop app for macOS, Windows and Linux where each agent is a real CLI in a real terminal, from any of twelve CLIs. Michael, your clone, hands out the work, the agents share a long-term memory, and anything waiting on you lands on the ASK ME board. The honest limit: as of 0.5.2, quitting the app stops every agent terminal, so there is no detach and walk away.</li>+</ul>+<p>Three names from older lists need a note. On 10 Apr 2026 Vibe Kanban announced it is <a href="https://www.vibekanban.com/blog/shutdown">sunsetting</a>; the code lives on as a community maintained project. Crystal’s repo now says it is Nimbalyst. YC’s qm is a multiplayer harness a company deploys for Slack and the web, a different job from a multiplexer.</p>+<h2 id="when-should-you-stay-on-herdr" tabindex="-1">When should you stay on herdr? <a class="anchor" href="#when-should-you-stay-on-herdr" aria-hidden="true">#</a></h2>+<p>Stay on herdr if you live in the terminal, work on remote machines over SSH, or want agents running after you close the client. Its 0.9.0 release manages local and saved SSH machines from one window, and its docs show it running from an ordinary SSH client on a phone with no mobile app. If what you really want is a crew that plans, remembers and asks before it guesses, a task tool saves you writing that layer yourself.</p>++++ <section class="faq" aria-label="Frequently asked questions">+ <h2 id="faq">FAQ</h2>++ <div class="qa">+ <p class="q">Is herdr open source?</p>+ <p class="a">Yes. Herdr is licensed under Apache 2.0, per its GitHub repository checked on 14 Sep 2026. It launched under AGPL 3.0 in March 2026, added a commercial license option on 26 May 2026, and was relicensed to Apache 2.0 on 22 Jul 2026, so reviews that still call it AGPL are out of date.</p>+ </div>++ <div class="qa">+ <p class="q">Does herdr work on Windows?</p>+ <p class="a">Yes. Herdr's changelog marks Windows support as generally available in 0.8.2 on 19 Aug 2026, and the 0.9.0 release on 7 Sep 2026 ships a Windows x86_64 build next to the Linux and macOS builds. Early August posts that call Windows a beta predate that change.</p>+ </div>++ <div class="qa">+ <p class="q">Does herdr replace tmux?</p>+ <p class="a">For agent work, it can. Herdr keeps panes alive in a background server the way tmux does, uses tmux style prefix keys, and adds agent states on top. Without coding agents, plain tmux does the job and has years more use behind it.</p>+ </div>++ <div class="qa">+ <p class="q">What is the difference between herdr and Claude Squad?</p>+ <p class="a">Herdr owns the terminals and tracks each agent's state, while Claude Squad is a terminal UI that sits on top of tmux and gives every task its own git worktree and branch. Claude Squad needs tmux and the GitHub CLI installed, per its README checked on 14 Sep 2026.</p>+ </div>++ <div class="qa">+ <p class="q">Can herdr agents share memory or a task board?</p>+ <p class="a">Not out of the box. Herdr's English docs, checked on 14 Sep 2026, have no page about shared memory, a task board or scheduling, and coordination happens through its CLI and socket API instead. If you want those parts built in, an orchestrated desktop app is the closer fit.</p>+ </div>++ </section>++++ <hr />+ <div class="share">+ <span class="lbl">Tags</span>+ <a class="tag" href="/blog/tags/comparisons/">Comparisons</a><a class="tag" href="/blog/tags/multi-agent/">Multi-Agent</a><a class="tag" href="/blog/tags/claude-code/">Claude Code</a><a class="tag" href="/blog/tags/tools/">Tools</a><a class="tag" href="/blog/tags/open-source/">Open Source</a>+ </div>++ </div>+++ <aside class="toc-rail" aria-label="Table of contents">+ <div class="tt">On this page</div>+ <ol>+ <li class="lvl-2"><a href="#what-is-herdr-exactly">What is herdr, exactly?</a></li><li class="lvl-2"><a href="#why-look-for-a-herdr-alternative">Why look for a herdr alternative?</a></li><li class="lvl-2"><a href="#is-plain-tmux-enough-instead-of-herdr">Is plain tmux enough instead of herdr?</a></li><li class="lvl-2"><a href="#which-herdr-alternatives-are-worth-trying">Which herdr alternatives are worth trying?</a></li><li class="lvl-2"><a href="#when-should-you-stay-on-herdr">When should you stay on herdr?</a></li>+ </ol>+ </aside>++ </div>++ <footer class="post-foot wrap"><div class="prevnext">+ <a class="pn prev" href="/blog/omniagent-alternatives/"><span class="k">← Older</span><span class="t">OmniAgent Alternatives: What to Use Instead of Databricks Omnigent</span></a>+ <a class="pn next" href="/blog/grok-bot-alternatives/"><span class="k">Newer →</span><span class="t">Grok Bot Alternatives: Six Picks, Grouped by What You Want</span></a>+ </div>+ <section class="related">+ <h2>Related in Comparisons</h2>+ <div class="post-grid">+ <article class="card t-comparisons">+ <a class="thumb t-comparisons" href="/blog/grok-bot-alternatives/" aria-hidden="true" tabindex="-1"><img src="/blog/assets/media/grok-bot-alternatives/hero.png" alt="" loading="lazy" decoding="async" /></a>+ <div class="body">+ <div class="meta">+ <time datetime="2026-09-14">Sep 14, 2026</time>+ <span class="dot" aria-hidden="true"></span>+ <span>5 min</span>+ </div>+ <h3><a href="/blog/grok-bot-alternatives/">Grok Bot Alternatives: Six Picks, Grouped by What You Want</a></h3>+ <p class="dek">Grok Bot runs every Bot on one shared cloud computer. Six alternatives checked on 14 Sep 2026, grouped by hosting, privacy and model choice.</p>+ <div class="foot">+ <span class="tag kind">Comparisons</span>+ <a class="more" href="/blog/grok-bot-alternatives/" aria-label="Read: Grok Bot Alternatives: Six Picks, Grouped by What You Want">Read →</a>+ </div>+ </div>+</article>+<article class="card t-comparisons">+ <a class="thumb t-comparisons" href="/blog/omniagent-alternatives/" aria-hidden="true" tabindex="-1"><span class="thumb-ph"><em class="ph-glyph" aria-hidden="true">✶</em><span>COMPARISONS</span></span></a>+ <div class="body">+ <div class="meta">+ <time datetime="2026-09-14">Sep 14, 2026</time>+ <span class="dot" aria-hidden="true"></span>+ <span>5 min</span>+ </div>+ <h3><a href="/blog/omniagent-alternatives/">OmniAgent Alternatives: What to Use Instead of Databricks Omnigent</a></h3>+ <p class="dek">OmniAgent is really Omnigent, the open source meta harness from Databricks. Alternatives checked on 14 Sep 2026, and who each one fits.</p>+ <div class="foot">+ <span class="tag kind">Comparisons</span>+ <a class="more" href="/blog/omniagent-alternatives/" aria-label="Read: OmniAgent Alternatives: What to Use Instead of Databricks Omnigent">Read →</a>+ </div>+ </div>+</article>+<article class="card t-comparisons">+ <a class="thumb t-comparisons" href="/blog/codex-cli-vs-claude-code/" aria-hidden="true" tabindex="-1"><img src="/blog/assets/media/codex-cli-vs-claude-code/hero.png" alt="" loading="lazy" decoding="async" /></a>+ <div class="body">+ <div class="meta">+ <time datetime="2026-09-10">Sep 10, 2026</time>+ <span class="dot" aria-hidden="true"></span>+ <span>5 min</span>+ </div>+ <h3><a href="/blog/codex-cli-vs-claude-code/">Codex CLI vs Claude Code</a></h3>+ <p class="dek">Codex CLI and Claude Code compared firsthand: sandbox and approval flags, AGENTS.md vs CLAUDE.md, real pricing, and where each terminal agent wins.</p>+ <div class="foot">+ <span class="tag kind">Comparisons</span>+ <a class="more" href="/blog/codex-cli-vs-claude-code/" aria-label="Read: Codex CLI vs Claude Code">Read →</a>+ </div>+ </div>+</article>++ </div>+ </section>++ </footer>+</article>++</main>+<footer class="site-foot">+ <div class="wrap">+ <div class="foot-top">+ <a class="foot-brand brand" href="https://munderdiffl.in" aria-label="Munder Difflin home">+ <img class="brand-logo" src="https://munderdiffl.in/logo.png" width="1318" height="840" alt="Munder Difflin, Inc. — Multi-Agent Harness" />+ </a>+ <div class="foot-links">+ <a href="/blog/">Latest</a>+ <a href="/blog/topics/">Topics</a>+ <a href="/blog/about/">About</a>+ <a href="https://munderdiffl.in/blog/feed.xml">RSS</a>+ <a href="https://github.com/chaitanyagiri/munder-difflin">GitHub</a>+ <a href="https://munderdiffl.in">munderdiffl.in ↗</a>+ </div>+ </div>+ <div class="foot-meta">+ © 2026 Munder Difflin · Local-first · MIT-licensed ·+ Built on <a href="https://munderdiffl.in">Electron, React, Pixi.js, xterm.js & node-pty</a>.+ Run an office of agents while you sleep.+ </div>+ </div>+</footer>++<script>+ // sticky-nav border on scroll+ (function () {+ var nav = document.getElementById('nav');+ if (!nav) return;+ var onScroll = function () { nav.classList.toggle('scrolled', window.scrollY > 8); };+ onScroll(); window.addEventListener('scroll', onScroll, { passive: true });+ })();+ // YouTube click-to-load: thumbnail button → youtube-nocookie iframe+ (function () {+ document.addEventListener('click', function (e) {+ var btn = e.target.closest('.yt-load');+ if (!btn) return;+ var box = btn.closest('.yt');+ var id = box && box.getAttribute('data-yt');+ if (!id) return;+ var frame = document.createElement('iframe');+ frame.src = 'https://www.youtube-nocookie.com/embed/' + id + '?autoplay=1';+ frame.title = box.getAttribute('data-title') || 'YouTube video';+ frame.allow = 'accelerometer; autoplay; clipboard-write; encrypted-media; gyroscope; picture-in-picture; web-share';+ frame.setAttribute('allowfullscreen', '');+ box.replaceChildren(frame);+ });+ })();+</script>++</body>+</html>diff --git a/docs/blog/how-ai-answer-engines-choose-sources/index.html b/docs/blog/how-ai-answer-engines-choose-sources/index.htmlindex f06826dd..886604b0 100644--- a/docs/blog/how-ai-answer-engines-choose-sources/index.html+++ b/docs/blog/how-ai-answer-engines-choose-sources/index.html@@ -303,50 +303,50 @@ broader map of the tooling AI engines cite, see our<h2>Related in Comparisons</h2><div class="post-grid"><article class="card t-comparisons">- <a class="thumb t-comparisons" href="/blog/codex-cli-vs-claude-code/" aria-hidden="true" tabindex="-1"><img src="/blog/assets/media/codex-cli-vs-claude-code/hero.png" alt="" loading="lazy" decoding="async" /></a>+ <a class="thumb t-comparisons" href="/blog/grok-bot-alternatives/" aria-hidden="true" tabindex="-1"><img src="/blog/assets/media/grok-bot-alternatives/hero.png" alt="" loading="lazy" decoding="async" /></a><div class="body"><div class="meta">- <time datetime="2026-09-10">Sep 10, 2026</time>+ <time datetime="2026-09-14">Sep 14, 2026</time><span class="dot" aria-hidden="true"></span><span>5 min</span></div>- <h3><a href="/blog/codex-cli-vs-claude-code/">Codex CLI vs Claude Code</a></h3>- <p class="dek">Codex CLI and Claude Code compared firsthand: sandbox and approval flags, AGENTS.md vs CLAUDE.md, real pricing, and where each terminal agent wins.</p>+ <h3><a href="/blog/grok-bot-alternatives/">Grok Bot Alternatives: Six Picks, Grouped by What You Want</a></h3>+ <p class="dek">Grok Bot runs every Bot on one shared cloud computer. Six alternatives checked on 14 Sep 2026, grouped by hosting, privacy and model choice.</p><div class="foot"><span class="tag kind">Comparisons</span>- <a class="more" href="/blog/codex-cli-vs-claude-code/" aria-label="Read: Codex CLI vs Claude Code">Read →</a>+ <a class="more" href="/blog/grok-bot-alternatives/" aria-label="Read: Grok Bot Alternatives: Six Picks, Grouped by What You Want">Read →</a></div></div></article><article class="card t-comparisons">- <a class="thumb t-comparisons" href="/blog/qm-vs-munder-difflin/" aria-hidden="true" tabindex="-1"><img src="/blog/assets/media/qm-vs-munder-difflin/hero.png" alt="" loading="lazy" decoding="async" /></a>+ <a class="thumb t-comparisons" href="/blog/herdr-alternatives/" aria-hidden="true" tabindex="-1"><img src="/blog/assets/media/herdr-alternatives/hero.png" alt="" loading="lazy" decoding="async" /></a><div class="body"><div class="meta">- <time datetime="2026-08-06">Aug 6, 2026</time>+ <time datetime="2026-09-14">Sep 14, 2026</time><span class="dot" aria-hidden="true"></span>- <span>4 min</span>+ <span>5 min</span></div>- <h3><a href="/blog/qm-vs-munder-difflin/">qm vs Munder Difflin: YC's Multiplayer Harness or an Office of Your Clones?</a></h3>- <p class="dek">An honest September 2026 comparison of YC's qm and Munder Difflin. qm is a multiplayer agent harness a company deploys for Slack and the web. Munder Difflin runs an office of your clones on your own machine, with Teams to connect them.</p>+ <h3><a href="/blog/herdr-alternatives/">Herdr Alternatives: What to Pick and Who Each One Fits</a></h3>+ <p class="dek">Herdr alternatives checked on 14 Sep 2026: tmux, Claude Squad, cmux, Orca, Conductor, Superset, Emdash and Munder Difflin, and who each fits.</p><div class="foot"><span class="tag kind">Comparisons</span>- <a class="more" href="/blog/qm-vs-munder-difflin/" aria-label="Read: qm vs Munder Difflin: YC's Multiplayer Harness or an Office of Your Clones?">Read →</a>+ <a class="more" href="/blog/herdr-alternatives/" aria-label="Read: Herdr Alternatives: What to Pick and Who Each One Fits">Read →</a></div></div></article><article class="card t-comparisons">- <a class="thumb t-comparisons" href="/blog/crewai-autogen-vs-a-local-agent-harness/" aria-hidden="true" tabindex="-1"><img src="/blog/assets/media/crewai-autogen-vs-a-local-agent-harness/hero.png" alt="" loading="lazy" decoding="async" /></a>+ <a class="thumb t-comparisons" href="/blog/omniagent-alternatives/" aria-hidden="true" tabindex="-1"><span class="thumb-ph"><em class="ph-glyph" aria-hidden="true">✶</em><span>COMPARISONS</span></span></a><div class="body"><div class="meta">- <time datetime="2026-07-03">Jul 3, 2026</time>+ <time datetime="2026-09-14">Sep 14, 2026</time><span class="dot" aria-hidden="true"></span><span>5 min</span></div>- <h3><a href="/blog/crewai-autogen-vs-a-local-agent-harness/">CrewAI and AutoGen vs a Local Agent Harness: Framework or App?</a></h3>- <p class="dek">CrewAI, AutoGen (now Microsoft Agent Framework), and LangGraph are frameworks — Python you write to build your own agent system. A multi-agent harness is an app you download that runs a team on your repos today. Here's how to tell which one you actually need.</p>+ <h3><a href="/blog/omniagent-alternatives/">OmniAgent Alternatives: What to Use Instead of Databricks Omnigent</a></h3>+ <p class="dek">OmniAgent is really Omnigent, the open source meta harness from Databricks. Alternatives checked on 14 Sep 2026, and who each one fits.</p><div class="foot"><span class="tag kind">Comparisons</span>- <a class="more" href="/blog/crewai-autogen-vs-a-local-agent-harness/" aria-label="Read: CrewAI and AutoGen vs a Local Agent Harness: Framework or App?">Read →</a>+ <a class="more" href="/blog/omniagent-alternatives/" aria-label="Read: OmniAgent Alternatives: What to Use Instead of Databricks Omnigent">Read →</a></div></div></article>diff --git a/docs/blog/how-much-does-claude-code-cost/index.html b/docs/blog/how-much-does-claude-code-cost/index.htmlindex ca6c6fbc..809b5458 100644--- a/docs/blog/how-much-does-claude-code-cost/index.html+++ b/docs/blog/how-much-does-claude-code-cost/index.html@@ -174,7 +174,7 @@<h2 id="is-claude-code-free-to-use" tabindex="-1">Is Claude Code free to use? <a class="anchor" href="#is-claude-code-free-to-use" aria-hidden="true">#</a></h2><p>No. Anthropic’s free Claude plan covers chat, web search, memory, file creation, code execution and a few other surfaces, but Claude Code does not appear on that list; it starts on Claude Pro (<a href="http://claude.com/pricing">claude.com/pricing</a>, checked 10 Sep 2026). The other route in skips the subscription entirely: connect an Anthropic API key and Claude Code bills per token instead.</p><h2 id="how-much-does-claude-code-cost-with-a-claude-subscription" tabindex="-1">How much does Claude Code cost with a Claude subscription? <a class="anchor" href="#how-much-does-claude-code-cost-with-a-claude-subscription" aria-hidden="true">#</a></h2>-<p>Claude Pro is $20 a month billed monthly, or $17 a month on the annual plan billed up front, and Claude Code comes included at no extra charge (Anthropic, <a href="http://claude.com/pricing">claude.com/pricing</a>, checked 10 Sep 2026). Claude Max sits above it at $100 a month for a five times usage tier and $200 a month for a twenty times tier, with both figures set against Pro’s own usage, and both plans meter Claude Code and Claude chat together rather than as two separate allowances (<a href="https://support.claude.com/en/articles/11145838-use-claude-code-with-your-pro-or-max-plan">support.claude.com</a>, checked 10 Sep 2026).</p>+<p>Claude Pro is $20 a month billed monthly, or $17 a month on the annual plan billed up front, and Claude Code comes included at no extra charge (Anthropic, <a href="http://claude.com/pricing">claude.com/pricing</a>, checked 10 Sep 2026). Claude Max sits above it at $100 a month for a five times usage tier and $200 a month for a twenty times tier, with both figures set against Pro’s own usage, and both plans meter Claude Code and Claude chat together rather than as two separate allowances (<a href="https://support.claude.com/en/articles/11145838-use-claude-code-with-your-pro-or-max-plan">support.claude.com</a>, checked 10 Sep 2026). Already on Max? Our guide on <a href="/blog/claude-code-max-plan-tips/">how to get the most out of your Claude Code Max plan</a> covers stretching that allowance.</p><figure class="fig fig-inline"><img src="/blog/assets/media/how-much-does-claude-code-cost/note-1.png" alt="Hand-drawn sketch from “How Much Does Claude Code Cost?”" loading="lazy" decoding="async" /></figure><h2 id="whats-the-difference-between-claude-pro-and-claude-max-for-claude-code" tabindex="-1">What’s the difference between Claude Pro and Claude Max for Claude Code? <a class="anchor" href="#whats-the-difference-between-claude-pro-and-claude-max-for-claude-code" aria-hidden="true">#</a></h2><p>Mostly how much you can burn through before you wait. Anthropic states usage on a rolling five hour window plus a weekly cap shared across models, and Max simply multiplies that ceiling by five or twenty depending on which tier you pick (<a href="https://support.claude.com/en/articles/11049741-what-is-the-max-plan">support.claude.com</a>, checked 10 Sep 2026). What neither official page states is an exact number of Claude Code prompts per window; specific figures like “10 to 40 prompts” that circulate on comparison blogs are not on Anthropic’s own pages as checked for this post, so treat them as someone’s estimate rather than a published limit.</p>diff --git a/docs/blog/how-to-add-a-github-copilot-cli-agent/index.html b/docs/blog/how-to-add-a-github-copilot-cli-agent/index.htmlindex a1ddf68a..309a6a2f 100644--- a/docs/blog/how-to-add-a-github-copilot-cli-agent/index.html+++ b/docs/blog/how-to-add-a-github-copilot-cli-agent/index.html@@ -283,50 +283,50 @@<h2>Related in Guides</h2><div class="post-grid"><article class="card t-guides">- <a class="thumb t-guides" href="/blog/how-to-use-claude-code-plan-mode/" aria-hidden="true" tabindex="-1"><img src="/blog/assets/media/how-to-use-claude-code-plan-mode/hero.png" alt="" loading="lazy" decoding="async" /></a>+ <a class="thumb t-guides" href="/blog/claude-code-max-plan-tips/" aria-hidden="true" tabindex="-1"><img src="/blog/assets/media/claude-code-max-plan-tips/hero.png" alt="" loading="lazy" decoding="async" /></a><div class="body"><div class="meta">- <time datetime="2026-09-11">Sep 11, 2026</time>+ <time datetime="2026-09-14">Sep 14, 2026</time><span class="dot" aria-hidden="true"></span><span>5 min</span></div>- <h3><a href="/blog/how-to-use-claude-code-plan-mode/">How to Use Claude Code Plan Mode</a></h3>- <p class="dek">How Claude Code's plan mode works: turning it on, what it blocks, what a real headless plan mode run prints, and how to leave it.</p>+ <h3><a href="/blog/claude-code-max-plan-tips/">How to Get the Most Out of Your Claude Code Max Plan</a></h3>+ <p class="dek">Stretch a Claude Code Max plan: model choice, context hygiene, prompt caching, subagents and unattended runs, checked against Anthropic's own pages.</p><div class="foot"><span class="tag kind">Guides</span>- <a class="more" href="/blog/how-to-use-claude-code-plan-mode/" aria-label="Read: How to Use Claude Code Plan Mode">Read →</a>+ <a class="more" href="/blog/claude-code-max-plan-tips/" aria-label="Read: How to Get the Most Out of Your Claude Code Max Plan">Read →</a></div></div></article><article class="card t-guides">- <a class="thumb t-guides" href="/blog/how-to-add-an-mcp-server-to-claude-code/" aria-hidden="true" tabindex="-1"><img src="/blog/assets/media/how-to-add-an-mcp-server-to-claude-code/hero.png" alt="" loading="lazy" decoding="async" /></a>+ <a class="thumb t-guides" href="/blog/codex-max-plan-tips/" aria-hidden="true" tabindex="-1"><img src="/blog/assets/media/codex-max-plan-tips/hero.png" alt="" loading="lazy" decoding="async" /></a><div class="body"><div class="meta">- <time datetime="2026-09-10">Sep 10, 2026</time>+ <time datetime="2026-09-14">Sep 14, 2026</time><span class="dot" aria-hidden="true"></span><span>5 min</span></div>- <h3><a href="/blog/how-to-add-an-mcp-server-to-claude-code/">How to Add an MCP Server to Claude Code</a></h3>- <p class="dek">The claude mcp add command, its scope flag, editing .mcp.json by hand, and how Munder Difflin's Capabilities screen grants an MCP server to one agent at a time.</p>+ <h3><a href="/blog/codex-max-plan-tips/">How to Make the Most of Your Codex Max Plan</a></h3>+ <p class="dek">There is no Codex Max plan. What ChatGPT Pro 5x and 20x give you in Codex, how the weekly limit works, and how to stretch it.</p><div class="foot"><span class="tag kind">Guides</span>- <a class="more" href="/blog/how-to-add-an-mcp-server-to-claude-code/" aria-label="Read: How to Add an MCP Server to Claude Code">Read →</a>+ <a class="more" href="/blog/codex-max-plan-tips/" aria-label="Read: How to Make the Most of Your Codex Max Plan">Read →</a></div></div></article><article class="card t-guides">- <a class="thumb t-guides" href="/blog/command-center-guide/" aria-hidden="true" tabindex="-1"><img src="/blog/assets/media/command-center-guide/hero.png" alt="" loading="lazy" decoding="async" /></a>+ <a class="thumb t-guides" href="/blog/how-to-use-claude-code-plan-mode/" aria-hidden="true" tabindex="-1"><img src="/blog/assets/media/how-to-use-claude-code-plan-mode/hero.png" alt="" loading="lazy" decoding="async" /></a><div class="body"><div class="meta">- <time datetime="2026-07-03">Jul 3, 2026</time>+ <time datetime="2026-09-11">Sep 11, 2026</time><span class="dot" aria-hidden="true"></span>- <span>4 min</span>+ <span>5 min</span></div>- <h3><a href="/blog/command-center-guide/">The Command Center: Kanban, Fleet and Budgets in One Place</a></h3>- <p class="dek">A guide to Munder Difflin's Command Center in 0.5.2: the kanban with task dependencies, the ask me tab, triggers, memory, live token use against each agent's budget, and when to watch the board instead of the floor.</p>+ <h3><a href="/blog/how-to-use-claude-code-plan-mode/">How to Use Claude Code Plan Mode</a></h3>+ <p class="dek">How Claude Code's plan mode works: turning it on, what it blocks, what a real headless plan mode run prints, and how to leave it.</p><div class="foot"><span class="tag kind">Guides</span>- <a class="more" href="/blog/command-center-guide/" aria-label="Read: The Command Center: Kanban, Fleet and Budgets in One Place">Read →</a>+ <a class="more" href="/blog/how-to-use-claude-code-plan-mode/" aria-label="Read: How to Use Claude Code Plan Mode">Read →</a></div></div></article>diff --git a/docs/blog/how-to-add-an-mcp-server-to-claude-code/index.html b/docs/blog/how-to-add-an-mcp-server-to-claude-code/index.htmlindex a9a9566d..3f8b1cfc 100644--- a/docs/blog/how-to-add-an-mcp-server-to-claude-code/index.html+++ b/docs/blog/how-to-add-an-mcp-server-to-claude-code/index.html@@ -291,50 +291,50 @@ terminal. A harness earns its place once several agents are running and only one<h2>Related in Guides</h2><div class="post-grid"><article class="card t-guides">- <a class="thumb t-guides" href="/blog/how-to-use-claude-code-plan-mode/" aria-hidden="true" tabindex="-1"><img src="/blog/assets/media/how-to-use-claude-code-plan-mode/hero.png" alt="" loading="lazy" decoding="async" /></a>+ <a class="thumb t-guides" href="/blog/claude-code-max-plan-tips/" aria-hidden="true" tabindex="-1"><img src="/blog/assets/media/claude-code-max-plan-tips/hero.png" alt="" loading="lazy" decoding="async" /></a><div class="body"><div class="meta">- <time datetime="2026-09-11">Sep 11, 2026</time>+ <time datetime="2026-09-14">Sep 14, 2026</time><span class="dot" aria-hidden="true"></span><span>5 min</span></div>- <h3><a href="/blog/how-to-use-claude-code-plan-mode/">How to Use Claude Code Plan Mode</a></h3>- <p class="dek">How Claude Code's plan mode works: turning it on, what it blocks, what a real headless plan mode run prints, and how to leave it.</p>+ <h3><a href="/blog/claude-code-max-plan-tips/">How to Get the Most Out of Your Claude Code Max Plan</a></h3>+ <p class="dek">Stretch a Claude Code Max plan: model choice, context hygiene, prompt caching, subagents and unattended runs, checked against Anthropic's own pages.</p><div class="foot"><span class="tag kind">Guides</span>- <a class="more" href="/blog/how-to-use-claude-code-plan-mode/" aria-label="Read: How to Use Claude Code Plan Mode">Read →</a>+ <a class="more" href="/blog/claude-code-max-plan-tips/" aria-label="Read: How to Get the Most Out of Your Claude Code Max Plan">Read →</a></div></div></article><article class="card t-guides">- <a class="thumb t-guides" href="/blog/command-center-guide/" aria-hidden="true" tabindex="-1"><img src="/blog/assets/media/command-center-guide/hero.png" alt="" loading="lazy" decoding="async" /></a>+ <a class="thumb t-guides" href="/blog/codex-max-plan-tips/" aria-hidden="true" tabindex="-1"><img src="/blog/assets/media/codex-max-plan-tips/hero.png" alt="" loading="lazy" decoding="async" /></a><div class="body"><div class="meta">- <time datetime="2026-07-03">Jul 3, 2026</time>+ <time datetime="2026-09-14">Sep 14, 2026</time><span class="dot" aria-hidden="true"></span>- <span>4 min</span>+ <span>5 min</span></div>- <h3><a href="/blog/command-center-guide/">The Command Center: Kanban, Fleet and Budgets in One Place</a></h3>- <p class="dek">A guide to Munder Difflin's Command Center in 0.5.2: the kanban with task dependencies, the ask me tab, triggers, memory, live token use against each agent's budget, and when to watch the board instead of the floor.</p>+ <h3><a href="/blog/codex-max-plan-tips/">How to Make the Most of Your Codex Max Plan</a></h3>+ <p class="dek">There is no Codex Max plan. What ChatGPT Pro 5x and 20x give you in Codex, how the weekly limit works, and how to stretch it.</p><div class="foot"><span class="tag kind">Guides</span>- <a class="more" href="/blog/command-center-guide/" aria-label="Read: The Command Center: Kanban, Fleet and Budgets in One Place">Read →</a>+ <a class="more" href="/blog/codex-max-plan-tips/" aria-label="Read: How to Make the Most of Your Codex Max Plan">Read →</a></div></div></article><article class="card t-guides">- <a class="thumb t-guides" href="/blog/how-to-add-a-github-copilot-cli-agent/" aria-hidden="true" tabindex="-1"><img src="/blog/assets/media/how-to-add-a-github-copilot-cli-agent/hero.png" alt="" loading="lazy" decoding="async" /></a>+ <a class="thumb t-guides" href="/blog/how-to-use-claude-code-plan-mode/" aria-hidden="true" tabindex="-1"><img src="/blog/assets/media/how-to-use-claude-code-plan-mode/hero.png" alt="" loading="lazy" decoding="async" /></a><div class="body"><div class="meta">- <time datetime="2026-07-03">Jul 3, 2026</time>+ <time datetime="2026-09-11">Sep 11, 2026</time><span class="dot" aria-hidden="true"></span>- <span>4 min</span>+ <span>5 min</span></div>- <h3><a href="/blog/how-to-add-a-github-copilot-cli-agent/">How to Add a GitHub Copilot CLI Agent to Your Floor</a></h3>- <p class="dek">A step-by-step v0.3.3 walkthrough: install GitHub Copilot CLI (or let the harness install it for you), hire a Copilot worker, pick a model, and know exactly what print mode can and can't do.</p>+ <h3><a href="/blog/how-to-use-claude-code-plan-mode/">How to Use Claude Code Plan Mode</a></h3>+ <p class="dek">How Claude Code's plan mode works: turning it on, what it blocks, what a real headless plan mode run prints, and how to leave it.</p><div class="foot"><span class="tag kind">Guides</span>- <a class="more" href="/blog/how-to-add-a-github-copilot-cli-agent/" aria-label="Read: How to Add a GitHub Copilot CLI Agent to Your Floor">Read →</a>+ <a class="more" href="/blog/how-to-use-claude-code-plan-mode/" aria-label="Read: How to Use Claude Code Plan Mode">Read →</a></div></div></article>diff --git a/docs/blog/how-to-choose-a-multi-agent-tool/index.html b/docs/blog/how-to-choose-a-multi-agent-tool/index.htmlindex 5dd2cb64..1c21e4cb 100644--- a/docs/blog/how-to-choose-a-multi-agent-tool/index.html+++ b/docs/blog/how-to-choose-a-multi-agent-tool/index.html@@ -318,50 +318,50 @@ local-first.</p><h2>Related in Comparisons</h2><div class="post-grid"><article class="card t-comparisons">- <a class="thumb t-comparisons" href="/blog/codex-cli-vs-claude-code/" aria-hidden="true" tabindex="-1"><img src="/blog/assets/media/codex-cli-vs-claude-code/hero.png" alt="" loading="lazy" decoding="async" /></a>+ <a class="thumb t-comparisons" href="/blog/grok-bot-alternatives/" aria-hidden="true" tabindex="-1"><img src="/blog/assets/media/grok-bot-alternatives/hero.png" alt="" loading="lazy" decoding="async" /></a><div class="body"><div class="meta">- <time datetime="2026-09-10">Sep 10, 2026</time>+ <time datetime="2026-09-14">Sep 14, 2026</time><span class="dot" aria-hidden="true"></span><span>5 min</span></div>- <h3><a href="/blog/codex-cli-vs-claude-code/">Codex CLI vs Claude Code</a></h3>- <p class="dek">Codex CLI and Claude Code compared firsthand: sandbox and approval flags, AGENTS.md vs CLAUDE.md, real pricing, and where each terminal agent wins.</p>+ <h3><a href="/blog/grok-bot-alternatives/">Grok Bot Alternatives: Six Picks, Grouped by What You Want</a></h3>+ <p class="dek">Grok Bot runs every Bot on one shared cloud computer. Six alternatives checked on 14 Sep 2026, grouped by hosting, privacy and model choice.</p><div class="foot"><span class="tag kind">Comparisons</span>- <a class="more" href="/blog/codex-cli-vs-claude-code/" aria-label="Read: Codex CLI vs Claude Code">Read →</a>+ <a class="more" href="/blog/grok-bot-alternatives/" aria-label="Read: Grok Bot Alternatives: Six Picks, Grouped by What You Want">Read →</a></div></div></article><article class="card t-comparisons">- <a class="thumb t-comparisons" href="/blog/qm-vs-munder-difflin/" aria-hidden="true" tabindex="-1"><img src="/blog/assets/media/qm-vs-munder-difflin/hero.png" alt="" loading="lazy" decoding="async" /></a>+ <a class="thumb t-comparisons" href="/blog/herdr-alternatives/" aria-hidden="true" tabindex="-1"><img src="/blog/assets/media/herdr-alternatives/hero.png" alt="" loading="lazy" decoding="async" /></a><div class="body"><div class="meta">- <time datetime="2026-08-06">Aug 6, 2026</time>+ <time datetime="2026-09-14">Sep 14, 2026</time><span class="dot" aria-hidden="true"></span>- <span>4 min</span>+ <span>5 min</span></div>- <h3><a href="/blog/qm-vs-munder-difflin/">qm vs Munder Difflin: YC's Multiplayer Harness or an Office of Your Clones?</a></h3>- <p class="dek">An honest September 2026 comparison of YC's qm and Munder Difflin. qm is a multiplayer agent harness a company deploys for Slack and the web. Munder Difflin runs an office of your clones on your own machine, with Teams to connect them.</p>+ <h3><a href="/blog/herdr-alternatives/">Herdr Alternatives: What to Pick and Who Each One Fits</a></h3>+ <p class="dek">Herdr alternatives checked on 14 Sep 2026: tmux, Claude Squad, cmux, Orca, Conductor, Superset, Emdash and Munder Difflin, and who each fits.</p><div class="foot"><span class="tag kind">Comparisons</span>- <a class="more" href="/blog/qm-vs-munder-difflin/" aria-label="Read: qm vs Munder Difflin: YC's Multiplayer Harness or an Office of Your Clones?">Read →</a>+ <a class="more" href="/blog/herdr-alternatives/" aria-label="Read: Herdr Alternatives: What to Pick and Who Each One Fits">Read →</a></div></div></article><article class="card t-comparisons">- <a class="thumb t-comparisons" href="/blog/crewai-autogen-vs-a-local-agent-harness/" aria-hidden="true" tabindex="-1"><img src="/blog/assets/media/crewai-autogen-vs-a-local-agent-harness/hero.png" alt="" loading="lazy" decoding="async" /></a>+ <a class="thumb t-comparisons" href="/blog/omniagent-alternatives/" aria-hidden="true" tabindex="-1"><span class="thumb-ph"><em class="ph-glyph" aria-hidden="true">✶</em><span>COMPARISONS</span></span></a><div class="body"><div class="meta">- <time datetime="2026-07-03">Jul 3, 2026</time>+ <time datetime="2026-09-14">Sep 14, 2026</time><span class="dot" aria-hidden="true"></span><span>5 min</span></div>- <h3><a href="/blog/crewai-autogen-vs-a-local-agent-harness/">CrewAI and AutoGen vs a Local Agent Harness: Framework or App?</a></h3>- <p class="dek">CrewAI, AutoGen (now Microsoft Agent Framework), and LangGraph are frameworks — Python you write to build your own agent system. A multi-agent harness is an app you download that runs a team on your repos today. Here's how to tell which one you actually need.</p>+ <h3><a href="/blog/omniagent-alternatives/">OmniAgent Alternatives: What to Use Instead of Databricks Omnigent</a></h3>+ <p class="dek">OmniAgent is really Omnigent, the open source meta harness from Databricks. Alternatives checked on 14 Sep 2026, and who each one fits.</p><div class="foot"><span class="tag kind">Comparisons</span>- <a class="more" href="/blog/crewai-autogen-vs-a-local-agent-harness/" aria-label="Read: CrewAI and AutoGen vs a Local Agent Harness: Framework or App?">Read →</a>+ <a class="more" href="/blog/omniagent-alternatives/" aria-label="Read: OmniAgent Alternatives: What to Use Instead of Databricks Omnigent">Read →</a></div></div></article>diff --git a/docs/blog/how-to-hire-from-the-agent-gallery/index.html b/docs/blog/how-to-hire-from-the-agent-gallery/index.htmlindex 4f80060f..28db2e12 100644--- a/docs/blog/how-to-hire-from-the-agent-gallery/index.html+++ b/docs/blog/how-to-hire-from-the-agent-gallery/index.html@@ -294,50 +294,50 @@ gallery page, then import it with Add agent and import hire. Manifests are plain<h2>Related in Guides</h2><div class="post-grid"><article class="card t-guides">- <a class="thumb t-guides" href="/blog/how-to-use-claude-code-plan-mode/" aria-hidden="true" tabindex="-1"><img src="/blog/assets/media/how-to-use-claude-code-plan-mode/hero.png" alt="" loading="lazy" decoding="async" /></a>+ <a class="thumb t-guides" href="/blog/claude-code-max-plan-tips/" aria-hidden="true" tabindex="-1"><img src="/blog/assets/media/claude-code-max-plan-tips/hero.png" alt="" loading="lazy" decoding="async" /></a><div class="body"><div class="meta">- <time datetime="2026-09-11">Sep 11, 2026</time>+ <time datetime="2026-09-14">Sep 14, 2026</time><span class="dot" aria-hidden="true"></span><span>5 min</span></div>- <h3><a href="/blog/how-to-use-claude-code-plan-mode/">How to Use Claude Code Plan Mode</a></h3>- <p class="dek">How Claude Code's plan mode works: turning it on, what it blocks, what a real headless plan mode run prints, and how to leave it.</p>+ <h3><a href="/blog/claude-code-max-plan-tips/">How to Get the Most Out of Your Claude Code Max Plan</a></h3>+ <p class="dek">Stretch a Claude Code Max plan: model choice, context hygiene, prompt caching, subagents and unattended runs, checked against Anthropic's own pages.</p><div class="foot"><span class="tag kind">Guides</span>- <a class="more" href="/blog/how-to-use-claude-code-plan-mode/" aria-label="Read: How to Use Claude Code Plan Mode">Read →</a>+ <a class="more" href="/blog/claude-code-max-plan-tips/" aria-label="Read: How to Get the Most Out of Your Claude Code Max Plan">Read →</a></div></div></article><article class="card t-guides">- <a class="thumb t-guides" href="/blog/how-to-add-an-mcp-server-to-claude-code/" aria-hidden="true" tabindex="-1"><img src="/blog/assets/media/how-to-add-an-mcp-server-to-claude-code/hero.png" alt="" loading="lazy" decoding="async" /></a>+ <a class="thumb t-guides" href="/blog/codex-max-plan-tips/" aria-hidden="true" tabindex="-1"><img src="/blog/assets/media/codex-max-plan-tips/hero.png" alt="" loading="lazy" decoding="async" /></a><div class="body"><div class="meta">- <time datetime="2026-09-10">Sep 10, 2026</time>+ <time datetime="2026-09-14">Sep 14, 2026</time><span class="dot" aria-hidden="true"></span><span>5 min</span></div>- <h3><a href="/blog/how-to-add-an-mcp-server-to-claude-code/">How to Add an MCP Server to Claude Code</a></h3>- <p class="dek">The claude mcp add command, its scope flag, editing .mcp.json by hand, and how Munder Difflin's Capabilities screen grants an MCP server to one agent at a time.</p>+ <h3><a href="/blog/codex-max-plan-tips/">How to Make the Most of Your Codex Max Plan</a></h3>+ <p class="dek">There is no Codex Max plan. What ChatGPT Pro 5x and 20x give you in Codex, how the weekly limit works, and how to stretch it.</p><div class="foot"><span class="tag kind">Guides</span>- <a class="more" href="/blog/how-to-add-an-mcp-server-to-claude-code/" aria-label="Read: How to Add an MCP Server to Claude Code">Read →</a>+ <a class="more" href="/blog/codex-max-plan-tips/" aria-label="Read: How to Make the Most of Your Codex Max Plan">Read →</a></div></div></article><article class="card t-guides">- <a class="thumb t-guides" href="/blog/command-center-guide/" aria-hidden="true" tabindex="-1"><img src="/blog/assets/media/command-center-guide/hero.png" alt="" loading="lazy" decoding="async" /></a>+ <a class="thumb t-guides" href="/blog/how-to-use-claude-code-plan-mode/" aria-hidden="true" tabindex="-1"><img src="/blog/assets/media/how-to-use-claude-code-plan-mode/hero.png" alt="" loading="lazy" decoding="async" /></a><div class="body"><div class="meta">- <time datetime="2026-07-03">Jul 3, 2026</time>+ <time datetime="2026-09-11">Sep 11, 2026</time><span class="dot" aria-hidden="true"></span>- <span>4 min</span>+ <span>5 min</span></div>- <h3><a href="/blog/command-center-guide/">The Command Center: Kanban, Fleet and Budgets in One Place</a></h3>- <p class="dek">A guide to Munder Difflin's Command Center in 0.5.2: the kanban with task dependencies, the ask me tab, triggers, memory, live token use against each agent's budget, and when to watch the board instead of the floor.</p>+ <h3><a href="/blog/how-to-use-claude-code-plan-mode/">How to Use Claude Code Plan Mode</a></h3>+ <p class="dek">How Claude Code's plan mode works: turning it on, what it blocks, what a real headless plan mode run prints, and how to leave it.</p><div class="foot"><span class="tag kind">Guides</span>- <a class="more" href="/blog/command-center-guide/" aria-label="Read: The Command Center: Kanban, Fleet and Budgets in One Place">Read →</a>+ <a class="more" href="/blog/how-to-use-claude-code-plan-mode/" aria-label="Read: How to Use Claude Code Plan Mode">Read →</a></div></div></article>diff --git a/docs/blog/how-to-install-and-use-munder-difflin/index.html b/docs/blog/how-to-install-and-use-munder-difflin/index.htmlindex b0fb2177..05287e29 100644--- a/docs/blog/how-to-install-and-use-munder-difflin/index.html+++ b/docs/blog/how-to-install-and-use-munder-difflin/index.html@@ -624,50 +624,50 @@ stuck, the <a href="https://munderdiffl.in">Discord</a> is the fastest place to<h2>Related in Guides</h2><div class="post-grid"><article class="card t-guides">- <a class="thumb t-guides" href="/blog/how-to-use-claude-code-plan-mode/" aria-hidden="true" tabindex="-1"><img src="/blog/assets/media/how-to-use-claude-code-plan-mode/hero.png" alt="" loading="lazy" decoding="async" /></a>+ <a class="thumb t-guides" href="/blog/claude-code-max-plan-tips/" aria-hidden="true" tabindex="-1"><img src="/blog/assets/media/claude-code-max-plan-tips/hero.png" alt="" loading="lazy" decoding="async" /></a><div class="body"><div class="meta">- <time datetime="2026-09-11">Sep 11, 2026</time>+ <time datetime="2026-09-14">Sep 14, 2026</time><span class="dot" aria-hidden="true"></span><span>5 min</span></div>- <h3><a href="/blog/how-to-use-claude-code-plan-mode/">How to Use Claude Code Plan Mode</a></h3>- <p class="dek">How Claude Code's plan mode works: turning it on, what it blocks, what a real headless plan mode run prints, and how to leave it.</p>+ <h3><a href="/blog/claude-code-max-plan-tips/">How to Get the Most Out of Your Claude Code Max Plan</a></h3>+ <p class="dek">Stretch a Claude Code Max plan: model choice, context hygiene, prompt caching, subagents and unattended runs, checked against Anthropic's own pages.</p><div class="foot"><span class="tag kind">Guides</span>- <a class="more" href="/blog/how-to-use-claude-code-plan-mode/" aria-label="Read: How to Use Claude Code Plan Mode">Read →</a>+ <a class="more" href="/blog/claude-code-max-plan-tips/" aria-label="Read: How to Get the Most Out of Your Claude Code Max Plan">Read →</a></div></div></article><article class="card t-guides">- <a class="thumb t-guides" href="/blog/how-to-add-an-mcp-server-to-claude-code/" aria-hidden="true" tabindex="-1"><img src="/blog/assets/media/how-to-add-an-mcp-server-to-claude-code/hero.png" alt="" loading="lazy" decoding="async" /></a>+ <a class="thumb t-guides" href="/blog/codex-max-plan-tips/" aria-hidden="true" tabindex="-1"><img src="/blog/assets/media/codex-max-plan-tips/hero.png" alt="" loading="lazy" decoding="async" /></a><div class="body"><div class="meta">- <time datetime="2026-09-10">Sep 10, 2026</time>+ <time datetime="2026-09-14">Sep 14, 2026</time><span class="dot" aria-hidden="true"></span><span>5 min</span></div>- <h3><a href="/blog/how-to-add-an-mcp-server-to-claude-code/">How to Add an MCP Server to Claude Code</a></h3>- <p class="dek">The claude mcp add command, its scope flag, editing .mcp.json by hand, and how Munder Difflin's Capabilities screen grants an MCP server to one agent at a time.</p>+ <h3><a href="/blog/codex-max-plan-tips/">How to Make the Most of Your Codex Max Plan</a></h3>+ <p class="dek">There is no Codex Max plan. What ChatGPT Pro 5x and 20x give you in Codex, how the weekly limit works, and how to stretch it.</p><div class="foot"><span class="tag kind">Guides</span>- <a class="more" href="/blog/how-to-add-an-mcp-server-to-claude-code/" aria-label="Read: How to Add an MCP Server to Claude Code">Read →</a>+ <a class="more" href="/blog/codex-max-plan-tips/" aria-label="Read: How to Make the Most of Your Codex Max Plan">Read →</a></div></div></article><article class="card t-guides">- <a class="thumb t-guides" href="/blog/command-center-guide/" aria-hidden="true" tabindex="-1"><img src="/blog/assets/media/command-center-guide/hero.png" alt="" loading="lazy" decoding="async" /></a>+ <a class="thumb t-guides" href="/blog/how-to-use-claude-code-plan-mode/" aria-hidden="true" tabindex="-1"><img src="/blog/assets/media/how-to-use-claude-code-plan-mode/hero.png" alt="" loading="lazy" decoding="async" /></a><div class="body"><div class="meta">- <time datetime="2026-07-03">Jul 3, 2026</time>+ <time datetime="2026-09-11">Sep 11, 2026</time><span class="dot" aria-hidden="true"></span>- <span>4 min</span>+ <span>5 min</span></div>- <h3><a href="/blog/command-center-guide/">The Command Center: Kanban, Fleet and Budgets in One Place</a></h3>- <p class="dek">A guide to Munder Difflin's Command Center in 0.5.2: the kanban with task dependencies, the ask me tab, triggers, memory, live token use against each agent's budget, and when to watch the board instead of the floor.</p>+ <h3><a href="/blog/how-to-use-claude-code-plan-mode/">How to Use Claude Code Plan Mode</a></h3>+ <p class="dek">How Claude Code's plan mode works: turning it on, what it blocks, what a real headless plan mode run prints, and how to leave it.</p><div class="foot"><span class="tag kind">Guides</span>- <a class="more" href="/blog/command-center-guide/" aria-label="Read: The Command Center: Kanban, Fleet and Budgets in One Place">Read →</a>+ <a class="more" href="/blog/how-to-use-claude-code-plan-mode/" aria-label="Read: How to Use Claude Code Plan Mode">Read →</a></div></div></article>diff --git a/docs/blog/how-to-run-multiple-claude-code-agents/index.html b/docs/blog/how-to-run-multiple-claude-code-agents/index.htmlindex de45f9eb..99c4edd9 100644--- a/docs/blog/how-to-run-multiple-claude-code-agents/index.html+++ b/docs/blog/how-to-run-multiple-claude-code-agents/index.html@@ -251,50 +251,50 @@ free and open source.</p><h2>Related in Guides</h2><div class="post-grid"><article class="card t-guides">- <a class="thumb t-guides" href="/blog/how-to-use-claude-code-plan-mode/" aria-hidden="true" tabindex="-1"><img src="/blog/assets/media/how-to-use-claude-code-plan-mode/hero.png" alt="" loading="lazy" decoding="async" /></a>+ <a class="thumb t-guides" href="/blog/claude-code-max-plan-tips/" aria-hidden="true" tabindex="-1"><img src="/blog/assets/media/claude-code-max-plan-tips/hero.png" alt="" loading="lazy" decoding="async" /></a><div class="body"><div class="meta">- <time datetime="2026-09-11">Sep 11, 2026</time>+ <time datetime="2026-09-14">Sep 14, 2026</time><span class="dot" aria-hidden="true"></span><span>5 min</span></div>- <h3><a href="/blog/how-to-use-claude-code-plan-mode/">How to Use Claude Code Plan Mode</a></h3>- <p class="dek">How Claude Code's plan mode works: turning it on, what it blocks, what a real headless plan mode run prints, and how to leave it.</p>+ <h3><a href="/blog/claude-code-max-plan-tips/">How to Get the Most Out of Your Claude Code Max Plan</a></h3>+ <p class="dek">Stretch a Claude Code Max plan: model choice, context hygiene, prompt caching, subagents and unattended runs, checked against Anthropic's own pages.</p><div class="foot"><span class="tag kind">Guides</span>- <a class="more" href="/blog/how-to-use-claude-code-plan-mode/" aria-label="Read: How to Use Claude Code Plan Mode">Read →</a>+ <a class="more" href="/blog/claude-code-max-plan-tips/" aria-label="Read: How to Get the Most Out of Your Claude Code Max Plan">Read →</a></div></div></article><article class="card t-guides">- <a class="thumb t-guides" href="/blog/how-to-add-an-mcp-server-to-claude-code/" aria-hidden="true" tabindex="-1"><img src="/blog/assets/media/how-to-add-an-mcp-server-to-claude-code/hero.png" alt="" loading="lazy" decoding="async" /></a>+ <a class="thumb t-guides" href="/blog/codex-max-plan-tips/" aria-hidden="true" tabindex="-1"><img src="/blog/assets/media/codex-max-plan-tips/hero.png" alt="" loading="lazy" decoding="async" /></a><div class="body"><div class="meta">- <time datetime="2026-09-10">Sep 10, 2026</time>+ <time datetime="2026-09-14">Sep 14, 2026</time><span class="dot" aria-hidden="true"></span><span>5 min</span></div>- <h3><a href="/blog/how-to-add-an-mcp-server-to-claude-code/">How to Add an MCP Server to Claude Code</a></h3>- <p class="dek">The claude mcp add command, its scope flag, editing .mcp.json by hand, and how Munder Difflin's Capabilities screen grants an MCP server to one agent at a time.</p>+ <h3><a href="/blog/codex-max-plan-tips/">How to Make the Most of Your Codex Max Plan</a></h3>+ <p class="dek">There is no Codex Max plan. What ChatGPT Pro 5x and 20x give you in Codex, how the weekly limit works, and how to stretch it.</p><div class="foot"><span class="tag kind">Guides</span>- <a class="more" href="/blog/how-to-add-an-mcp-server-to-claude-code/" aria-label="Read: How to Add an MCP Server to Claude Code">Read →</a>+ <a class="more" href="/blog/codex-max-plan-tips/" aria-label="Read: How to Make the Most of Your Codex Max Plan">Read →</a></div></div></article><article class="card t-guides">- <a class="thumb t-guides" href="/blog/command-center-guide/" aria-hidden="true" tabindex="-1"><img src="/blog/assets/media/command-center-guide/hero.png" alt="" loading="lazy" decoding="async" /></a>+ <a class="thumb t-guides" href="/blog/how-to-use-claude-code-plan-mode/" aria-hidden="true" tabindex="-1"><img src="/blog/assets/media/how-to-use-claude-code-plan-mode/hero.png" alt="" loading="lazy" decoding="async" /></a><div class="body"><div class="meta">- <time datetime="2026-07-03">Jul 3, 2026</time>+ <time datetime="2026-09-11">Sep 11, 2026</time><span class="dot" aria-hidden="true"></span>- <span>4 min</span>+ <span>5 min</span></div>- <h3><a href="/blog/command-center-guide/">The Command Center: Kanban, Fleet and Budgets in One Place</a></h3>- <p class="dek">A guide to Munder Difflin's Command Center in 0.5.2: the kanban with task dependencies, the ask me tab, triggers, memory, live token use against each agent's budget, and when to watch the board instead of the floor.</p>+ <h3><a href="/blog/how-to-use-claude-code-plan-mode/">How to Use Claude Code Plan Mode</a></h3>+ <p class="dek">How Claude Code's plan mode works: turning it on, what it blocks, what a real headless plan mode run prints, and how to leave it.</p><div class="foot"><span class="tag kind">Guides</span>- <a class="more" href="/blog/command-center-guide/" aria-label="Read: The Command Center: Kanban, Fleet and Budgets in One Place">Read →</a>+ <a class="more" href="/blog/how-to-use-claude-code-plan-mode/" aria-label="Read: How to Use Claude Code Plan Mode">Read →</a></div></div></article>diff --git a/docs/blog/how-to-talk-to-your-orchestrator/index.html b/docs/blog/how-to-talk-to-your-orchestrator/index.htmlindex c49eb058..a8373d9b 100644--- a/docs/blog/how-to-talk-to-your-orchestrator/index.html+++ b/docs/blog/how-to-talk-to-your-orchestrator/index.html@@ -274,50 +274,50 @@ Three goals in a trench coat. Split them — the task board handles dependencies<h2>Related in Guides</h2><div class="post-grid"><article class="card t-guides">- <a class="thumb t-guides" href="/blog/how-to-use-claude-code-plan-mode/" aria-hidden="true" tabindex="-1"><img src="/blog/assets/media/how-to-use-claude-code-plan-mode/hero.png" alt="" loading="lazy" decoding="async" /></a>+ <a class="thumb t-guides" href="/blog/claude-code-max-plan-tips/" aria-hidden="true" tabindex="-1"><img src="/blog/assets/media/claude-code-max-plan-tips/hero.png" alt="" loading="lazy" decoding="async" /></a><div class="body"><div class="meta">- <time datetime="2026-09-11">Sep 11, 2026</time>+ <time datetime="2026-09-14">Sep 14, 2026</time><span class="dot" aria-hidden="true"></span><span>5 min</span></div>- <h3><a href="/blog/how-to-use-claude-code-plan-mode/">How to Use Claude Code Plan Mode</a></h3>- <p class="dek">How Claude Code's plan mode works: turning it on, what it blocks, what a real headless plan mode run prints, and how to leave it.</p>+ <h3><a href="/blog/claude-code-max-plan-tips/">How to Get the Most Out of Your Claude Code Max Plan</a></h3>+ <p class="dek">Stretch a Claude Code Max plan: model choice, context hygiene, prompt caching, subagents and unattended runs, checked against Anthropic's own pages.</p><div class="foot"><span class="tag kind">Guides</span>- <a class="more" href="/blog/how-to-use-claude-code-plan-mode/" aria-label="Read: How to Use Claude Code Plan Mode">Read →</a>+ <a class="more" href="/blog/claude-code-max-plan-tips/" aria-label="Read: How to Get the Most Out of Your Claude Code Max Plan">Read →</a></div></div></article><article class="card t-guides">- <a class="thumb t-guides" href="/blog/how-to-add-an-mcp-server-to-claude-code/" aria-hidden="true" tabindex="-1"><img src="/blog/assets/media/how-to-add-an-mcp-server-to-claude-code/hero.png" alt="" loading="lazy" decoding="async" /></a>+ <a class="thumb t-guides" href="/blog/codex-max-plan-tips/" aria-hidden="true" tabindex="-1"><img src="/blog/assets/media/codex-max-plan-tips/hero.png" alt="" loading="lazy" decoding="async" /></a><div class="body"><div class="meta">- <time datetime="2026-09-10">Sep 10, 2026</time>+ <time datetime="2026-09-14">Sep 14, 2026</time><span class="dot" aria-hidden="true"></span><span>5 min</span></div>- <h3><a href="/blog/how-to-add-an-mcp-server-to-claude-code/">How to Add an MCP Server to Claude Code</a></h3>- <p class="dek">The claude mcp add command, its scope flag, editing .mcp.json by hand, and how Munder Difflin's Capabilities screen grants an MCP server to one agent at a time.</p>+ <h3><a href="/blog/codex-max-plan-tips/">How to Make the Most of Your Codex Max Plan</a></h3>+ <p class="dek">There is no Codex Max plan. What ChatGPT Pro 5x and 20x give you in Codex, how the weekly limit works, and how to stretch it.</p><div class="foot"><span class="tag kind">Guides</span>- <a class="more" href="/blog/how-to-add-an-mcp-server-to-claude-code/" aria-label="Read: How to Add an MCP Server to Claude Code">Read →</a>+ <a class="more" href="/blog/codex-max-plan-tips/" aria-label="Read: How to Make the Most of Your Codex Max Plan">Read →</a></div></div></article><article class="card t-guides">- <a class="thumb t-guides" href="/blog/command-center-guide/" aria-hidden="true" tabindex="-1"><img src="/blog/assets/media/command-center-guide/hero.png" alt="" loading="lazy" decoding="async" /></a>+ <a class="thumb t-guides" href="/blog/how-to-use-claude-code-plan-mode/" aria-hidden="true" tabindex="-1"><img src="/blog/assets/media/how-to-use-claude-code-plan-mode/hero.png" alt="" loading="lazy" decoding="async" /></a><div class="body"><div class="meta">- <time datetime="2026-07-03">Jul 3, 2026</time>+ <time datetime="2026-09-11">Sep 11, 2026</time><span class="dot" aria-hidden="true"></span>- <span>4 min</span>+ <span>5 min</span></div>- <h3><a href="/blog/command-center-guide/">The Command Center: Kanban, Fleet and Budgets in One Place</a></h3>- <p class="dek">A guide to Munder Difflin's Command Center in 0.5.2: the kanban with task dependencies, the ask me tab, triggers, memory, live token use against each agent's budget, and when to watch the board instead of the floor.</p>+ <h3><a href="/blog/how-to-use-claude-code-plan-mode/">How to Use Claude Code Plan Mode</a></h3>+ <p class="dek">How Claude Code's plan mode works: turning it on, what it blocks, what a real headless plan mode run prints, and how to leave it.</p><div class="foot"><span class="tag kind">Guides</span>- <a class="more" href="/blog/command-center-guide/" aria-label="Read: The Command Center: Kanban, Fleet and Budgets in One Place">Read →</a>+ <a class="more" href="/blog/how-to-use-claude-code-plan-mode/" aria-label="Read: How to Use Claude Code Plan Mode">Read →</a></div></div></article>diff --git a/docs/blog/how-to-use-claude-code-plan-mode/index.html b/docs/blog/how-to-use-claude-code-plan-mode/index.htmlindex 15f1ffb3..2329248e 100644--- a/docs/blog/how-to-use-claude-code-plan-mode/index.html+++ b/docs/blog/how-to-use-claude-code-plan-mode/index.html@@ -259,56 +259,56 @@ Turn plan mode off (Shift+Tab in the CLI, or restart without plan mode) and tell<footer class="post-foot wrap"><div class="prevnext"><a class="pn prev" href="/blog/what-is-an-mcp-server/"><span class="k">← Older</span><span class="t">What Is an MCP Server?</span></a>- <span></span>+ <a class="pn next" href="/blog/omniagent-alternatives/"><span class="k">Newer →</span><span class="t">OmniAgent Alternatives: What to Use Instead of Databricks Omnigent</span></a></div><section class="related"><h2>Related in Guides</h2><div class="post-grid"><article class="card t-guides">- <a class="thumb t-guides" href="/blog/how-to-add-an-mcp-server-to-claude-code/" aria-hidden="true" tabindex="-1"><img src="/blog/assets/media/how-to-add-an-mcp-server-to-claude-code/hero.png" alt="" loading="lazy" decoding="async" /></a>+ <a class="thumb t-guides" href="/blog/claude-code-max-plan-tips/" aria-hidden="true" tabindex="-1"><img src="/blog/assets/media/claude-code-max-plan-tips/hero.png" alt="" loading="lazy" decoding="async" /></a><div class="body"><div class="meta">- <time datetime="2026-09-10">Sep 10, 2026</time>+ <time datetime="2026-09-14">Sep 14, 2026</time><span class="dot" aria-hidden="true"></span><span>5 min</span></div>- <h3><a href="/blog/how-to-add-an-mcp-server-to-claude-code/">How to Add an MCP Server to Claude Code</a></h3>- <p class="dek">The claude mcp add command, its scope flag, editing .mcp.json by hand, and how Munder Difflin's Capabilities screen grants an MCP server to one agent at a time.</p>+ <h3><a href="/blog/claude-code-max-plan-tips/">How to Get the Most Out of Your Claude Code Max Plan</a></h3>+ <p class="dek">Stretch a Claude Code Max plan: model choice, context hygiene, prompt caching, subagents and unattended runs, checked against Anthropic's own pages.</p><div class="foot"><span class="tag kind">Guides</span>- <a class="more" href="/blog/how-to-add-an-mcp-server-to-claude-code/" aria-label="Read: How to Add an MCP Server to Claude Code">Read →</a>+ <a class="more" href="/blog/claude-code-max-plan-tips/" aria-label="Read: How to Get the Most Out of Your Claude Code Max Plan">Read →</a></div></div></article><article class="card t-guides">- <a class="thumb t-guides" href="/blog/command-center-guide/" aria-hidden="true" tabindex="-1"><img src="/blog/assets/media/command-center-guide/hero.png" alt="" loading="lazy" decoding="async" /></a>+ <a class="thumb t-guides" href="/blog/codex-max-plan-tips/" aria-hidden="true" tabindex="-1"><img src="/blog/assets/media/codex-max-plan-tips/hero.png" alt="" loading="lazy" decoding="async" /></a><div class="body"><div class="meta">- <time datetime="2026-07-03">Jul 3, 2026</time>+ <time datetime="2026-09-14">Sep 14, 2026</time><span class="dot" aria-hidden="true"></span>- <span>4 min</span>+ <span>5 min</span></div>- <h3><a href="/blog/command-center-guide/">The Command Center: Kanban, Fleet and Budgets in One Place</a></h3>- <p class="dek">A guide to Munder Difflin's Command Center in 0.5.2: the kanban with task dependencies, the ask me tab, triggers, memory, live token use against each agent's budget, and when to watch the board instead of the floor.</p>+ <h3><a href="/blog/codex-max-plan-tips/">How to Make the Most of Your Codex Max Plan</a></h3>+ <p class="dek">There is no Codex Max plan. What ChatGPT Pro 5x and 20x give you in Codex, how the weekly limit works, and how to stretch it.</p><div class="foot"><span class="tag kind">Guides</span>- <a class="more" href="/blog/command-center-guide/" aria-label="Read: The Command Center: Kanban, Fleet and Budgets in One Place">Read →</a>+ <a class="more" href="/blog/codex-max-plan-tips/" aria-label="Read: How to Make the Most of Your Codex Max Plan">Read →</a></div></div></article><article class="card t-guides">- <a class="thumb t-guides" href="/blog/how-to-add-a-github-copilot-cli-agent/" aria-hidden="true" tabindex="-1"><img src="/blog/assets/media/how-to-add-a-github-copilot-cli-agent/hero.png" alt="" loading="lazy" decoding="async" /></a>+ <a class="thumb t-guides" href="/blog/how-to-add-an-mcp-server-to-claude-code/" aria-hidden="true" tabindex="-1"><img src="/blog/assets/media/how-to-add-an-mcp-server-to-claude-code/hero.png" alt="" loading="lazy" decoding="async" /></a><div class="body"><div class="meta">- <time datetime="2026-07-03">Jul 3, 2026</time>+ <time datetime="2026-09-10">Sep 10, 2026</time><span class="dot" aria-hidden="true"></span>- <span>4 min</span>+ <span>5 min</span></div>- <h3><a href="/blog/how-to-add-a-github-copilot-cli-agent/">How to Add a GitHub Copilot CLI Agent to Your Floor</a></h3>- <p class="dek">A step-by-step v0.3.3 walkthrough: install GitHub Copilot CLI (or let the harness install it for you), hire a Copilot worker, pick a model, and know exactly what print mode can and can't do.</p>+ <h3><a href="/blog/how-to-add-an-mcp-server-to-claude-code/">How to Add an MCP Server to Claude Code</a></h3>+ <p class="dek">The claude mcp add command, its scope flag, editing .mcp.json by hand, and how Munder Difflin's Capabilities screen grants an MCP server to one agent at a time.</p><div class="foot"><span class="tag kind">Guides</span>- <a class="more" href="/blog/how-to-add-a-github-copilot-cli-agent/" aria-label="Read: How to Add a GitHub Copilot CLI Agent to Your Floor">Read →</a>+ <a class="more" href="/blog/how-to-add-an-mcp-server-to-claude-code/" aria-label="Read: How to Add an MCP Server to Claude Code">Read →</a></div></div></article>diff --git a/docs/blog/how-to-use-the-built-in-monaco-ide/index.html b/docs/blog/how-to-use-the-built-in-monaco-ide/index.htmlindex 66378c6f..c5651aa6 100644--- a/docs/blog/how-to-use-the-built-in-monaco-ide/index.html+++ b/docs/blog/how-to-use-the-built-in-monaco-ide/index.html@@ -272,50 +272,50 @@<h2>Related in Guides</h2><div class="post-grid"><article class="card t-guides">- <a class="thumb t-guides" href="/blog/how-to-use-claude-code-plan-mode/" aria-hidden="true" tabindex="-1"><img src="/blog/assets/media/how-to-use-claude-code-plan-mode/hero.png" alt="" loading="lazy" decoding="async" /></a>+ <a class="thumb t-guides" href="/blog/claude-code-max-plan-tips/" aria-hidden="true" tabindex="-1"><img src="/blog/assets/media/claude-code-max-plan-tips/hero.png" alt="" loading="lazy" decoding="async" /></a><div class="body"><div class="meta">- <time datetime="2026-09-11">Sep 11, 2026</time>+ <time datetime="2026-09-14">Sep 14, 2026</time><span class="dot" aria-hidden="true"></span><span>5 min</span></div>- <h3><a href="/blog/how-to-use-claude-code-plan-mode/">How to Use Claude Code Plan Mode</a></h3>- <p class="dek">How Claude Code's plan mode works: turning it on, what it blocks, what a real headless plan mode run prints, and how to leave it.</p>+ <h3><a href="/blog/claude-code-max-plan-tips/">How to Get the Most Out of Your Claude Code Max Plan</a></h3>+ <p class="dek">Stretch a Claude Code Max plan: model choice, context hygiene, prompt caching, subagents and unattended runs, checked against Anthropic's own pages.</p><div class="foot"><span class="tag kind">Guides</span>- <a class="more" href="/blog/how-to-use-claude-code-plan-mode/" aria-label="Read: How to Use Claude Code Plan Mode">Read →</a>+ <a class="more" href="/blog/claude-code-max-plan-tips/" aria-label="Read: How to Get the Most Out of Your Claude Code Max Plan">Read →</a></div></div></article><article class="card t-guides">- <a class="thumb t-guides" href="/blog/how-to-add-an-mcp-server-to-claude-code/" aria-hidden="true" tabindex="-1"><img src="/blog/assets/media/how-to-add-an-mcp-server-to-claude-code/hero.png" alt="" loading="lazy" decoding="async" /></a>+ <a class="thumb t-guides" href="/blog/codex-max-plan-tips/" aria-hidden="true" tabindex="-1"><img src="/blog/assets/media/codex-max-plan-tips/hero.png" alt="" loading="lazy" decoding="async" /></a><div class="body"><div class="meta">- <time datetime="2026-09-10">Sep 10, 2026</time>+ <time datetime="2026-09-14">Sep 14, 2026</time><span class="dot" aria-hidden="true"></span><span>5 min</span></div>- <h3><a href="/blog/how-to-add-an-mcp-server-to-claude-code/">How to Add an MCP Server to Claude Code</a></h3>- <p class="dek">The claude mcp add command, its scope flag, editing .mcp.json by hand, and how Munder Difflin's Capabilities screen grants an MCP server to one agent at a time.</p>+ <h3><a href="/blog/codex-max-plan-tips/">How to Make the Most of Your Codex Max Plan</a></h3>+ <p class="dek">There is no Codex Max plan. What ChatGPT Pro 5x and 20x give you in Codex, how the weekly limit works, and how to stretch it.</p><div class="foot"><span class="tag kind">Guides</span>- <a class="more" href="/blog/how-to-add-an-mcp-server-to-claude-code/" aria-label="Read: How to Add an MCP Server to Claude Code">Read →</a>+ <a class="more" href="/blog/codex-max-plan-tips/" aria-label="Read: How to Make the Most of Your Codex Max Plan">Read →</a></div></div></article><article class="card t-guides">- <a class="thumb t-guides" href="/blog/command-center-guide/" aria-hidden="true" tabindex="-1"><img src="/blog/assets/media/command-center-guide/hero.png" alt="" loading="lazy" decoding="async" /></a>+ <a class="thumb t-guides" href="/blog/how-to-use-claude-code-plan-mode/" aria-hidden="true" tabindex="-1"><img src="/blog/assets/media/how-to-use-claude-code-plan-mode/hero.png" alt="" loading="lazy" decoding="async" /></a><div class="body"><div class="meta">- <time datetime="2026-07-03">Jul 3, 2026</time>+ <time datetime="2026-09-11">Sep 11, 2026</time><span class="dot" aria-hidden="true"></span>- <span>4 min</span>+ <span>5 min</span></div>- <h3><a href="/blog/command-center-guide/">The Command Center: Kanban, Fleet and Budgets in One Place</a></h3>- <p class="dek">A guide to Munder Difflin's Command Center in 0.5.2: the kanban with task dependencies, the ask me tab, triggers, memory, live token use against each agent's budget, and when to watch the board instead of the floor.</p>+ <h3><a href="/blog/how-to-use-claude-code-plan-mode/">How to Use Claude Code Plan Mode</a></h3>+ <p class="dek">How Claude Code's plan mode works: turning it on, what it blocks, what a real headless plan mode run prints, and how to leave it.</p><div class="foot"><span class="tag kind">Guides</span>- <a class="more" href="/blog/command-center-guide/" aria-label="Read: The Command Center: Kanban, Fleet and Budgets in One Place">Read →</a>+ <a class="more" href="/blog/how-to-use-claude-code-plan-mode/" aria-label="Read: How to Use Claude Code Plan Mode">Read →</a></div></div></article>diff --git a/docs/blog/human-in-the-loop-approving-ai-agents/index.html b/docs/blog/human-in-the-loop-approving-ai-agents/index.htmlindex 6751086c..d843dc99 100644--- a/docs/blog/human-in-the-loop-approving-ai-agents/index.html+++ b/docs/blog/human-in-the-loop-approving-ai-agents/index.html@@ -307,50 +307,50 @@ you talk to? You can <a href="/#install">download Munder Difflin</a> free; it’<h2>Related in Guides</h2><div class="post-grid"><article class="card t-guides">- <a class="thumb t-guides" href="/blog/how-to-use-claude-code-plan-mode/" aria-hidden="true" tabindex="-1"><img src="/blog/assets/media/how-to-use-claude-code-plan-mode/hero.png" alt="" loading="lazy" decoding="async" /></a>+ <a class="thumb t-guides" href="/blog/claude-code-max-plan-tips/" aria-hidden="true" tabindex="-1"><img src="/blog/assets/media/claude-code-max-plan-tips/hero.png" alt="" loading="lazy" decoding="async" /></a><div class="body"><div class="meta">- <time datetime="2026-09-11">Sep 11, 2026</time>+ <time datetime="2026-09-14">Sep 14, 2026</time><span class="dot" aria-hidden="true"></span><span>5 min</span></div>- <h3><a href="/blog/how-to-use-claude-code-plan-mode/">How to Use Claude Code Plan Mode</a></h3>- <p class="dek">How Claude Code's plan mode works: turning it on, what it blocks, what a real headless plan mode run prints, and how to leave it.</p>+ <h3><a href="/blog/claude-code-max-plan-tips/">How to Get the Most Out of Your Claude Code Max Plan</a></h3>+ <p class="dek">Stretch a Claude Code Max plan: model choice, context hygiene, prompt caching, subagents and unattended runs, checked against Anthropic's own pages.</p><div class="foot"><span class="tag kind">Guides</span>- <a class="more" href="/blog/how-to-use-claude-code-plan-mode/" aria-label="Read: How to Use Claude Code Plan Mode">Read →</a>+ <a class="more" href="/blog/claude-code-max-plan-tips/" aria-label="Read: How to Get the Most Out of Your Claude Code Max Plan">Read →</a></div></div></article><article class="card t-guides">- <a class="thumb t-guides" href="/blog/how-to-add-an-mcp-server-to-claude-code/" aria-hidden="true" tabindex="-1"><img src="/blog/assets/media/how-to-add-an-mcp-server-to-claude-code/hero.png" alt="" loading="lazy" decoding="async" /></a>+ <a class="thumb t-guides" href="/blog/codex-max-plan-tips/" aria-hidden="true" tabindex="-1"><img src="/blog/assets/media/codex-max-plan-tips/hero.png" alt="" loading="lazy" decoding="async" /></a><div class="body"><div class="meta">- <time datetime="2026-09-10">Sep 10, 2026</time>+ <time datetime="2026-09-14">Sep 14, 2026</time><span class="dot" aria-hidden="true"></span><span>5 min</span></div>- <h3><a href="/blog/how-to-add-an-mcp-server-to-claude-code/">How to Add an MCP Server to Claude Code</a></h3>- <p class="dek">The claude mcp add command, its scope flag, editing .mcp.json by hand, and how Munder Difflin's Capabilities screen grants an MCP server to one agent at a time.</p>+ <h3><a href="/blog/codex-max-plan-tips/">How to Make the Most of Your Codex Max Plan</a></h3>+ <p class="dek">There is no Codex Max plan. What ChatGPT Pro 5x and 20x give you in Codex, how the weekly limit works, and how to stretch it.</p><div class="foot"><span class="tag kind">Guides</span>- <a class="more" href="/blog/how-to-add-an-mcp-server-to-claude-code/" aria-label="Read: How to Add an MCP Server to Claude Code">Read →</a>+ <a class="more" href="/blog/codex-max-plan-tips/" aria-label="Read: How to Make the Most of Your Codex Max Plan">Read →</a></div></div></article><article class="card t-guides">- <a class="thumb t-guides" href="/blog/command-center-guide/" aria-hidden="true" tabindex="-1"><img src="/blog/assets/media/command-center-guide/hero.png" alt="" loading="lazy" decoding="async" /></a>+ <a class="thumb t-guides" href="/blog/how-to-use-claude-code-plan-mode/" aria-hidden="true" tabindex="-1"><img src="/blog/assets/media/how-to-use-claude-code-plan-mode/hero.png" alt="" loading="lazy" decoding="async" /></a><div class="body"><div class="meta">- <time datetime="2026-07-03">Jul 3, 2026</time>+ <time datetime="2026-09-11">Sep 11, 2026</time><span class="dot" aria-hidden="true"></span>- <span>4 min</span>+ <span>5 min</span></div>- <h3><a href="/blog/command-center-guide/">The Command Center: Kanban, Fleet and Budgets in One Place</a></h3>- <p class="dek">A guide to Munder Difflin's Command Center in 0.5.2: the kanban with task dependencies, the ask me tab, triggers, memory, live token use against each agent's budget, and when to watch the board instead of the floor.</p>+ <h3><a href="/blog/how-to-use-claude-code-plan-mode/">How to Use Claude Code Plan Mode</a></h3>+ <p class="dek">How Claude Code's plan mode works: turning it on, what it blocks, what a real headless plan mode run prints, and how to leave it.</p><div class="foot"><span class="tag kind">Guides</span>- <a class="more" href="/blog/command-center-guide/" aria-label="Read: The Command Center: Kanban, Fleet and Budgets in One Place">Read →</a>+ <a class="more" href="/blog/how-to-use-claude-code-plan-mode/" aria-label="Read: How to Use Claude Code Plan Mode">Read →</a></div></div></article>diff --git a/docs/blog/index.html b/docs/blog/index.htmlindex edc6f65a..cc76e16b 100644--- a/docs/blog/index.html+++ b/docs/blog/index.html@@ -117,15 +117,15 @@building a self-coordinating hive of agents with a GOD orchestrator you talk to.</p><div class="filters" role="navigation" aria-label="Topics">- <a class="chip" aria-current="page">All<span class="ct">137</span></a>+ <a class="chip" aria-current="page">All<span class="ct">142</span></a>- <a class="chip" href="/blog/topics/guides/">guides<span class="ct">36</span></a>+ <a class="chip" href="/blog/topics/guides/">guides<span class="ct">38</span></a><a class="chip" href="/blog/topics/concepts/">concepts<span class="ct">23</span></a>- <a class="chip" href="/blog/topics/internals/">internals<span class="ct">19</span></a>+ <a class="chip" href="/blog/topics/comparisons/">comparisons<span class="ct">21</span></a>- <a class="chip" href="/blog/topics/comparisons/">comparisons<span class="ct">18</span></a>+ <a class="chip" href="/blog/topics/internals/">internals<span class="ct">19</span></a><a class="chip" href="/blog/topics/story/">story<span class="ct">18</span></a>@@ -245,18 +245,18 @@<div class="wrap featured"><article class="card t-guides">- <a class="thumb t-guides" href="/blog/how-to-use-claude-code-plan-mode/" aria-hidden="true" tabindex="-1"><img src="/blog/assets/media/how-to-use-claude-code-plan-mode/hero.png" alt="" loading="lazy" decoding="async" /></a>+ <a class="thumb t-guides" href="/blog/claude-code-max-plan-tips/" aria-hidden="true" tabindex="-1"><img src="/blog/assets/media/claude-code-max-plan-tips/hero.png" alt="" loading="lazy" decoding="async" /></a><div class="body"><div class="meta">- <time datetime="2026-09-11">Sep 11, 2026</time>+ <time datetime="2026-09-14">Sep 14, 2026</time><span class="dot" aria-hidden="true"></span><span>5 min</span></div>- <h3><a href="/blog/how-to-use-claude-code-plan-mode/">How to Use Claude Code Plan Mode</a></h3>- <p class="dek">How Claude Code's plan mode works: turning it on, what it blocks, what a real headless plan mode run prints, and how to leave it.</p>+ <h3><a href="/blog/claude-code-max-plan-tips/">How to Get the Most Out of Your Claude Code Max Plan</a></h3>+ <p class="dek">Stretch a Claude Code Max plan: model choice, context hygiene, prompt caching, subagents and unattended runs, checked against Anthropic's own pages.</p><div class="foot"><span class="tag kind">Guides</span>- <a class="more" href="/blog/how-to-use-claude-code-plan-mode/" aria-label="Read: How to Use Claude Code Plan Mode">Read →</a>+ <a class="more" href="/blog/claude-code-max-plan-tips/" aria-label="Read: How to Get the Most Out of Your Claude Code Max Plan">Read →</a></div></div></article>@@ -267,7 +267,87 @@<section class="wrap"><div class="post-grid">- <article class="card t-concepts">+ <article class="card t-guides">+ <a class="thumb t-guides" href="/blog/codex-max-plan-tips/" aria-hidden="true" tabindex="-1"><img src="/blog/assets/media/codex-max-plan-tips/hero.png" alt="" loading="lazy" decoding="async" /></a>+ <div class="body">+ <div class="meta">+ <time datetime="2026-09-14">Sep 14, 2026</time>+ <span class="dot" aria-hidden="true"></span>+ <span>5 min</span>+ </div>+ <h3><a href="/blog/codex-max-plan-tips/">How to Make the Most of Your Codex Max Plan</a></h3>+ <p class="dek">There is no Codex Max plan. What ChatGPT Pro 5x and 20x give you in Codex, how the weekly limit works, and how to stretch it.</p>+ <div class="foot">+ <span class="tag kind">Guides</span>+ <a class="more" href="/blog/codex-max-plan-tips/" aria-label="Read: How to Make the Most of Your Codex Max Plan">Read →</a>+ </div>+ </div>+</article>+<article class="card t-comparisons">+ <a class="thumb t-comparisons" href="/blog/grok-bot-alternatives/" aria-hidden="true" tabindex="-1"><img src="/blog/assets/media/grok-bot-alternatives/hero.png" alt="" loading="lazy" decoding="async" /></a>+ <div class="body">+ <div class="meta">+ <time datetime="2026-09-14">Sep 14, 2026</time>+ <span class="dot" aria-hidden="true"></span>+ <span>5 min</span>+ </div>+ <h3><a href="/blog/grok-bot-alternatives/">Grok Bot Alternatives: Six Picks, Grouped by What You Want</a></h3>+ <p class="dek">Grok Bot runs every Bot on one shared cloud computer. Six alternatives checked on 14 Sep 2026, grouped by hosting, privacy and model choice.</p>+ <div class="foot">+ <span class="tag kind">Comparisons</span>+ <a class="more" href="/blog/grok-bot-alternatives/" aria-label="Read: Grok Bot Alternatives: Six Picks, Grouped by What You Want">Read →</a>+ </div>+ </div>+</article>+<article class="card t-comparisons">+ <a class="thumb t-comparisons" href="/blog/herdr-alternatives/" aria-hidden="true" tabindex="-1"><img src="/blog/assets/media/herdr-alternatives/hero.png" alt="" loading="lazy" decoding="async" /></a>+ <div class="body">+ <div class="meta">+ <time datetime="2026-09-14">Sep 14, 2026</time>+ <span class="dot" aria-hidden="true"></span>+ <span>5 min</span>+ </div>+ <h3><a href="/blog/herdr-alternatives/">Herdr Alternatives: What to Pick and Who Each One Fits</a></h3>+ <p class="dek">Herdr alternatives checked on 14 Sep 2026: tmux, Claude Squad, cmux, Orca, Conductor, Superset, Emdash and Munder Difflin, and who each fits.</p>+ <div class="foot">+ <span class="tag kind">Comparisons</span>+ <a class="more" href="/blog/herdr-alternatives/" aria-label="Read: Herdr Alternatives: What to Pick and Who Each One Fits">Read →</a>+ </div>+ </div>+</article>+<article class="card t-comparisons">+ <a class="thumb t-comparisons" href="/blog/omniagent-alternatives/" aria-hidden="true" tabindex="-1"><span class="thumb-ph"><em class="ph-glyph" aria-hidden="true">✶</em><span>COMPARISONS</span></span></a>+ <div class="body">+ <div class="meta">+ <time datetime="2026-09-14">Sep 14, 2026</time>+ <span class="dot" aria-hidden="true"></span>+ <span>5 min</span>+ </div>+ <h3><a href="/blog/omniagent-alternatives/">OmniAgent Alternatives: What to Use Instead of Databricks Omnigent</a></h3>+ <p class="dek">OmniAgent is really Omnigent, the open source meta harness from Databricks. Alternatives checked on 14 Sep 2026, and who each one fits.</p>+ <div class="foot">+ <span class="tag kind">Comparisons</span>+ <a class="more" href="/blog/omniagent-alternatives/" aria-label="Read: OmniAgent Alternatives: What to Use Instead of Databricks Omnigent">Read →</a>+ </div>+ </div>+</article>+<article class="card t-guides">+ <a class="thumb t-guides" href="/blog/how-to-use-claude-code-plan-mode/" aria-hidden="true" tabindex="-1"><img src="/blog/assets/media/how-to-use-claude-code-plan-mode/hero.png" alt="" loading="lazy" decoding="async" /></a>+ <div class="body">+ <div class="meta">+ <time datetime="2026-09-11">Sep 11, 2026</time>+ <span class="dot" aria-hidden="true"></span>+ <span>5 min</span>+ </div>+ <h3><a href="/blog/how-to-use-claude-code-plan-mode/">How to Use Claude Code Plan Mode</a></h3>+ <p class="dek">How Claude Code's plan mode works: turning it on, what it blocks, what a real headless plan mode run prints, and how to leave it.</p>+ <div class="foot">+ <span class="tag kind">Guides</span>+ <a class="more" href="/blog/how-to-use-claude-code-plan-mode/" aria-label="Read: How to Use Claude Code Plan Mode">Read →</a>+ </div>+ </div>+</article>+<article class="card t-concepts"><a class="thumb t-concepts" href="/blog/what-is-an-mcp-server/" aria-hidden="true" tabindex="-1"><img src="/blog/assets/media/what-is-an-mcp-server/hero.png" alt="" loading="lazy" decoding="async" /></a><div class="body"><div class="meta">@@ -801,7 +881,7 @@<div class="meta"><time datetime="2026-07-03">Jul 3, 2026</time><span class="dot" aria-hidden="true"></span>- <span>4 min</span>+ <span>5 min</span></div><h3><a href="/blog/tmux-and-scripts-vs-an-agent-harness/">Running Agents in tmux vs an Agent Harness</a></h3><p class="dek">tmux panes, git worktrees, shell scripts, and cron will absolutely run several Claude Code sessions at once. Here's what that DIY setup does well, where it breaks at scale, and what a purpose-built agent harness automates.</p>diff --git a/docs/blog/local-first-vs-cloud-agent-sdks/index.html b/docs/blog/local-first-vs-cloud-agent-sdks/index.htmlindex 5ac7c14d..15812d63 100644--- a/docs/blog/local-first-vs-cloud-agent-sdks/index.html+++ b/docs/blog/local-first-vs-cloud-agent-sdks/index.html@@ -349,50 +349,50 @@ to run agents on your own terms — free and open source.</p><h2>Related in Comparisons</h2><div class="post-grid"><article class="card t-comparisons">- <a class="thumb t-comparisons" href="/blog/codex-cli-vs-claude-code/" aria-hidden="true" tabindex="-1"><img src="/blog/assets/media/codex-cli-vs-claude-code/hero.png" alt="" loading="lazy" decoding="async" /></a>+ <a class="thumb t-comparisons" href="/blog/grok-bot-alternatives/" aria-hidden="true" tabindex="-1"><img src="/blog/assets/media/grok-bot-alternatives/hero.png" alt="" loading="lazy" decoding="async" /></a><div class="body"><div class="meta">- <time datetime="2026-09-10">Sep 10, 2026</time>+ <time datetime="2026-09-14">Sep 14, 2026</time><span class="dot" aria-hidden="true"></span><span>5 min</span></div>- <h3><a href="/blog/codex-cli-vs-claude-code/">Codex CLI vs Claude Code</a></h3>- <p class="dek">Codex CLI and Claude Code compared firsthand: sandbox and approval flags, AGENTS.md vs CLAUDE.md, real pricing, and where each terminal agent wins.</p>+ <h3><a href="/blog/grok-bot-alternatives/">Grok Bot Alternatives: Six Picks, Grouped by What You Want</a></h3>+ <p class="dek">Grok Bot runs every Bot on one shared cloud computer. Six alternatives checked on 14 Sep 2026, grouped by hosting, privacy and model choice.</p><div class="foot"><span class="tag kind">Comparisons</span>- <a class="more" href="/blog/codex-cli-vs-claude-code/" aria-label="Read: Codex CLI vs Claude Code">Read →</a>+ <a class="more" href="/blog/grok-bot-alternatives/" aria-label="Read: Grok Bot Alternatives: Six Picks, Grouped by What You Want">Read →</a></div></div></article><article class="card t-comparisons">- <a class="thumb t-comparisons" href="/blog/qm-vs-munder-difflin/" aria-hidden="true" tabindex="-1"><img src="/blog/assets/media/qm-vs-munder-difflin/hero.png" alt="" loading="lazy" decoding="async" /></a>+ <a class="thumb t-comparisons" href="/blog/herdr-alternatives/" aria-hidden="true" tabindex="-1"><img src="/blog/assets/media/herdr-alternatives/hero.png" alt="" loading="lazy" decoding="async" /></a><div class="body"><div class="meta">- <time datetime="2026-08-06">Aug 6, 2026</time>+ <time datetime="2026-09-14">Sep 14, 2026</time><span class="dot" aria-hidden="true"></span>- <span>4 min</span>+ <span>5 min</span></div>- <h3><a href="/blog/qm-vs-munder-difflin/">qm vs Munder Difflin: YC's Multiplayer Harness or an Office of Your Clones?</a></h3>- <p class="dek">An honest September 2026 comparison of YC's qm and Munder Difflin. qm is a multiplayer agent harness a company deploys for Slack and the web. Munder Difflin runs an office of your clones on your own machine, with Teams to connect them.</p>+ <h3><a href="/blog/herdr-alternatives/">Herdr Alternatives: What to Pick and Who Each One Fits</a></h3>+ <p class="dek">Herdr alternatives checked on 14 Sep 2026: tmux, Claude Squad, cmux, Orca, Conductor, Superset, Emdash and Munder Difflin, and who each fits.</p><div class="foot"><span class="tag kind">Comparisons</span>- <a class="more" href="/blog/qm-vs-munder-difflin/" aria-label="Read: qm vs Munder Difflin: YC's Multiplayer Harness or an Office of Your Clones?">Read →</a>+ <a class="more" href="/blog/herdr-alternatives/" aria-label="Read: Herdr Alternatives: What to Pick and Who Each One Fits">Read →</a></div></div></article><article class="card t-comparisons">- <a class="thumb t-comparisons" href="/blog/crewai-autogen-vs-a-local-agent-harness/" aria-hidden="true" tabindex="-1"><img src="/blog/assets/media/crewai-autogen-vs-a-local-agent-harness/hero.png" alt="" loading="lazy" decoding="async" /></a>+ <a class="thumb t-comparisons" href="/blog/omniagent-alternatives/" aria-hidden="true" tabindex="-1"><span class="thumb-ph"><em class="ph-glyph" aria-hidden="true">✶</em><span>COMPARISONS</span></span></a><div class="body"><div class="meta">- <time datetime="2026-07-03">Jul 3, 2026</time>+ <time datetime="2026-09-14">Sep 14, 2026</time><span class="dot" aria-hidden="true"></span><span>5 min</span></div>- <h3><a href="/blog/crewai-autogen-vs-a-local-agent-harness/">CrewAI and AutoGen vs a Local Agent Harness: Framework or App?</a></h3>- <p class="dek">CrewAI, AutoGen (now Microsoft Agent Framework), and LangGraph are frameworks — Python you write to build your own agent system. A multi-agent harness is an app you download that runs a team on your repos today. Here's how to tell which one you actually need.</p>+ <h3><a href="/blog/omniagent-alternatives/">OmniAgent Alternatives: What to Use Instead of Databricks Omnigent</a></h3>+ <p class="dek">OmniAgent is really Omnigent, the open source meta harness from Databricks. Alternatives checked on 14 Sep 2026, and who each one fits.</p><div class="foot"><span class="tag kind">Comparisons</span>- <a class="more" href="/blog/crewai-autogen-vs-a-local-agent-harness/" aria-label="Read: CrewAI and AutoGen vs a Local Agent Harness: Framework or App?">Read →</a>+ <a class="more" href="/blog/omniagent-alternatives/" aria-label="Read: OmniAgent Alternatives: What to Use Instead of Databricks Omnigent">Read →</a></div></div></article>diff --git a/docs/blog/manage-multiple-claude-code-sessions/index.html b/docs/blog/manage-multiple-claude-code-sessions/index.htmlindex b4b80150..fd97a23e 100644--- a/docs/blog/manage-multiple-claude-code-sessions/index.html+++ b/docs/blog/manage-multiple-claude-code-sessions/index.html@@ -304,50 +304,50 @@ isolated agents, shared memory, and a single committer, all on your own machine.<h2>Related in Guides</h2><div class="post-grid"><article class="card t-guides">- <a class="thumb t-guides" href="/blog/how-to-use-claude-code-plan-mode/" aria-hidden="true" tabindex="-1"><img src="/blog/assets/media/how-to-use-claude-code-plan-mode/hero.png" alt="" loading="lazy" decoding="async" /></a>+ <a class="thumb t-guides" href="/blog/claude-code-max-plan-tips/" aria-hidden="true" tabindex="-1"><img src="/blog/assets/media/claude-code-max-plan-tips/hero.png" alt="" loading="lazy" decoding="async" /></a><div class="body"><div class="meta">- <time datetime="2026-09-11">Sep 11, 2026</time>+ <time datetime="2026-09-14">Sep 14, 2026</time><span class="dot" aria-hidden="true"></span><span>5 min</span></div>- <h3><a href="/blog/how-to-use-claude-code-plan-mode/">How to Use Claude Code Plan Mode</a></h3>- <p class="dek">How Claude Code's plan mode works: turning it on, what it blocks, what a real headless plan mode run prints, and how to leave it.</p>+ <h3><a href="/blog/claude-code-max-plan-tips/">How to Get the Most Out of Your Claude Code Max Plan</a></h3>+ <p class="dek">Stretch a Claude Code Max plan: model choice, context hygiene, prompt caching, subagents and unattended runs, checked against Anthropic's own pages.</p><div class="foot"><span class="tag kind">Guides</span>- <a class="more" href="/blog/how-to-use-claude-code-plan-mode/" aria-label="Read: How to Use Claude Code Plan Mode">Read →</a>+ <a class="more" href="/blog/claude-code-max-plan-tips/" aria-label="Read: How to Get the Most Out of Your Claude Code Max Plan">Read →</a></div></div></article><article class="card t-guides">- <a class="thumb t-guides" href="/blog/how-to-add-an-mcp-server-to-claude-code/" aria-hidden="true" tabindex="-1"><img src="/blog/assets/media/how-to-add-an-mcp-server-to-claude-code/hero.png" alt="" loading="lazy" decoding="async" /></a>+ <a class="thumb t-guides" href="/blog/codex-max-plan-tips/" aria-hidden="true" tabindex="-1"><img src="/blog/assets/media/codex-max-plan-tips/hero.png" alt="" loading="lazy" decoding="async" /></a><div class="body"><div class="meta">- <time datetime="2026-09-10">Sep 10, 2026</time>+ <time datetime="2026-09-14">Sep 14, 2026</time><span class="dot" aria-hidden="true"></span><span>5 min</span></div>- <h3><a href="/blog/how-to-add-an-mcp-server-to-claude-code/">How to Add an MCP Server to Claude Code</a></h3>- <p class="dek">The claude mcp add command, its scope flag, editing .mcp.json by hand, and how Munder Difflin's Capabilities screen grants an MCP server to one agent at a time.</p>+ <h3><a href="/blog/codex-max-plan-tips/">How to Make the Most of Your Codex Max Plan</a></h3>+ <p class="dek">There is no Codex Max plan. What ChatGPT Pro 5x and 20x give you in Codex, how the weekly limit works, and how to stretch it.</p><div class="foot"><span class="tag kind">Guides</span>- <a class="more" href="/blog/how-to-add-an-mcp-server-to-claude-code/" aria-label="Read: How to Add an MCP Server to Claude Code">Read →</a>+ <a class="more" href="/blog/codex-max-plan-tips/" aria-label="Read: How to Make the Most of Your Codex Max Plan">Read →</a></div></div></article><article class="card t-guides">- <a class="thumb t-guides" href="/blog/command-center-guide/" aria-hidden="true" tabindex="-1"><img src="/blog/assets/media/command-center-guide/hero.png" alt="" loading="lazy" decoding="async" /></a>+ <a class="thumb t-guides" href="/blog/how-to-use-claude-code-plan-mode/" aria-hidden="true" tabindex="-1"><img src="/blog/assets/media/how-to-use-claude-code-plan-mode/hero.png" alt="" loading="lazy" decoding="async" /></a><div class="body"><div class="meta">- <time datetime="2026-07-03">Jul 3, 2026</time>+ <time datetime="2026-09-11">Sep 11, 2026</time><span class="dot" aria-hidden="true"></span>- <span>4 min</span>+ <span>5 min</span></div>- <h3><a href="/blog/command-center-guide/">The Command Center: Kanban, Fleet and Budgets in One Place</a></h3>- <p class="dek">A guide to Munder Difflin's Command Center in 0.5.2: the kanban with task dependencies, the ask me tab, triggers, memory, live token use against each agent's budget, and when to watch the board instead of the floor.</p>+ <h3><a href="/blog/how-to-use-claude-code-plan-mode/">How to Use Claude Code Plan Mode</a></h3>+ <p class="dek">How Claude Code's plan mode works: turning it on, what it blocks, what a real headless plan mode run prints, and how to leave it.</p><div class="foot"><span class="tag kind">Guides</span>- <a class="more" href="/blog/command-center-guide/" aria-label="Read: The Command Center: Kanban, Fleet and Budgets in One Place">Read →</a>+ <a class="more" href="/blog/how-to-use-claude-code-plan-mode/" aria-label="Read: How to Use Claude Code Plan Mode">Read →</a></div></div></article>diff --git a/docs/blog/mcp-and-skills-in-a-hive/index.html b/docs/blog/mcp-and-skills-in-a-hive/index.htmlindex 3b8186a3..c1400240 100644--- a/docs/blog/mcp-and-skills-in-a-hive/index.html+++ b/docs/blog/mcp-and-skills-in-a-hive/index.html@@ -320,50 +320,50 @@ existing setup into a coordinated team of agents; it’s free and open source.</<h2>Related in Guides</h2><div class="post-grid"><article class="card t-guides">- <a class="thumb t-guides" href="/blog/how-to-use-claude-code-plan-mode/" aria-hidden="true" tabindex="-1"><img src="/blog/assets/media/how-to-use-claude-code-plan-mode/hero.png" alt="" loading="lazy" decoding="async" /></a>+ <a class="thumb t-guides" href="/blog/claude-code-max-plan-tips/" aria-hidden="true" tabindex="-1"><img src="/blog/assets/media/claude-code-max-plan-tips/hero.png" alt="" loading="lazy" decoding="async" /></a><div class="body"><div class="meta">- <time datetime="2026-09-11">Sep 11, 2026</time>+ <time datetime="2026-09-14">Sep 14, 2026</time><span class="dot" aria-hidden="true"></span><span>5 min</span></div>- <h3><a href="/blog/how-to-use-claude-code-plan-mode/">How to Use Claude Code Plan Mode</a></h3>- <p class="dek">How Claude Code's plan mode works: turning it on, what it blocks, what a real headless plan mode run prints, and how to leave it.</p>+ <h3><a href="/blog/claude-code-max-plan-tips/">How to Get the Most Out of Your Claude Code Max Plan</a></h3>+ <p class="dek">Stretch a Claude Code Max plan: model choice, context hygiene, prompt caching, subagents and unattended runs, checked against Anthropic's own pages.</p><div class="foot"><span class="tag kind">Guides</span>- <a class="more" href="/blog/how-to-use-claude-code-plan-mode/" aria-label="Read: How to Use Claude Code Plan Mode">Read →</a>+ <a class="more" href="/blog/claude-code-max-plan-tips/" aria-label="Read: How to Get the Most Out of Your Claude Code Max Plan">Read →</a></div></div></article><article class="card t-guides">- <a class="thumb t-guides" href="/blog/how-to-add-an-mcp-server-to-claude-code/" aria-hidden="true" tabindex="-1"><img src="/blog/assets/media/how-to-add-an-mcp-server-to-claude-code/hero.png" alt="" loading="lazy" decoding="async" /></a>+ <a class="thumb t-guides" href="/blog/codex-max-plan-tips/" aria-hidden="true" tabindex="-1"><img src="/blog/assets/media/codex-max-plan-tips/hero.png" alt="" loading="lazy" decoding="async" /></a><div class="body"><div class="meta">- <time datetime="2026-09-10">Sep 10, 2026</time>+ <time datetime="2026-09-14">Sep 14, 2026</time><span class="dot" aria-hidden="true"></span><span>5 min</span></div>- <h3><a href="/blog/how-to-add-an-mcp-server-to-claude-code/">How to Add an MCP Server to Claude Code</a></h3>- <p class="dek">The claude mcp add command, its scope flag, editing .mcp.json by hand, and how Munder Difflin's Capabilities screen grants an MCP server to one agent at a time.</p>+ <h3><a href="/blog/codex-max-plan-tips/">How to Make the Most of Your Codex Max Plan</a></h3>+ <p class="dek">There is no Codex Max plan. What ChatGPT Pro 5x and 20x give you in Codex, how the weekly limit works, and how to stretch it.</p><div class="foot"><span class="tag kind">Guides</span>- <a class="more" href="/blog/how-to-add-an-mcp-server-to-claude-code/" aria-label="Read: How to Add an MCP Server to Claude Code">Read →</a>+ <a class="more" href="/blog/codex-max-plan-tips/" aria-label="Read: How to Make the Most of Your Codex Max Plan">Read →</a></div></div></article><article class="card t-guides">- <a class="thumb t-guides" href="/blog/command-center-guide/" aria-hidden="true" tabindex="-1"><img src="/blog/assets/media/command-center-guide/hero.png" alt="" loading="lazy" decoding="async" /></a>+ <a class="thumb t-guides" href="/blog/how-to-use-claude-code-plan-mode/" aria-hidden="true" tabindex="-1"><img src="/blog/assets/media/how-to-use-claude-code-plan-mode/hero.png" alt="" loading="lazy" decoding="async" /></a><div class="body"><div class="meta">- <time datetime="2026-07-03">Jul 3, 2026</time>+ <time datetime="2026-09-11">Sep 11, 2026</time><span class="dot" aria-hidden="true"></span>- <span>4 min</span>+ <span>5 min</span></div>- <h3><a href="/blog/command-center-guide/">The Command Center: Kanban, Fleet and Budgets in One Place</a></h3>- <p class="dek">A guide to Munder Difflin's Command Center in 0.5.2: the kanban with task dependencies, the ask me tab, triggers, memory, live token use against each agent's budget, and when to watch the board instead of the floor.</p>+ <h3><a href="/blog/how-to-use-claude-code-plan-mode/">How to Use Claude Code Plan Mode</a></h3>+ <p class="dek">How Claude Code's plan mode works: turning it on, what it blocks, what a real headless plan mode run prints, and how to leave it.</p><div class="foot"><span class="tag kind">Guides</span>- <a class="more" href="/blog/command-center-guide/" aria-label="Read: The Command Center: Kanban, Fleet and Budgets in One Place">Read →</a>+ <a class="more" href="/blog/how-to-use-claude-code-plan-mode/" aria-label="Read: How to Use Claude Code Plan Mode">Read →</a></div></div></article>diff --git a/docs/blog/mcp-security-tool-poisoning/index.html b/docs/blog/mcp-security-tool-poisoning/index.htmlindex db56c1ef..20a1975d 100644--- a/docs/blog/mcp-security-tool-poisoning/index.html+++ b/docs/blog/mcp-security-tool-poisoning/index.html@@ -309,50 +309,50 @@ execution. Do that and MCP is what it should be: a powerful, <em>bounded</em> wa<h2>Related in Guides</h2><div class="post-grid"><article class="card t-guides">- <a class="thumb t-guides" href="/blog/how-to-use-claude-code-plan-mode/" aria-hidden="true" tabindex="-1"><img src="/blog/assets/media/how-to-use-claude-code-plan-mode/hero.png" alt="" loading="lazy" decoding="async" /></a>+ <a class="thumb t-guides" href="/blog/claude-code-max-plan-tips/" aria-hidden="true" tabindex="-1"><img src="/blog/assets/media/claude-code-max-plan-tips/hero.png" alt="" loading="lazy" decoding="async" /></a><div class="body"><div class="meta">- <time datetime="2026-09-11">Sep 11, 2026</time>+ <time datetime="2026-09-14">Sep 14, 2026</time><span class="dot" aria-hidden="true"></span><span>5 min</span></div>- <h3><a href="/blog/how-to-use-claude-code-plan-mode/">How to Use Claude Code Plan Mode</a></h3>- <p class="dek">How Claude Code's plan mode works: turning it on, what it blocks, what a real headless plan mode run prints, and how to leave it.</p>+ <h3><a href="/blog/claude-code-max-plan-tips/">How to Get the Most Out of Your Claude Code Max Plan</a></h3>+ <p class="dek">Stretch a Claude Code Max plan: model choice, context hygiene, prompt caching, subagents and unattended runs, checked against Anthropic's own pages.</p><div class="foot"><span class="tag kind">Guides</span>- <a class="more" href="/blog/how-to-use-claude-code-plan-mode/" aria-label="Read: How to Use Claude Code Plan Mode">Read →</a>+ <a class="more" href="/blog/claude-code-max-plan-tips/" aria-label="Read: How to Get the Most Out of Your Claude Code Max Plan">Read →</a></div></div></article><article class="card t-guides">- <a class="thumb t-guides" href="/blog/how-to-add-an-mcp-server-to-claude-code/" aria-hidden="true" tabindex="-1"><img src="/blog/assets/media/how-to-add-an-mcp-server-to-claude-code/hero.png" alt="" loading="lazy" decoding="async" /></a>+ <a class="thumb t-guides" href="/blog/codex-max-plan-tips/" aria-hidden="true" tabindex="-1"><img src="/blog/assets/media/codex-max-plan-tips/hero.png" alt="" loading="lazy" decoding="async" /></a><div class="body"><div class="meta">- <time datetime="2026-09-10">Sep 10, 2026</time>+ <time datetime="2026-09-14">Sep 14, 2026</time><span class="dot" aria-hidden="true"></span><span>5 min</span></div>- <h3><a href="/blog/how-to-add-an-mcp-server-to-claude-code/">How to Add an MCP Server to Claude Code</a></h3>- <p class="dek">The claude mcp add command, its scope flag, editing .mcp.json by hand, and how Munder Difflin's Capabilities screen grants an MCP server to one agent at a time.</p>+ <h3><a href="/blog/codex-max-plan-tips/">How to Make the Most of Your Codex Max Plan</a></h3>+ <p class="dek">There is no Codex Max plan. What ChatGPT Pro 5x and 20x give you in Codex, how the weekly limit works, and how to stretch it.</p><div class="foot"><span class="tag kind">Guides</span>- <a class="more" href="/blog/how-to-add-an-mcp-server-to-claude-code/" aria-label="Read: How to Add an MCP Server to Claude Code">Read →</a>+ <a class="more" href="/blog/codex-max-plan-tips/" aria-label="Read: How to Make the Most of Your Codex Max Plan">Read →</a></div></div></article><article class="card t-guides">- <a class="thumb t-guides" href="/blog/command-center-guide/" aria-hidden="true" tabindex="-1"><img src="/blog/assets/media/command-center-guide/hero.png" alt="" loading="lazy" decoding="async" /></a>+ <a class="thumb t-guides" href="/blog/how-to-use-claude-code-plan-mode/" aria-hidden="true" tabindex="-1"><img src="/blog/assets/media/how-to-use-claude-code-plan-mode/hero.png" alt="" loading="lazy" decoding="async" /></a><div class="body"><div class="meta">- <time datetime="2026-07-03">Jul 3, 2026</time>+ <time datetime="2026-09-11">Sep 11, 2026</time><span class="dot" aria-hidden="true"></span>- <span>4 min</span>+ <span>5 min</span></div>- <h3><a href="/blog/command-center-guide/">The Command Center: Kanban, Fleet and Budgets in One Place</a></h3>- <p class="dek">A guide to Munder Difflin's Command Center in 0.5.2: the kanban with task dependencies, the ask me tab, triggers, memory, live token use against each agent's budget, and when to watch the board instead of the floor.</p>+ <h3><a href="/blog/how-to-use-claude-code-plan-mode/">How to Use Claude Code Plan Mode</a></h3>+ <p class="dek">How Claude Code's plan mode works: turning it on, what it blocks, what a real headless plan mode run prints, and how to leave it.</p><div class="foot"><span class="tag kind">Guides</span>- <a class="more" href="/blog/command-center-guide/" aria-label="Read: The Command Center: Kanban, Fleet and Budgets in One Place">Read →</a>+ <a class="more" href="/blog/how-to-use-claude-code-plan-mode/" aria-label="Read: How to Use Claude Code Plan Mode">Read →</a></div></div></article>diff --git a/docs/blog/munder-difflin-v0-2-4-feature-walkthrough/index.html b/docs/blog/munder-difflin-v0-2-4-feature-walkthrough/index.htmlindex 9740dbee..26a5cb52 100644--- a/docs/blog/munder-difflin-v0-2-4-feature-walkthrough/index.html+++ b/docs/blog/munder-difflin-v0-2-4-feature-walkthrough/index.html@@ -285,50 +285,50 @@<h2>Related in Guides</h2><div class="post-grid"><article class="card t-guides">- <a class="thumb t-guides" href="/blog/how-to-use-claude-code-plan-mode/" aria-hidden="true" tabindex="-1"><img src="/blog/assets/media/how-to-use-claude-code-plan-mode/hero.png" alt="" loading="lazy" decoding="async" /></a>+ <a class="thumb t-guides" href="/blog/claude-code-max-plan-tips/" aria-hidden="true" tabindex="-1"><img src="/blog/assets/media/claude-code-max-plan-tips/hero.png" alt="" loading="lazy" decoding="async" /></a><div class="body"><div class="meta">- <time datetime="2026-09-11">Sep 11, 2026</time>+ <time datetime="2026-09-14">Sep 14, 2026</time><span class="dot" aria-hidden="true"></span><span>5 min</span></div>- <h3><a href="/blog/how-to-use-claude-code-plan-mode/">How to Use Claude Code Plan Mode</a></h3>- <p class="dek">How Claude Code's plan mode works: turning it on, what it blocks, what a real headless plan mode run prints, and how to leave it.</p>+ <h3><a href="/blog/claude-code-max-plan-tips/">How to Get the Most Out of Your Claude Code Max Plan</a></h3>+ <p class="dek">Stretch a Claude Code Max plan: model choice, context hygiene, prompt caching, subagents and unattended runs, checked against Anthropic's own pages.</p><div class="foot"><span class="tag kind">Guides</span>- <a class="more" href="/blog/how-to-use-claude-code-plan-mode/" aria-label="Read: How to Use Claude Code Plan Mode">Read →</a>+ <a class="more" href="/blog/claude-code-max-plan-tips/" aria-label="Read: How to Get the Most Out of Your Claude Code Max Plan">Read →</a></div></div></article><article class="card t-guides">- <a class="thumb t-guides" href="/blog/how-to-add-an-mcp-server-to-claude-code/" aria-hidden="true" tabindex="-1"><img src="/blog/assets/media/how-to-add-an-mcp-server-to-claude-code/hero.png" alt="" loading="lazy" decoding="async" /></a>+ <a class="thumb t-guides" href="/blog/codex-max-plan-tips/" aria-hidden="true" tabindex="-1"><img src="/blog/assets/media/codex-max-plan-tips/hero.png" alt="" loading="lazy" decoding="async" /></a><div class="body"><div class="meta">- <time datetime="2026-09-10">Sep 10, 2026</time>+ <time datetime="2026-09-14">Sep 14, 2026</time><span class="dot" aria-hidden="true"></span><span>5 min</span></div>- <h3><a href="/blog/how-to-add-an-mcp-server-to-claude-code/">How to Add an MCP Server to Claude Code</a></h3>- <p class="dek">The claude mcp add command, its scope flag, editing .mcp.json by hand, and how Munder Difflin's Capabilities screen grants an MCP server to one agent at a time.</p>+ <h3><a href="/blog/codex-max-plan-tips/">How to Make the Most of Your Codex Max Plan</a></h3>+ <p class="dek">There is no Codex Max plan. What ChatGPT Pro 5x and 20x give you in Codex, how the weekly limit works, and how to stretch it.</p><div class="foot"><span class="tag kind">Guides</span>- <a class="more" href="/blog/how-to-add-an-mcp-server-to-claude-code/" aria-label="Read: How to Add an MCP Server to Claude Code">Read →</a>+ <a class="more" href="/blog/codex-max-plan-tips/" aria-label="Read: How to Make the Most of Your Codex Max Plan">Read →</a></div></div></article><article class="card t-guides">- <a class="thumb t-guides" href="/blog/command-center-guide/" aria-hidden="true" tabindex="-1"><img src="/blog/assets/media/command-center-guide/hero.png" alt="" loading="lazy" decoding="async" /></a>+ <a class="thumb t-guides" href="/blog/how-to-use-claude-code-plan-mode/" aria-hidden="true" tabindex="-1"><img src="/blog/assets/media/how-to-use-claude-code-plan-mode/hero.png" alt="" loading="lazy" decoding="async" /></a><div class="body"><div class="meta">- <time datetime="2026-07-03">Jul 3, 2026</time>+ <time datetime="2026-09-11">Sep 11, 2026</time><span class="dot" aria-hidden="true"></span>- <span>4 min</span>+ <span>5 min</span></div>- <h3><a href="/blog/command-center-guide/">The Command Center: Kanban, Fleet and Budgets in One Place</a></h3>- <p class="dek">A guide to Munder Difflin's Command Center in 0.5.2: the kanban with task dependencies, the ask me tab, triggers, memory, live token use against each agent's budget, and when to watch the board instead of the floor.</p>+ <h3><a href="/blog/how-to-use-claude-code-plan-mode/">How to Use Claude Code Plan Mode</a></h3>+ <p class="dek">How Claude Code's plan mode works: turning it on, what it blocks, what a real headless plan mode run prints, and how to leave it.</p><div class="foot"><span class="tag kind">Guides</span>- <a class="more" href="/blog/command-center-guide/" aria-label="Read: The Command Center: Kanban, Fleet and Budgets in One Place">Read →</a>+ <a class="more" href="/blog/how-to-use-claude-code-plan-mode/" aria-label="Read: How to Use Claude Code Plan Mode">Read →</a></div></div></article>diff --git a/docs/blog/omniagent-alternatives/index.html b/docs/blog/omniagent-alternatives/index.htmlnew file mode 100644index 00000000..6a9d3c81--- /dev/null+++ b/docs/blog/omniagent-alternatives/index.html@@ -0,0 +1,397 @@+<!doctype html>+<html lang="en">+<head>+<meta charset="UTF-8" />+<meta name="viewport" content="width=device-width, initial-scale=1.0" />+<title>OmniAgent Alternatives: What to Use Instead of Databricks Omnigent — Munder Difflin Blog</title>+<meta name="description" content="OmniAgent is really Omnigent, the open source meta harness from Databricks. Alternatives checked on 14 Sep 2026, and who each one fits." />+<link rel="canonical" href="https://munderdiffl.in/blog/omniagent-alternatives/" />++<link rel="icon" type="image/png" href="https://munderdiffl.in/logo.png" />+<link rel="apple-touch-icon" href="https://munderdiffl.in/logo.png" />+<meta name="theme-color" content="#F5F2E8" />++<!-- Open Graph -->+<meta property="og:site_name" content="Munder Difflin Blog" />+<meta property="og:type" content="article" />+<meta property="og:title" content="OmniAgent Alternatives: What to Use Instead of Databricks Omnigent — Munder Difflin Blog" />+<meta property="og:description" content="OmniAgent is really Omnigent, the open source meta harness from Databricks. Alternatives checked on 14 Sep 2026, and who each one fits." />+<meta property="og:url" content="https://munderdiffl.in/blog/omniagent-alternatives/" />+<meta property="og:image" content="https://munderdiffl.in/media/og.png" />+<meta property="og:locale" content="en_US" />+<meta property="article:published_time" content="2026-09-14T00:00:00.000Z" />+<meta property="article:author" content="Chaitanya Giri" />+<meta property="article:tag" content="Comparisons" />+<meta property="article:tag" content="Multi-Agent" />+<meta property="article:tag" content="Claude Code" />+<meta property="article:tag" content="Tools" />+<meta property="article:tag" content="Open Source" />+++<!-- Twitter -->+<meta name="twitter:card" content="summary_large_image" />+<meta name="twitter:title" content="OmniAgent Alternatives: What to Use Instead of Databricks Omnigent — Munder Difflin Blog" />+<meta name="twitter:description" content="OmniAgent is really Omnigent, the open source meta harness from Databricks. Alternatives checked on 14 Sep 2026, and who each one fits." />+<meta name="twitter:image" content="https://munderdiffl.in/media/og.png" />++<link rel="alternate" type="application/atom+xml" title="Munder Difflin Blog" href="https://munderdiffl.in/blog/feed.xml" />+<link rel="preconnect" href="https://fonts.googleapis.com" />+<link rel="preconnect" href="https://fonts.gstatic.com" crossorigin />+<link href="https://fonts.googleapis.com/css2?family=Fraunces:opsz,[email protected],500;9..144,600;9..144,700;9..144,900&family=Source+Serif+4:opsz,[email protected],400;8..60,600;8..60,700&family=Space+Grotesk:wght@500;600;700&family=JetBrains+Mono:wght@400;600&display=swap" rel="stylesheet" />+<link rel="stylesheet" href="/blog/assets/blog-press.css" />++<script type="application/ld+json">+{+ "@context": "https://schema.org",+ "@type": "BlogPosting",+ "headline": "OmniAgent Alternatives: What to Use Instead of Databricks Omnigent",+ "description": "OmniAgent is really Omnigent, the open source meta harness from Databricks. Alternatives checked on 14 Sep 2026, and who each one fits.",+ "image": ["https://munderdiffl.in/media/og.png"],+ "datePublished": "2026-09-14T00:00:00.000Z",+ "dateModified": "2026-09-14T00:00:00.000Z",+ "author": { "@type": "Person", "name": "Chaitanya Giri" },+ "publisher": {+ "@type": "Organization",+ "name": "Munder Difflin",+ "logo": { "@type": "ImageObject", "url": "https://munderdiffl.in/logo.png" }+ },+ "mainEntityOfPage": { "@type": "WebPage", "@id": "https://munderdiffl.in/blog/omniagent-alternatives/" },+ "keywords": "omniagent alternatives, omnigent alternatives, omnigent databricks, omnigent meta harness, omniagent harness, omnigent vs opencode",+ "articleSection": "Comparisons",+ "inLanguage": "en-US",+ "url": "https://munderdiffl.in/blog/omniagent-alternatives/"+}+</script>+<script type="application/ld+json">+{+ "@context": "https://schema.org",+ "@type": "BreadcrumbList",+ "itemListElement": [+ { "@type": "ListItem", "position": 1, "name": "Home", "item": "https://munderdiffl.in/" },+ { "@type": "ListItem", "position": 2, "name": "Blog", "item": "https://munderdiffl.in/blog/" },+ { "@type": "ListItem", "position": 3, "name": "OmniAgent Alternatives: What to Use Instead of Databricks Omnigent", "item": "https://munderdiffl.in/blog/omniagent-alternatives/" }+ ]+}+</script>++<script type="application/ld+json">+{+ "@context": "https://schema.org",+ "@type": "FAQPage",+ "mainEntity": [+ { "@type": "Question", "name": "Is OmniAgent the same as Omnigent?", "acceptedAnswer": { "@type": "Answer", "text": "If you mean the Databricks agent harness, yes: the project is called Omnigent and lives in the omnigent-ai/omnigent repository on GitHub. OmniAgent is also the name of unrelated projects, such as a personal assistant that answers across chat apps (plexusone/omniagent) and a terminal for CLI agents on remote servers (sbyoun/OmniAgent)." } },+ { "@type": "Question", "name": "Is Omnigent open source?", "acceptedAnswer": { "@type": "Answer", "text": "Yes. Omnigent is licensed under Apache 2.0, and its NOTICE file carries a Databricks copyright, checked on 14 Sep 2026. Databricks also runs a managed version called Omnigent on Databricks, which its docs listed as Beta on 11 Sep 2026." } },+ { "@type": "Question", "name": "Do you need Databricks to use Omnigent?", "acceptedAnswer": { "@type": "Answer", "text": "No. The open source release runs on your own machine or any server, and its README lists four kinds of model credentials: a vendor API key, a Claude or ChatGPT subscription through the official CLIs, a compatible gateway such as OpenRouter or Ollama, or a Databricks workspace. Databricks is one option, not a requirement." } },+ { "@type": "Question", "name": "Does Omnigent work on Windows?", "acceptedAnswer": { "@type": "Answer", "text": "Partly. The README says Omnigent runs natively on Windows in a degraded mode: the server, the web UI and the SDK based harnesses work, but the native Claude, Codex and Cursor terminal wrappers and the filesystem and network sandbox do not. For those it points you to Linux, macOS or WSL." } }++ ]+}+</script>+++<script>+ // Anonymous blog analytics (PostHog) — same posture as the main site and the+ // app's TELEMETRY.md: public write-only token ('' = inert), anonymous-only+ // (person_profiles 'never'), no autocapture/recording, DNT respected.+ (function () {+ var PH_KEY = 'phc_qJzsokwcbtTGHemnvywR3nSqivNNgMjHeNVEWkZNydFB';+ if (!PH_KEY || navigator.doNotTrack === '1') return;+ var s = document.createElement('script');+ s.async = true;+ s.src = 'https://us-assets.i.posthog.com/static/array.js';+ s.onload = function () {+ if (!window.posthog) return;+ window.posthog.init(PH_KEY, {+ api_host: 'https://us.i.posthog.com',+ person_profiles: 'never',+ autocapture: false,+ before_send: function (event) {+ // PostHog fills $ip from the connection unless the event carries one.+ // Null it here and disable the GeoIP lookup so no IP, city, postal+ // code or lat/long is ever derived or stored for this page view.+ if (event && event.properties) {+ event.properties.$ip = null;+ event.properties.$geoip_disable = true;+ }+ return event;+ },+ disable_session_recording: true,+ respect_dnt: true+ });+ };+ document.head.appendChild(s);+ })();+</script>+</head>+<body class="theme-press">+<a class="skip-link" href="#main">Skip to content</a>+<nav id="nav">+ <a class="brand" href="https://munderdiffl.in" aria-label="Munder Difflin home">+ <img class="brand-logo" src="https://munderdiffl.in/logo.png" width="1318" height="840" alt="Munder Difflin, Inc. — Multi-Agent Harness" />+ </a>+ <span class="spacer"></span>+ <div class="links">+ <a href="/blog/">Latest</a>+ <a href="/blog/topics/">Topics</a>+ <a href="/blog/about/">About</a>+ <a href="https://munderdiffl.in">↗ Product</a>+ </div>+ <div class="nav-actions">+ <a class="btn sm" href="https://munderdiffl.in/blog/feed.xml" aria-label="RSS feed">⤵ RSS</a>+ <a class="btn sm primary" href="https://munderdiffl.in/#install">⤓ Download</a>+ </div>+</nav>++<main id="main">++<article class="t-comparisons">+ <header class="post-head wrap">+ <nav class="crumbs" aria-label="Breadcrumb">+ <a href="/blog/">Blog</a>+ <span>/</span>+ <a href="/blog/topics/comparisons/">Comparisons</a>+ </nav>+ <h1>OmniAgent Alternatives: What to Use Instead of Databricks Omnigent</h1>+ <p class="dek">OmniAgent is really Omnigent, the open source meta harness from Databricks. Alternatives checked on 14 Sep 2026, and who each one fits.</p>+ <div class="byline">+ <span class="av" aria-hidden="true">MD</span>+ <strong>Chaitanya Giri</strong>+ <span class="dot" aria-hidden="true">·</span>+ <time datetime="2026-09-14">Sep 14, 2026</time>+ <span class="dot" aria-hidden="true">·</span>+ <span>5 min read</span>+ <span class="tag kind">Comparisons</span>+ </div>+ </header>++ <div class="hero-wrap wrap"><figure class="fig fig-placeholder t-comparisons fig-hero" role="img" aria-label="A yellow cartoon character in a control tower with binoculars, guiding differently shaped robot agents towards one building"><div class="ph-art" aria-hidden="true"><span class="ph-glyph">✶</span><span class="ph-note">illustration on its way</span></div></figure></div>++ <div class="post-wrap wrap">+ <div class="prose">+ <p>The OmniAgent harness people search for is Omnigent, an Apache 2.0 meta harness from Databricks. Good alternatives: Claude Code agent teams for a lighter setup, Orca or Munder Difflin for a local desktop app, Paperclip for company style governance, and LangGraph or the OpenAI Agents SDK if you’d rather write the orchestration yourself.</p>+<p>The name is crowded. On GitHub, plexusone/omniagent is a personal assistant that replies for you across chat apps, and sbyoun/OmniAgent is a terminal for running CLI agents across servers. CallMiner also sells an unrelated customer service OmniAgent. If “harness” is a new word here, start with <a href="/blog/what-is-a-multi-agent-harness/">what a multi-agent harness is</a>. Everything below was checked on 14 Sep 2026.</p>+<h2 id="is-it-called-omniagent-or-omnigent" tabindex="-1">Is it called OmniAgent or Omnigent? <a class="anchor" href="#is-it-called-omniagent-or-omnigent" aria-hidden="true">#</a></h2>+<p>It is called Omnigent. Databricks announced it on 13 Jun 2026 in a <a href="https://www.databricks.com/blog/introducing-omnigent-meta-harness-combine-control-and-share-your-agents">post by Matei Zaharia, Kasey Uhlenhuth and Corey Zumar</a> and released it under Apache 2.0; the repo’s <code>NOTICE</code> file reads “Copyright (2026) Databricks, Inc.” A couple of explainers spell it OmniAgent, and Google autocomplete for “omniagent” suggests “omnigent databrick”, so both spellings lead to the same project. We pulled the basics from GitHub:</p>+<pre><code>$ gh api repos/omnigent-ai/omnigent --jq '.license.spdx_id, .language, .created_at'+Apache-2.0+Python+2026-06-11T12:18:13Z+$ gh api repos/omnigent-ai/omnigent/releases/latest --jq '.tag_name, .published_at'+v0.13.0+2026-09-09T14:56:32Z+</code></pre>+<p>Omnigent does not replace Claude Code or Codex; it runs them under one server. Per its <a href="https://github.com/omnigent-ai/omnigent">README</a>, it puts Claude Code, Codex, Cursor, OpenCode, Hermes, Pi and your own YAML defined agents behind one layer: mix them in a single session, ask one to review another’s work, or swap the harness by changing one line. A server stores every session and serves a web UI (<code>http://localhost:6767</code> when it runs locally), so the same session opens in your terminal, a browser, the desktop app or a phone. Teammates can watch it live, co-drive it on your machine or fork it.</p>+<figure class="fig fig-placeholder t-comparisons fig-inline" role="img" aria-label="A power strip with four different plugs, each cable leading to a different small robot"><div class="ph-art" aria-hidden="true"><span class="ph-glyph">✶</span><span class="ph-note">illustration on its way</span></div></figure>+<h2 id="why-look-for-an-omnigent-alternative" tabindex="-1">Why look for an Omnigent alternative? <a class="anchor" href="#why-look-for-an-omnigent-alternative" aria-hidden="true">#</a></h2>+<p>Four things can push you elsewhere: the setup, the server at the centre, the style of governance, or a wish to write the orchestration themselves. None of them makes Omnigent a bad tool.</p>+<p>The setup is more than one download. The README lists Python 3.12 or newer, <code>uv</code>, <code>git</code>, Node 22 with <code>npm</code> and <code>pnpm</code>, <code>tmux</code> for the native Claude and Codex wrappers, and <code>bubblewrap</code> on Linux, though the one line installer offers uv, tmux and bubblewrap. On Windows it runs “in a degraded mode”, without the native terminal wrappers or the filesystem and network sandbox. The project still wears an alpha badge, and releases went from v0.9.0 on 11 Aug to v0.13.0 on 9 Sep 2026, so expect things to move under you.</p>+<p>Everything goes through a server. Even solo, you run one on your laptop and every client attaches to it. That is what makes shared sessions possible, and it is more moving parts than one person at one desk needs. Our piece on <a href="/blog/local-first-vs-cloud-agent-sdks/">local first vs cloud agent SDKs</a> covers that trade in general.</p>+<p>Governance is written as code. Omnigent policies return allow, deny or ask, and they stack at three levels: server wide for admins, per agent in the YAML, and per session in the UI, with session rules checked first. Built-in handlers ask before file and shell tool calls, cap tool calls per session and block expensive models past a spend limit, with optional warnings before that. You can toggle the built-ins in the UI, but a rule beyond them means writing a Python handler, which is either a relief or a chore depending on who owns Python on your team. On the managed service, <a href="https://docs.databricks.com/aws/en/omnigent/">Databricks’ docs</a> (updated 11 Sep 2026) say only the built-in contextual policies are supported.</p>+<figure class="fig fig-placeholder t-comparisons fig-inline" role="img" aria-label="A yellow cartoon character with a clipboard beside a rope gate while a robot waits and a long receipt unrolls on the floor"><div class="ph-art" aria-hidden="true"><span class="ph-glyph">✶</span><span class="ph-note">illustration on its way</span></div></figure>+<h2 id="which-omnigent-alternatives-are-worth-trying" tabindex="-1">Which Omnigent alternatives are worth trying? <a class="anchor" href="#which-omnigent-alternatives-are-worth-trying" aria-hidden="true">#</a></h2>+<p>Five are worth a look, each checked on its own repo or docs on 14 Sep 2026.</p>+<div class="table-scroll">+<table>+<thead>+<tr>+<th>Alternative</th>+<th>What it is</th>+<th>Fits you if</th>+</tr>+</thead>+<tbody>+<tr>+<td>Claude Code agent teams</td>+<td>Built into Claude Code, experimental, switched on with <code>CLAUDE_CODE_EXPERIMENTAL_AGENT_TEAMS=1</code>. A lead session spawns teammates that share a task list and message each other (<a href="https://code.claude.com/docs/en/agent-teams">docs</a>).</td>+<td>You only run Claude and want nothing new installed. It will not mix in Codex or Cursor.</td>+</tr>+<tr>+<td><a href="https://github.com/stablyai/orca">Orca</a></td>+<td>MIT licensed desktop app for macOS, Windows and Linux that runs Codex, Claude Code, OpenCode or Pi side by side, each in its own git worktree, with a mobile companion.</td>+<td>You want parallel agents in a GUI and you compare their results yourself.</td>+</tr>+<tr>+<td>Munder Difflin</td>+<td>Our local desktop app, described below.</td>+<td>You want many CLIs working as one team on your own machine.</td>+</tr>+<tr>+<td>Paperclip</td>+<td>MIT licensed, self hosted Node server and React UI that runs agents as a company, with an org chart, monthly budgets per agent and approval for new hires (<a href="https://github.com/paperclipai/paperclip">repo</a>).</td>+<td>Your governance question is who reports to whom and what each agent may spend, rather than rules on every tool call.</td>+</tr>+<tr>+<td>LangGraph, OpenAI Agents SDK, Claude Agent SDK</td>+<td>Libraries you build agents on.</td>+<td>You are shipping an agent product, not supervising coding agents. See <a href="/blog/crewai-autogen-vs-a-local-agent-harness/">frameworks vs a local harness</a>.</td>+</tr>+</tbody>+</table>+</div>+<p>Munder Difflin is ours, so weigh this entry with that in mind. It is a desktop app for macOS, Windows and Linux where every agent is a real CLI in a real terminal, across twelve providers including Claude Code, Codex, Gemini CLI, Copilot and Cursor. Michael, your clone, is the orchestrator you brief. Each agent keeps durable notes in its own <code>memory.md</code> that every other agent can read. You can set a token budget for the whole floor and a cap per agent, and a circuit breaker steers an agent that loops or burns tokens too fast.</p>+<p>It is not a like for like swap. It has nothing like Omnigent’s layered policies, with rules set server wide, per agent and per session, and your laptop has to stay on because the agents run there. Auto Mode, which skips each CLI’s own permission prompts, is on by default in 0.5.2, so turn it off if you want to approve tool calls yourself. The classic office is open source under MIT, and the paid plans are on the <a href="https://munderdiffl.in/#pricing">pricing page</a>.</p>+<h2 id="when-is-omnigent-the-better-choice" tabindex="-1">When is Omnigent the better choice? <a class="anchor" href="#when-is-omnigent-the-better-choice" aria-hidden="true">#</a></h2>+<p>Omnigent is the better pick when a team needs one policy layer and one audit story across agents from several vendors. That case is strongest inside Databricks. The managed service runs the server for you, tied to your workspace’s identity provider, with model access through Foundation Model APIs and AI Gateway. The repo’s <code>docs/databricks.md</code> guide for self managed installs adds audit logs and per key cost tracking at the gateway, with traces kept in MLflow Tracing in Unity Catalog.</p>+<p>It also wins when people need to share, co-drive or fork a live session, or run agents in cloud sandboxes such as Modal or E2B with no laptop left open. A desktop app on one machine cannot stand in for that.</p>++++ <section class="faq" aria-label="Frequently asked questions">+ <h2 id="faq">FAQ</h2>++ <div class="qa">+ <p class="q">Is OmniAgent the same as Omnigent?</p>+ <p class="a">If you mean the Databricks agent harness, yes: the project is called Omnigent and lives in the omnigent-ai/omnigent repository on GitHub. OmniAgent is also the name of unrelated projects, such as a personal assistant that answers across chat apps (plexusone/omniagent) and a terminal for CLI agents on remote servers (sbyoun/OmniAgent).</p>+ </div>++ <div class="qa">+ <p class="q">Is Omnigent open source?</p>+ <p class="a">Yes. Omnigent is licensed under Apache 2.0, and its NOTICE file carries a Databricks copyright, checked on 14 Sep 2026. Databricks also runs a managed version called Omnigent on Databricks, which its docs listed as Beta on 11 Sep 2026.</p>+ </div>++ <div class="qa">+ <p class="q">Do you need Databricks to use Omnigent?</p>+ <p class="a">No. The open source release runs on your own machine or any server, and its README lists four kinds of model credentials: a vendor API key, a Claude or ChatGPT subscription through the official CLIs, a compatible gateway such as OpenRouter or Ollama, or a Databricks workspace. Databricks is one option, not a requirement.</p>+ </div>++ <div class="qa">+ <p class="q">Does Omnigent work on Windows?</p>+ <p class="a">Partly. The README says Omnigent runs natively on Windows in a degraded mode: the server, the web UI and the SDK based harnesses work, but the native Claude, Codex and Cursor terminal wrappers and the filesystem and network sandbox do not. For those it points you to Linux, macOS or WSL.</p>+ </div>++ </section>++++ <hr />+ <div class="share">+ <span class="lbl">Tags</span>+ <a class="tag" href="/blog/tags/comparisons/">Comparisons</a><a class="tag" href="/blog/tags/multi-agent/">Multi-Agent</a><a class="tag" href="/blog/tags/claude-code/">Claude Code</a><a class="tag" href="/blog/tags/tools/">Tools</a><a class="tag" href="/blog/tags/open-source/">Open Source</a>+ </div>++ </div>+++ <aside class="toc-rail" aria-label="Table of contents">+ <div class="tt">On this page</div>+ <ol>+ <li class="lvl-2"><a href="#is-it-called-omniagent-or-omnigent">Is it called OmniAgent or Omnigent?</a></li><li class="lvl-2"><a href="#why-look-for-an-omnigent-alternative">Why look for an Omnigent alternative?</a></li><li class="lvl-2"><a href="#which-omnigent-alternatives-are-worth-trying">Which Omnigent alternatives are worth trying?</a></li><li class="lvl-2"><a href="#when-is-omnigent-the-better-choice">When is Omnigent the better choice?</a></li>+ </ol>+ </aside>++ </div>++ <footer class="post-foot wrap"><div class="prevnext">+ <a class="pn prev" href="/blog/how-to-use-claude-code-plan-mode/"><span class="k">← Older</span><span class="t">How to Use Claude Code Plan Mode</span></a>+ <a class="pn next" href="/blog/herdr-alternatives/"><span class="k">Newer →</span><span class="t">Herdr Alternatives: What to Pick and Who Each One Fits</span></a>+ </div>+ <section class="related">+ <h2>Related in Comparisons</h2>+ <div class="post-grid">+ <article class="card t-comparisons">+ <a class="thumb t-comparisons" href="/blog/grok-bot-alternatives/" aria-hidden="true" tabindex="-1"><img src="/blog/assets/media/grok-bot-alternatives/hero.png" alt="" loading="lazy" decoding="async" /></a>+ <div class="body">+ <div class="meta">+ <time datetime="2026-09-14">Sep 14, 2026</time>+ <span class="dot" aria-hidden="true"></span>+ <span>5 min</span>+ </div>+ <h3><a href="/blog/grok-bot-alternatives/">Grok Bot Alternatives: Six Picks, Grouped by What You Want</a></h3>+ <p class="dek">Grok Bot runs every Bot on one shared cloud computer. Six alternatives checked on 14 Sep 2026, grouped by hosting, privacy and model choice.</p>+ <div class="foot">+ <span class="tag kind">Comparisons</span>+ <a class="more" href="/blog/grok-bot-alternatives/" aria-label="Read: Grok Bot Alternatives: Six Picks, Grouped by What You Want">Read →</a>+ </div>+ </div>+</article>+<article class="card t-comparisons">+ <a class="thumb t-comparisons" href="/blog/herdr-alternatives/" aria-hidden="true" tabindex="-1"><img src="/blog/assets/media/herdr-alternatives/hero.png" alt="" loading="lazy" decoding="async" /></a>+ <div class="body">+ <div class="meta">+ <time datetime="2026-09-14">Sep 14, 2026</time>+ <span class="dot" aria-hidden="true"></span>+ <span>5 min</span>+ </div>+ <h3><a href="/blog/herdr-alternatives/">Herdr Alternatives: What to Pick and Who Each One Fits</a></h3>+ <p class="dek">Herdr alternatives checked on 14 Sep 2026: tmux, Claude Squad, cmux, Orca, Conductor, Superset, Emdash and Munder Difflin, and who each fits.</p>+ <div class="foot">+ <span class="tag kind">Comparisons</span>+ <a class="more" href="/blog/herdr-alternatives/" aria-label="Read: Herdr Alternatives: What to Pick and Who Each One Fits">Read →</a>+ </div>+ </div>+</article>+<article class="card t-comparisons">+ <a class="thumb t-comparisons" href="/blog/codex-cli-vs-claude-code/" aria-hidden="true" tabindex="-1"><img src="/blog/assets/media/codex-cli-vs-claude-code/hero.png" alt="" loading="lazy" decoding="async" /></a>+ <div class="body">+ <div class="meta">+ <time datetime="2026-09-10">Sep 10, 2026</time>+ <span class="dot" aria-hidden="true"></span>+ <span>5 min</span>+ </div>+ <h3><a href="/blog/codex-cli-vs-claude-code/">Codex CLI vs Claude Code</a></h3>+ <p class="dek">Codex CLI and Claude Code compared firsthand: sandbox and approval flags, AGENTS.md vs CLAUDE.md, real pricing, and where each terminal agent wins.</p>+ <div class="foot">+ <span class="tag kind">Comparisons</span>+ <a class="more" href="/blog/codex-cli-vs-claude-code/" aria-label="Read: Codex CLI vs Claude Code">Read →</a>+ </div>+ </div>+</article>++ </div>+ </section>++ </footer>+</article>++</main>+<footer class="site-foot">+ <div class="wrap">+ <div class="foot-top">+ <a class="foot-brand brand" href="https://munderdiffl.in" aria-label="Munder Difflin home">+ <img class="brand-logo" src="https://munderdiffl.in/logo.png" width="1318" height="840" alt="Munder Difflin, Inc. — Multi-Agent Harness" />+ </a>+ <div class="foot-links">+ <a href="/blog/">Latest</a>+ <a href="/blog/topics/">Topics</a>+ <a href="/blog/about/">About</a>+ <a href="https://munderdiffl.in/blog/feed.xml">RSS</a>+ <a href="https://github.com/chaitanyagiri/munder-difflin">GitHub</a>+ <a href="https://munderdiffl.in">munderdiffl.in ↗</a>+ </div>+ </div>+ <div class="foot-meta">+ © 2026 Munder Difflin · Local-first · MIT-licensed ·+ Built on <a href="https://munderdiffl.in">Electron, React, Pixi.js, xterm.js & node-pty</a>.+ Run an office of agents while you sleep.+ </div>+ </div>+</footer>++<script>+ // sticky-nav border on scroll+ (function () {+ var nav = document.getElementById('nav');+ if (!nav) return;+ var onScroll = function () { nav.classList.toggle('scrolled', window.scrollY > 8); };+ onScroll(); window.addEventListener('scroll', onScroll, { passive: true });+ })();+ // YouTube click-to-load: thumbnail button → youtube-nocookie iframe+ (function () {+ document.addEventListener('click', function (e) {+ var btn = e.target.closest('.yt-load');+ if (!btn) return;+ var box = btn.closest('.yt');+ var id = box && box.getAttribute('data-yt');+ if (!id) return;+ var frame = document.createElement('iframe');+ frame.src = 'https://www.youtube-nocookie.com/embed/' + id + '?autoplay=1';+ frame.title = box.getAttribute('data-title') || 'YouTube video';+ frame.allow = 'accelerometer; autoplay; clipboard-write; encrypted-media; gyroscope; picture-in-picture; web-share';+ frame.setAttribute('allowfullscreen', '');+ box.replaceChildren(frame);+ });+ })();+</script>++</body>+</html>diff --git a/docs/blog/orca-vs-munder-difflin/index.html b/docs/blog/orca-vs-munder-difflin/index.htmlindex 3204fc81..20037e71 100644--- a/docs/blog/orca-vs-munder-difflin/index.html+++ b/docs/blog/orca-vs-munder-difflin/index.html@@ -327,50 +327,50 @@<h2>Related in Comparisons</h2><div class="post-grid"><article class="card t-comparisons">- <a class="thumb t-comparisons" href="/blog/codex-cli-vs-claude-code/" aria-hidden="true" tabindex="-1"><img src="/blog/assets/media/codex-cli-vs-claude-code/hero.png" alt="" loading="lazy" decoding="async" /></a>+ <a class="thumb t-comparisons" href="/blog/grok-bot-alternatives/" aria-hidden="true" tabindex="-1"><img src="/blog/assets/media/grok-bot-alternatives/hero.png" alt="" loading="lazy" decoding="async" /></a><div class="body"><div class="meta">- <time datetime="2026-09-10">Sep 10, 2026</time>+ <time datetime="2026-09-14">Sep 14, 2026</time><span class="dot" aria-hidden="true"></span><span>5 min</span></div>- <h3><a href="/blog/codex-cli-vs-claude-code/">Codex CLI vs Claude Code</a></h3>- <p class="dek">Codex CLI and Claude Code compared firsthand: sandbox and approval flags, AGENTS.md vs CLAUDE.md, real pricing, and where each terminal agent wins.</p>+ <h3><a href="/blog/grok-bot-alternatives/">Grok Bot Alternatives: Six Picks, Grouped by What You Want</a></h3>+ <p class="dek">Grok Bot runs every Bot on one shared cloud computer. Six alternatives checked on 14 Sep 2026, grouped by hosting, privacy and model choice.</p><div class="foot"><span class="tag kind">Comparisons</span>- <a class="more" href="/blog/codex-cli-vs-claude-code/" aria-label="Read: Codex CLI vs Claude Code">Read →</a>+ <a class="more" href="/blog/grok-bot-alternatives/" aria-label="Read: Grok Bot Alternatives: Six Picks, Grouped by What You Want">Read →</a></div></div></article><article class="card t-comparisons">- <a class="thumb t-comparisons" href="/blog/qm-vs-munder-difflin/" aria-hidden="true" tabindex="-1"><img src="/blog/assets/media/qm-vs-munder-difflin/hero.png" alt="" loading="lazy" decoding="async" /></a>+ <a class="thumb t-comparisons" href="/blog/herdr-alternatives/" aria-hidden="true" tabindex="-1"><img src="/blog/assets/media/herdr-alternatives/hero.png" alt="" loading="lazy" decoding="async" /></a><div class="body"><div class="meta">- <time datetime="2026-08-06">Aug 6, 2026</time>+ <time datetime="2026-09-14">Sep 14, 2026</time><span class="dot" aria-hidden="true"></span>- <span>4 min</span>+ <span>5 min</span></div>- <h3><a href="/blog/qm-vs-munder-difflin/">qm vs Munder Difflin: YC's Multiplayer Harness or an Office of Your Clones?</a></h3>- <p class="dek">An honest September 2026 comparison of YC's qm and Munder Difflin. qm is a multiplayer agent harness a company deploys for Slack and the web. Munder Difflin runs an office of your clones on your own machine, with Teams to connect them.</p>+ <h3><a href="/blog/herdr-alternatives/">Herdr Alternatives: What to Pick and Who Each One Fits</a></h3>+ <p class="dek">Herdr alternatives checked on 14 Sep 2026: tmux, Claude Squad, cmux, Orca, Conductor, Superset, Emdash and Munder Difflin, and who each fits.</p><div class="foot"><span class="tag kind">Comparisons</span>- <a class="more" href="/blog/qm-vs-munder-difflin/" aria-label="Read: qm vs Munder Difflin: YC's Multiplayer Harness or an Office of Your Clones?">Read →</a>+ <a class="more" href="/blog/herdr-alternatives/" aria-label="Read: Herdr Alternatives: What to Pick and Who Each One Fits">Read →</a></div></div></article><article class="card t-comparisons">- <a class="thumb t-comparisons" href="/blog/crewai-autogen-vs-a-local-agent-harness/" aria-hidden="true" tabindex="-1"><img src="/blog/assets/media/crewai-autogen-vs-a-local-agent-harness/hero.png" alt="" loading="lazy" decoding="async" /></a>+ <a class="thumb t-comparisons" href="/blog/omniagent-alternatives/" aria-hidden="true" tabindex="-1"><span class="thumb-ph"><em class="ph-glyph" aria-hidden="true">✶</em><span>COMPARISONS</span></span></a><div class="body"><div class="meta">- <time datetime="2026-07-03">Jul 3, 2026</time>+ <time datetime="2026-09-14">Sep 14, 2026</time><span class="dot" aria-hidden="true"></span><span>5 min</span></div>- <h3><a href="/blog/crewai-autogen-vs-a-local-agent-harness/">CrewAI and AutoGen vs a Local Agent Harness: Framework or App?</a></h3>- <p class="dek">CrewAI, AutoGen (now Microsoft Agent Framework), and LangGraph are frameworks — Python you write to build your own agent system. A multi-agent harness is an app you download that runs a team on your repos today. Here's how to tell which one you actually need.</p>+ <h3><a href="/blog/omniagent-alternatives/">OmniAgent Alternatives: What to Use Instead of Databricks Omnigent</a></h3>+ <p class="dek">OmniAgent is really Omnigent, the open source meta harness from Databricks. Alternatives checked on 14 Sep 2026, and who each one fits.</p><div class="foot"><span class="tag kind">Comparisons</span>- <a class="more" href="/blog/crewai-autogen-vs-a-local-agent-harness/" aria-label="Read: CrewAI and AutoGen vs a Local Agent Harness: Framework or App?">Read →</a>+ <a class="more" href="/blog/omniagent-alternatives/" aria-label="Read: OmniAgent Alternatives: What to Use Instead of Databricks Omnigent">Read →</a></div></div></article>diff --git a/docs/blog/prompt-caching-for-ai-agents/index.html b/docs/blog/prompt-caching-for-ai-agents/index.htmlindex d82f0b74..676490ec 100644--- a/docs/blog/prompt-caching-for-ai-agents/index.html+++ b/docs/blog/prompt-caching-for-ai-agents/index.html@@ -339,50 +339,50 @@ that doesn’t waste your tokens; it’s free and open source.</p><h2>Related in Guides</h2><div class="post-grid"><article class="card t-guides">- <a class="thumb t-guides" href="/blog/how-to-use-claude-code-plan-mode/" aria-hidden="true" tabindex="-1"><img src="/blog/assets/media/how-to-use-claude-code-plan-mode/hero.png" alt="" loading="lazy" decoding="async" /></a>+ <a class="thumb t-guides" href="/blog/claude-code-max-plan-tips/" aria-hidden="true" tabindex="-1"><img src="/blog/assets/media/claude-code-max-plan-tips/hero.png" alt="" loading="lazy" decoding="async" /></a><div class="body"><div class="meta">- <time datetime="2026-09-11">Sep 11, 2026</time>+ <time datetime="2026-09-14">Sep 14, 2026</time><span class="dot" aria-hidden="true"></span><span>5 min</span></div>- <h3><a href="/blog/how-to-use-claude-code-plan-mode/">How to Use Claude Code Plan Mode</a></h3>- <p class="dek">How Claude Code's plan mode works: turning it on, what it blocks, what a real headless plan mode run prints, and how to leave it.</p>+ <h3><a href="/blog/claude-code-max-plan-tips/">How to Get the Most Out of Your Claude Code Max Plan</a></h3>+ <p class="dek">Stretch a Claude Code Max plan: model choice, context hygiene, prompt caching, subagents and unattended runs, checked against Anthropic's own pages.</p><div class="foot"><span class="tag kind">Guides</span>- <a class="more" href="/blog/how-to-use-claude-code-plan-mode/" aria-label="Read: How to Use Claude Code Plan Mode">Read →</a>+ <a class="more" href="/blog/claude-code-max-plan-tips/" aria-label="Read: How to Get the Most Out of Your Claude Code Max Plan">Read →</a></div></div></article><article class="card t-guides">- <a class="thumb t-guides" href="/blog/how-to-add-an-mcp-server-to-claude-code/" aria-hidden="true" tabindex="-1"><img src="/blog/assets/media/how-to-add-an-mcp-server-to-claude-code/hero.png" alt="" loading="lazy" decoding="async" /></a>+ <a class="thumb t-guides" href="/blog/codex-max-plan-tips/" aria-hidden="true" tabindex="-1"><img src="/blog/assets/media/codex-max-plan-tips/hero.png" alt="" loading="lazy" decoding="async" /></a><div class="body"><div class="meta">- <time datetime="2026-09-10">Sep 10, 2026</time>+ <time datetime="2026-09-14">Sep 14, 2026</time><span class="dot" aria-hidden="true"></span><span>5 min</span></div>- <h3><a href="/blog/how-to-add-an-mcp-server-to-claude-code/">How to Add an MCP Server to Claude Code</a></h3>- <p class="dek">The claude mcp add command, its scope flag, editing .mcp.json by hand, and how Munder Difflin's Capabilities screen grants an MCP server to one agent at a time.</p>+ <h3><a href="/blog/codex-max-plan-tips/">How to Make the Most of Your Codex Max Plan</a></h3>+ <p class="dek">There is no Codex Max plan. What ChatGPT Pro 5x and 20x give you in Codex, how the weekly limit works, and how to stretch it.</p><div class="foot"><span class="tag kind">Guides</span>- <a class="more" href="/blog/how-to-add-an-mcp-server-to-claude-code/" aria-label="Read: How to Add an MCP Server to Claude Code">Read →</a>+ <a class="more" href="/blog/codex-max-plan-tips/" aria-label="Read: How to Make the Most of Your Codex Max Plan">Read →</a></div></div></article><article class="card t-guides">- <a class="thumb t-guides" href="/blog/command-center-guide/" aria-hidden="true" tabindex="-1"><img src="/blog/assets/media/command-center-guide/hero.png" alt="" loading="lazy" decoding="async" /></a>+ <a class="thumb t-guides" href="/blog/how-to-use-claude-code-plan-mode/" aria-hidden="true" tabindex="-1"><img src="/blog/assets/media/how-to-use-claude-code-plan-mode/hero.png" alt="" loading="lazy" decoding="async" /></a><div class="body"><div class="meta">- <time datetime="2026-07-03">Jul 3, 2026</time>+ <time datetime="2026-09-11">Sep 11, 2026</time><span class="dot" aria-hidden="true"></span>- <span>4 min</span>+ <span>5 min</span></div>- <h3><a href="/blog/command-center-guide/">The Command Center: Kanban, Fleet and Budgets in One Place</a></h3>- <p class="dek">A guide to Munder Difflin's Command Center in 0.5.2: the kanban with task dependencies, the ask me tab, triggers, memory, live token use against each agent's budget, and when to watch the board instead of the floor.</p>+ <h3><a href="/blog/how-to-use-claude-code-plan-mode/">How to Use Claude Code Plan Mode</a></h3>+ <p class="dek">How Claude Code's plan mode works: turning it on, what it blocks, what a real headless plan mode run prints, and how to leave it.</p><div class="foot"><span class="tag kind">Guides</span>- <a class="more" href="/blog/command-center-guide/" aria-label="Read: The Command Center: Kanban, Fleet and Budgets in One Place">Read →</a>+ <a class="more" href="/blog/how-to-use-claude-code-plan-mode/" aria-label="Read: How to Use Claude Code Plan Mode">Read →</a></div></div></article>diff --git a/docs/blog/qm-vs-munder-difflin/index.html b/docs/blog/qm-vs-munder-difflin/index.htmlindex 24f8012e..d8c2c213 100644--- a/docs/blog/qm-vs-munder-difflin/index.html+++ b/docs/blog/qm-vs-munder-difflin/index.html@@ -338,50 +338,50 @@ where each person watches and steers their own agents. They do not compete for t<h2>Related in Comparisons</h2><div class="post-grid"><article class="card t-comparisons">- <a class="thumb t-comparisons" href="/blog/codex-cli-vs-claude-code/" aria-hidden="true" tabindex="-1"><img src="/blog/assets/media/codex-cli-vs-claude-code/hero.png" alt="" loading="lazy" decoding="async" /></a>+ <a class="thumb t-comparisons" href="/blog/grok-bot-alternatives/" aria-hidden="true" tabindex="-1"><img src="/blog/assets/media/grok-bot-alternatives/hero.png" alt="" loading="lazy" decoding="async" /></a><div class="body"><div class="meta">- <time datetime="2026-09-10">Sep 10, 2026</time>+ <time datetime="2026-09-14">Sep 14, 2026</time><span class="dot" aria-hidden="true"></span><span>5 min</span></div>- <h3><a href="/blog/codex-cli-vs-claude-code/">Codex CLI vs Claude Code</a></h3>- <p class="dek">Codex CLI and Claude Code compared firsthand: sandbox and approval flags, AGENTS.md vs CLAUDE.md, real pricing, and where each terminal agent wins.</p>+ <h3><a href="/blog/grok-bot-alternatives/">Grok Bot Alternatives: Six Picks, Grouped by What You Want</a></h3>+ <p class="dek">Grok Bot runs every Bot on one shared cloud computer. Six alternatives checked on 14 Sep 2026, grouped by hosting, privacy and model choice.</p><div class="foot"><span class="tag kind">Comparisons</span>- <a class="more" href="/blog/codex-cli-vs-claude-code/" aria-label="Read: Codex CLI vs Claude Code">Read →</a>+ <a class="more" href="/blog/grok-bot-alternatives/" aria-label="Read: Grok Bot Alternatives: Six Picks, Grouped by What You Want">Read →</a></div></div></article><article class="card t-comparisons">- <a class="thumb t-comparisons" href="/blog/crewai-autogen-vs-a-local-agent-harness/" aria-hidden="true" tabindex="-1"><img src="/blog/assets/media/crewai-autogen-vs-a-local-agent-harness/hero.png" alt="" loading="lazy" decoding="async" /></a>+ <a class="thumb t-comparisons" href="/blog/herdr-alternatives/" aria-hidden="true" tabindex="-1"><img src="/blog/assets/media/herdr-alternatives/hero.png" alt="" loading="lazy" decoding="async" /></a><div class="body"><div class="meta">- <time datetime="2026-07-03">Jul 3, 2026</time>+ <time datetime="2026-09-14">Sep 14, 2026</time><span class="dot" aria-hidden="true"></span><span>5 min</span></div>- <h3><a href="/blog/crewai-autogen-vs-a-local-agent-harness/">CrewAI and AutoGen vs a Local Agent Harness: Framework or App?</a></h3>- <p class="dek">CrewAI, AutoGen (now Microsoft Agent Framework), and LangGraph are frameworks — Python you write to build your own agent system. A multi-agent harness is an app you download that runs a team on your repos today. Here's how to tell which one you actually need.</p>+ <h3><a href="/blog/herdr-alternatives/">Herdr Alternatives: What to Pick and Who Each One Fits</a></h3>+ <p class="dek">Herdr alternatives checked on 14 Sep 2026: tmux, Claude Squad, cmux, Orca, Conductor, Superset, Emdash and Munder Difflin, and who each fits.</p><div class="foot"><span class="tag kind">Comparisons</span>- <a class="more" href="/blog/crewai-autogen-vs-a-local-agent-harness/" aria-label="Read: CrewAI and AutoGen vs a Local Agent Harness: Framework or App?">Read →</a>+ <a class="more" href="/blog/herdr-alternatives/" aria-label="Read: Herdr Alternatives: What to Pick and Who Each One Fits">Read →</a></div></div></article><article class="card t-comparisons">- <a class="thumb t-comparisons" href="/blog/github-copilot-cli-vs-claude-code-for-hive-work/" aria-hidden="true" tabindex="-1"><img src="/blog/assets/media/github-copilot-cli-vs-claude-code-for-hive-work/hero.png" alt="" loading="lazy" decoding="async" /></a>+ <a class="thumb t-comparisons" href="/blog/omniagent-alternatives/" aria-hidden="true" tabindex="-1"><span class="thumb-ph"><em class="ph-glyph" aria-hidden="true">✶</em><span>COMPARISONS</span></span></a><div class="body"><div class="meta">- <time datetime="2026-07-03">Jul 3, 2026</time>+ <time datetime="2026-09-14">Sep 14, 2026</time><span class="dot" aria-hidden="true"></span><span>5 min</span></div>- <h3><a href="/blog/github-copilot-cli-vs-claude-code-for-hive-work/">GitHub Copilot CLI vs Claude Code as Hive Workers</a></h3>- <p class="dek">How GitHub Copilot CLI and Claude Code behave as agent engines inside a multi-agent harness: hooks, inbox mail, orchestration, session lifecycle — and why the right answer is to run both.</p>+ <h3><a href="/blog/omniagent-alternatives/">OmniAgent Alternatives: What to Use Instead of Databricks Omnigent</a></h3>+ <p class="dek">OmniAgent is really Omnigent, the open source meta harness from Databricks. Alternatives checked on 14 Sep 2026, and who each one fits.</p><div class="foot"><span class="tag kind">Comparisons</span>- <a class="more" href="/blog/github-copilot-cli-vs-claude-code-for-hive-work/" aria-label="Read: GitHub Copilot CLI vs Claude Code as Hive Workers">Read →</a>+ <a class="more" href="/blog/omniagent-alternatives/" aria-label="Read: OmniAgent Alternatives: What to Use Instead of Databricks Omnigent">Read →</a></div></div></article>diff --git a/docs/blog/run-a-mixed-engine-office/index.html b/docs/blog/run-a-mixed-engine-office/index.htmlindex 7f193194..b7b61b09 100644--- a/docs/blog/run-a-mixed-engine-office/index.html+++ b/docs/blog/run-a-mixed-engine-office/index.html@@ -267,50 +267,50 @@<h2>Related in Guides</h2><div class="post-grid"><article class="card t-guides">- <a class="thumb t-guides" href="/blog/how-to-use-claude-code-plan-mode/" aria-hidden="true" tabindex="-1"><img src="/blog/assets/media/how-to-use-claude-code-plan-mode/hero.png" alt="" loading="lazy" decoding="async" /></a>+ <a class="thumb t-guides" href="/blog/claude-code-max-plan-tips/" aria-hidden="true" tabindex="-1"><img src="/blog/assets/media/claude-code-max-plan-tips/hero.png" alt="" loading="lazy" decoding="async" /></a><div class="body"><div class="meta">- <time datetime="2026-09-11">Sep 11, 2026</time>+ <time datetime="2026-09-14">Sep 14, 2026</time><span class="dot" aria-hidden="true"></span><span>5 min</span></div>- <h3><a href="/blog/how-to-use-claude-code-plan-mode/">How to Use Claude Code Plan Mode</a></h3>- <p class="dek">How Claude Code's plan mode works: turning it on, what it blocks, what a real headless plan mode run prints, and how to leave it.</p>+ <h3><a href="/blog/claude-code-max-plan-tips/">How to Get the Most Out of Your Claude Code Max Plan</a></h3>+ <p class="dek">Stretch a Claude Code Max plan: model choice, context hygiene, prompt caching, subagents and unattended runs, checked against Anthropic's own pages.</p><div class="foot"><span class="tag kind">Guides</span>- <a class="more" href="/blog/how-to-use-claude-code-plan-mode/" aria-label="Read: How to Use Claude Code Plan Mode">Read →</a>+ <a class="more" href="/blog/claude-code-max-plan-tips/" aria-label="Read: How to Get the Most Out of Your Claude Code Max Plan">Read →</a></div></div></article><article class="card t-guides">- <a class="thumb t-guides" href="/blog/how-to-add-an-mcp-server-to-claude-code/" aria-hidden="true" tabindex="-1"><img src="/blog/assets/media/how-to-add-an-mcp-server-to-claude-code/hero.png" alt="" loading="lazy" decoding="async" /></a>+ <a class="thumb t-guides" href="/blog/codex-max-plan-tips/" aria-hidden="true" tabindex="-1"><img src="/blog/assets/media/codex-max-plan-tips/hero.png" alt="" loading="lazy" decoding="async" /></a><div class="body"><div class="meta">- <time datetime="2026-09-10">Sep 10, 2026</time>+ <time datetime="2026-09-14">Sep 14, 2026</time><span class="dot" aria-hidden="true"></span><span>5 min</span></div>- <h3><a href="/blog/how-to-add-an-mcp-server-to-claude-code/">How to Add an MCP Server to Claude Code</a></h3>- <p class="dek">The claude mcp add command, its scope flag, editing .mcp.json by hand, and how Munder Difflin's Capabilities screen grants an MCP server to one agent at a time.</p>+ <h3><a href="/blog/codex-max-plan-tips/">How to Make the Most of Your Codex Max Plan</a></h3>+ <p class="dek">There is no Codex Max plan. What ChatGPT Pro 5x and 20x give you in Codex, how the weekly limit works, and how to stretch it.</p><div class="foot"><span class="tag kind">Guides</span>- <a class="more" href="/blog/how-to-add-an-mcp-server-to-claude-code/" aria-label="Read: How to Add an MCP Server to Claude Code">Read →</a>+ <a class="more" href="/blog/codex-max-plan-tips/" aria-label="Read: How to Make the Most of Your Codex Max Plan">Read →</a></div></div></article><article class="card t-guides">- <a class="thumb t-guides" href="/blog/command-center-guide/" aria-hidden="true" tabindex="-1"><img src="/blog/assets/media/command-center-guide/hero.png" alt="" loading="lazy" decoding="async" /></a>+ <a class="thumb t-guides" href="/blog/how-to-use-claude-code-plan-mode/" aria-hidden="true" tabindex="-1"><img src="/blog/assets/media/how-to-use-claude-code-plan-mode/hero.png" alt="" loading="lazy" decoding="async" /></a><div class="body"><div class="meta">- <time datetime="2026-07-03">Jul 3, 2026</time>+ <time datetime="2026-09-11">Sep 11, 2026</time><span class="dot" aria-hidden="true"></span>- <span>4 min</span>+ <span>5 min</span></div>- <h3><a href="/blog/command-center-guide/">The Command Center: Kanban, Fleet and Budgets in One Place</a></h3>- <p class="dek">A guide to Munder Difflin's Command Center in 0.5.2: the kanban with task dependencies, the ask me tab, triggers, memory, live token use against each agent's budget, and when to watch the board instead of the floor.</p>+ <h3><a href="/blog/how-to-use-claude-code-plan-mode/">How to Use Claude Code Plan Mode</a></h3>+ <p class="dek">How Claude Code's plan mode works: turning it on, what it blocks, what a real headless plan mode run prints, and how to leave it.</p><div class="foot"><span class="tag kind">Guides</span>- <a class="more" href="/blog/command-center-guide/" aria-label="Read: The Command Center: Kanban, Fleet and Budgets in One Place">Read →</a>+ <a class="more" href="/blog/how-to-use-claude-code-plan-mode/" aria-label="Read: How to Use Claude Code Plan Mode">Read →</a></div></div></article>diff --git a/docs/blog/run-ai-agent-hive-from-slack-setup/index.html b/docs/blog/run-ai-agent-hive-from-slack-setup/index.htmlindex 8c6e242b..2d600999 100644--- a/docs/blog/run-ai-agent-hive-from-slack-setup/index.html+++ b/docs/blog/run-ai-agent-hive-from-slack-setup/index.html@@ -365,50 +365,50 @@ it’s free and open source.</p><h2>Related in Guides</h2><div class="post-grid"><article class="card t-guides">- <a class="thumb t-guides" href="/blog/how-to-use-claude-code-plan-mode/" aria-hidden="true" tabindex="-1"><img src="/blog/assets/media/how-to-use-claude-code-plan-mode/hero.png" alt="" loading="lazy" decoding="async" /></a>+ <a class="thumb t-guides" href="/blog/claude-code-max-plan-tips/" aria-hidden="true" tabindex="-1"><img src="/blog/assets/media/claude-code-max-plan-tips/hero.png" alt="" loading="lazy" decoding="async" /></a><div class="body"><div class="meta">- <time datetime="2026-09-11">Sep 11, 2026</time>+ <time datetime="2026-09-14">Sep 14, 2026</time><span class="dot" aria-hidden="true"></span><span>5 min</span></div>- <h3><a href="/blog/how-to-use-claude-code-plan-mode/">How to Use Claude Code Plan Mode</a></h3>- <p class="dek">How Claude Code's plan mode works: turning it on, what it blocks, what a real headless plan mode run prints, and how to leave it.</p>+ <h3><a href="/blog/claude-code-max-plan-tips/">How to Get the Most Out of Your Claude Code Max Plan</a></h3>+ <p class="dek">Stretch a Claude Code Max plan: model choice, context hygiene, prompt caching, subagents and unattended runs, checked against Anthropic's own pages.</p><div class="foot"><span class="tag kind">Guides</span>- <a class="more" href="/blog/how-to-use-claude-code-plan-mode/" aria-label="Read: How to Use Claude Code Plan Mode">Read →</a>+ <a class="more" href="/blog/claude-code-max-plan-tips/" aria-label="Read: How to Get the Most Out of Your Claude Code Max Plan">Read →</a></div></div></article><article class="card t-guides">- <a class="thumb t-guides" href="/blog/how-to-add-an-mcp-server-to-claude-code/" aria-hidden="true" tabindex="-1"><img src="/blog/assets/media/how-to-add-an-mcp-server-to-claude-code/hero.png" alt="" loading="lazy" decoding="async" /></a>+ <a class="thumb t-guides" href="/blog/codex-max-plan-tips/" aria-hidden="true" tabindex="-1"><img src="/blog/assets/media/codex-max-plan-tips/hero.png" alt="" loading="lazy" decoding="async" /></a><div class="body"><div class="meta">- <time datetime="2026-09-10">Sep 10, 2026</time>+ <time datetime="2026-09-14">Sep 14, 2026</time><span class="dot" aria-hidden="true"></span><span>5 min</span></div>- <h3><a href="/blog/how-to-add-an-mcp-server-to-claude-code/">How to Add an MCP Server to Claude Code</a></h3>- <p class="dek">The claude mcp add command, its scope flag, editing .mcp.json by hand, and how Munder Difflin's Capabilities screen grants an MCP server to one agent at a time.</p>+ <h3><a href="/blog/codex-max-plan-tips/">How to Make the Most of Your Codex Max Plan</a></h3>+ <p class="dek">There is no Codex Max plan. What ChatGPT Pro 5x and 20x give you in Codex, how the weekly limit works, and how to stretch it.</p><div class="foot"><span class="tag kind">Guides</span>- <a class="more" href="/blog/how-to-add-an-mcp-server-to-claude-code/" aria-label="Read: How to Add an MCP Server to Claude Code">Read →</a>+ <a class="more" href="/blog/codex-max-plan-tips/" aria-label="Read: How to Make the Most of Your Codex Max Plan">Read →</a></div></div></article><article class="card t-guides">- <a class="thumb t-guides" href="/blog/command-center-guide/" aria-hidden="true" tabindex="-1"><img src="/blog/assets/media/command-center-guide/hero.png" alt="" loading="lazy" decoding="async" /></a>+ <a class="thumb t-guides" href="/blog/how-to-use-claude-code-plan-mode/" aria-hidden="true" tabindex="-1"><img src="/blog/assets/media/how-to-use-claude-code-plan-mode/hero.png" alt="" loading="lazy" decoding="async" /></a><div class="body"><div class="meta">- <time datetime="2026-07-03">Jul 3, 2026</time>+ <time datetime="2026-09-11">Sep 11, 2026</time><span class="dot" aria-hidden="true"></span>- <span>4 min</span>+ <span>5 min</span></div>- <h3><a href="/blog/command-center-guide/">The Command Center: Kanban, Fleet and Budgets in One Place</a></h3>- <p class="dek">A guide to Munder Difflin's Command Center in 0.5.2: the kanban with task dependencies, the ask me tab, triggers, memory, live token use against each agent's budget, and when to watch the board instead of the floor.</p>+ <h3><a href="/blog/how-to-use-claude-code-plan-mode/">How to Use Claude Code Plan Mode</a></h3>+ <p class="dek">How Claude Code's plan mode works: turning it on, what it blocks, what a real headless plan mode run prints, and how to leave it.</p><div class="foot"><span class="tag kind">Guides</span>- <a class="more" href="/blog/command-center-guide/" aria-label="Read: The Command Center: Kanban, Fleet and Budgets in One Place">Read →</a>+ <a class="more" href="/blog/how-to-use-claude-code-plan-mode/" aria-label="Read: How to Use Claude Code Plan Mode">Read →</a></div></div></article>diff --git a/docs/blog/run-munder-difflin-on-a-mac-mini/index.html b/docs/blog/run-munder-difflin-on-a-mac-mini/index.htmlindex 07c91587..9409f530 100644--- a/docs/blog/run-munder-difflin-on-a-mac-mini/index.html+++ b/docs/blog/run-munder-difflin-on-a-mac-mini/index.html@@ -400,50 +400,50 @@ machine awake while at least one agent is running.</li><h2>Related in Guides</h2><div class="post-grid"><article class="card t-guides">- <a class="thumb t-guides" href="/blog/how-to-use-claude-code-plan-mode/" aria-hidden="true" tabindex="-1"><img src="/blog/assets/media/how-to-use-claude-code-plan-mode/hero.png" alt="" loading="lazy" decoding="async" /></a>+ <a class="thumb t-guides" href="/blog/claude-code-max-plan-tips/" aria-hidden="true" tabindex="-1"><img src="/blog/assets/media/claude-code-max-plan-tips/hero.png" alt="" loading="lazy" decoding="async" /></a><div class="body"><div class="meta">- <time datetime="2026-09-11">Sep 11, 2026</time>+ <time datetime="2026-09-14">Sep 14, 2026</time><span class="dot" aria-hidden="true"></span><span>5 min</span></div>- <h3><a href="/blog/how-to-use-claude-code-plan-mode/">How to Use Claude Code Plan Mode</a></h3>- <p class="dek">How Claude Code's plan mode works: turning it on, what it blocks, what a real headless plan mode run prints, and how to leave it.</p>+ <h3><a href="/blog/claude-code-max-plan-tips/">How to Get the Most Out of Your Claude Code Max Plan</a></h3>+ <p class="dek">Stretch a Claude Code Max plan: model choice, context hygiene, prompt caching, subagents and unattended runs, checked against Anthropic's own pages.</p><div class="foot"><span class="tag kind">Guides</span>- <a class="more" href="/blog/how-to-use-claude-code-plan-mode/" aria-label="Read: How to Use Claude Code Plan Mode">Read →</a>+ <a class="more" href="/blog/claude-code-max-plan-tips/" aria-label="Read: How to Get the Most Out of Your Claude Code Max Plan">Read →</a></div></div></article><article class="card t-guides">- <a class="thumb t-guides" href="/blog/how-to-add-an-mcp-server-to-claude-code/" aria-hidden="true" tabindex="-1"><img src="/blog/assets/media/how-to-add-an-mcp-server-to-claude-code/hero.png" alt="" loading="lazy" decoding="async" /></a>+ <a class="thumb t-guides" href="/blog/codex-max-plan-tips/" aria-hidden="true" tabindex="-1"><img src="/blog/assets/media/codex-max-plan-tips/hero.png" alt="" loading="lazy" decoding="async" /></a><div class="body"><div class="meta">- <time datetime="2026-09-10">Sep 10, 2026</time>+ <time datetime="2026-09-14">Sep 14, 2026</time><span class="dot" aria-hidden="true"></span><span>5 min</span></div>- <h3><a href="/blog/how-to-add-an-mcp-server-to-claude-code/">How to Add an MCP Server to Claude Code</a></h3>- <p class="dek">The claude mcp add command, its scope flag, editing .mcp.json by hand, and how Munder Difflin's Capabilities screen grants an MCP server to one agent at a time.</p>+ <h3><a href="/blog/codex-max-plan-tips/">How to Make the Most of Your Codex Max Plan</a></h3>+ <p class="dek">There is no Codex Max plan. What ChatGPT Pro 5x and 20x give you in Codex, how the weekly limit works, and how to stretch it.</p><div class="foot"><span class="tag kind">Guides</span>- <a class="more" href="/blog/how-to-add-an-mcp-server-to-claude-code/" aria-label="Read: How to Add an MCP Server to Claude Code">Read →</a>+ <a class="more" href="/blog/codex-max-plan-tips/" aria-label="Read: How to Make the Most of Your Codex Max Plan">Read →</a></div></div></article><article class="card t-guides">- <a class="thumb t-guides" href="/blog/command-center-guide/" aria-hidden="true" tabindex="-1"><img src="/blog/assets/media/command-center-guide/hero.png" alt="" loading="lazy" decoding="async" /></a>+ <a class="thumb t-guides" href="/blog/how-to-use-claude-code-plan-mode/" aria-hidden="true" tabindex="-1"><img src="/blog/assets/media/how-to-use-claude-code-plan-mode/hero.png" alt="" loading="lazy" decoding="async" /></a><div class="body"><div class="meta">- <time datetime="2026-07-03">Jul 3, 2026</time>+ <time datetime="2026-09-11">Sep 11, 2026</time><span class="dot" aria-hidden="true"></span>- <span>4 min</span>+ <span>5 min</span></div>- <h3><a href="/blog/command-center-guide/">The Command Center: Kanban, Fleet and Budgets in One Place</a></h3>- <p class="dek">A guide to Munder Difflin's Command Center in 0.5.2: the kanban with task dependencies, the ask me tab, triggers, memory, live token use against each agent's budget, and when to watch the board instead of the floor.</p>+ <h3><a href="/blog/how-to-use-claude-code-plan-mode/">How to Use Claude Code Plan Mode</a></h3>+ <p class="dek">How Claude Code's plan mode works: turning it on, what it blocks, what a real headless plan mode run prints, and how to leave it.</p><div class="foot"><span class="tag kind">Guides</span>- <a class="more" href="/blog/command-center-guide/" aria-label="Read: The Command Center: Kanban, Fleet and Budgets in One Place">Read →</a>+ <a class="more" href="/blog/how-to-use-claude-code-plan-mode/" aria-label="Read: How to Use Claude Code Plan Mode">Read →</a></div></div></article>diff --git a/docs/blog/run-munder-difflin-on-open-models/index.html b/docs/blog/run-munder-difflin-on-open-models/index.htmlindex 00189a71..35f1e898 100644--- a/docs/blog/run-munder-difflin-on-open-models/index.html+++ b/docs/blog/run-munder-difflin-on-open-models/index.html@@ -515,50 +515,50 @@ and want the sizing walkthrough? Read the <a href="/blog/run-munder-difflin-on-a<h2>Related in Guides</h2><div class="post-grid"><article class="card t-guides">- <a class="thumb t-guides" href="/blog/how-to-use-claude-code-plan-mode/" aria-hidden="true" tabindex="-1"><img src="/blog/assets/media/how-to-use-claude-code-plan-mode/hero.png" alt="" loading="lazy" decoding="async" /></a>+ <a class="thumb t-guides" href="/blog/claude-code-max-plan-tips/" aria-hidden="true" tabindex="-1"><img src="/blog/assets/media/claude-code-max-plan-tips/hero.png" alt="" loading="lazy" decoding="async" /></a><div class="body"><div class="meta">- <time datetime="2026-09-11">Sep 11, 2026</time>+ <time datetime="2026-09-14">Sep 14, 2026</time><span class="dot" aria-hidden="true"></span><span>5 min</span></div>- <h3><a href="/blog/how-to-use-claude-code-plan-mode/">How to Use Claude Code Plan Mode</a></h3>- <p class="dek">How Claude Code's plan mode works: turning it on, what it blocks, what a real headless plan mode run prints, and how to leave it.</p>+ <h3><a href="/blog/claude-code-max-plan-tips/">How to Get the Most Out of Your Claude Code Max Plan</a></h3>+ <p class="dek">Stretch a Claude Code Max plan: model choice, context hygiene, prompt caching, subagents and unattended runs, checked against Anthropic's own pages.</p><div class="foot"><span class="tag kind">Guides</span>- <a class="more" href="/blog/how-to-use-claude-code-plan-mode/" aria-label="Read: How to Use Claude Code Plan Mode">Read →</a>+ <a class="more" href="/blog/claude-code-max-plan-tips/" aria-label="Read: How to Get the Most Out of Your Claude Code Max Plan">Read →</a></div></div></article><article class="card t-guides">- <a class="thumb t-guides" href="/blog/how-to-add-an-mcp-server-to-claude-code/" aria-hidden="true" tabindex="-1"><img src="/blog/assets/media/how-to-add-an-mcp-server-to-claude-code/hero.png" alt="" loading="lazy" decoding="async" /></a>+ <a class="thumb t-guides" href="/blog/codex-max-plan-tips/" aria-hidden="true" tabindex="-1"><img src="/blog/assets/media/codex-max-plan-tips/hero.png" alt="" loading="lazy" decoding="async" /></a><div class="body"><div class="meta">- <time datetime="2026-09-10">Sep 10, 2026</time>+ <time datetime="2026-09-14">Sep 14, 2026</time><span class="dot" aria-hidden="true"></span><span>5 min</span></div>- <h3><a href="/blog/how-to-add-an-mcp-server-to-claude-code/">How to Add an MCP Server to Claude Code</a></h3>- <p class="dek">The claude mcp add command, its scope flag, editing .mcp.json by hand, and how Munder Difflin's Capabilities screen grants an MCP server to one agent at a time.</p>+ <h3><a href="/blog/codex-max-plan-tips/">How to Make the Most of Your Codex Max Plan</a></h3>+ <p class="dek">There is no Codex Max plan. What ChatGPT Pro 5x and 20x give you in Codex, how the weekly limit works, and how to stretch it.</p><div class="foot"><span class="tag kind">Guides</span>- <a class="more" href="/blog/how-to-add-an-mcp-server-to-claude-code/" aria-label="Read: How to Add an MCP Server to Claude Code">Read →</a>+ <a class="more" href="/blog/codex-max-plan-tips/" aria-label="Read: How to Make the Most of Your Codex Max Plan">Read →</a></div></div></article><article class="card t-guides">- <a class="thumb t-guides" href="/blog/command-center-guide/" aria-hidden="true" tabindex="-1"><img src="/blog/assets/media/command-center-guide/hero.png" alt="" loading="lazy" decoding="async" /></a>+ <a class="thumb t-guides" href="/blog/how-to-use-claude-code-plan-mode/" aria-hidden="true" tabindex="-1"><img src="/blog/assets/media/how-to-use-claude-code-plan-mode/hero.png" alt="" loading="lazy" decoding="async" /></a><div class="body"><div class="meta">- <time datetime="2026-07-03">Jul 3, 2026</time>+ <time datetime="2026-09-11">Sep 11, 2026</time><span class="dot" aria-hidden="true"></span>- <span>4 min</span>+ <span>5 min</span></div>- <h3><a href="/blog/command-center-guide/">The Command Center: Kanban, Fleet and Budgets in One Place</a></h3>- <p class="dek">A guide to Munder Difflin's Command Center in 0.5.2: the kanban with task dependencies, the ask me tab, triggers, memory, live token use against each agent's budget, and when to watch the board instead of the floor.</p>+ <h3><a href="/blog/how-to-use-claude-code-plan-mode/">How to Use Claude Code Plan Mode</a></h3>+ <p class="dek">How Claude Code's plan mode works: turning it on, what it blocks, what a real headless plan mode run prints, and how to leave it.</p><div class="foot"><span class="tag kind">Guides</span>- <a class="more" href="/blog/command-center-guide/" aria-label="Read: The Command Center: Kanban, Fleet and Budgets in One Place">Read →</a>+ <a class="more" href="/blog/how-to-use-claude-code-plan-mode/" aria-label="Read: How to Use Claude Code Plan Mode">Read →</a></div></div></article>diff --git a/docs/blog/security-for-ai-coding-agents/index.html b/docs/blog/security-for-ai-coding-agents/index.htmlindex 09fba143..89950739 100644--- a/docs/blog/security-for-ai-coding-agents/index.html+++ b/docs/blog/security-for-ai-coding-agents/index.html@@ -304,50 +304,50 @@ and open source.</p><h2>Related in Guides</h2><div class="post-grid"><article class="card t-guides">- <a class="thumb t-guides" href="/blog/how-to-use-claude-code-plan-mode/" aria-hidden="true" tabindex="-1"><img src="/blog/assets/media/how-to-use-claude-code-plan-mode/hero.png" alt="" loading="lazy" decoding="async" /></a>+ <a class="thumb t-guides" href="/blog/claude-code-max-plan-tips/" aria-hidden="true" tabindex="-1"><img src="/blog/assets/media/claude-code-max-plan-tips/hero.png" alt="" loading="lazy" decoding="async" /></a><div class="body"><div class="meta">- <time datetime="2026-09-11">Sep 11, 2026</time>+ <time datetime="2026-09-14">Sep 14, 2026</time><span class="dot" aria-hidden="true"></span><span>5 min</span></div>- <h3><a href="/blog/how-to-use-claude-code-plan-mode/">How to Use Claude Code Plan Mode</a></h3>- <p class="dek">How Claude Code's plan mode works: turning it on, what it blocks, what a real headless plan mode run prints, and how to leave it.</p>+ <h3><a href="/blog/claude-code-max-plan-tips/">How to Get the Most Out of Your Claude Code Max Plan</a></h3>+ <p class="dek">Stretch a Claude Code Max plan: model choice, context hygiene, prompt caching, subagents and unattended runs, checked against Anthropic's own pages.</p><div class="foot"><span class="tag kind">Guides</span>- <a class="more" href="/blog/how-to-use-claude-code-plan-mode/" aria-label="Read: How to Use Claude Code Plan Mode">Read →</a>+ <a class="more" href="/blog/claude-code-max-plan-tips/" aria-label="Read: How to Get the Most Out of Your Claude Code Max Plan">Read →</a></div></div></article><article class="card t-guides">- <a class="thumb t-guides" href="/blog/how-to-add-an-mcp-server-to-claude-code/" aria-hidden="true" tabindex="-1"><img src="/blog/assets/media/how-to-add-an-mcp-server-to-claude-code/hero.png" alt="" loading="lazy" decoding="async" /></a>+ <a class="thumb t-guides" href="/blog/codex-max-plan-tips/" aria-hidden="true" tabindex="-1"><img src="/blog/assets/media/codex-max-plan-tips/hero.png" alt="" loading="lazy" decoding="async" /></a><div class="body"><div class="meta">- <time datetime="2026-09-10">Sep 10, 2026</time>+ <time datetime="2026-09-14">Sep 14, 2026</time><span class="dot" aria-hidden="true"></span><span>5 min</span></div>- <h3><a href="/blog/how-to-add-an-mcp-server-to-claude-code/">How to Add an MCP Server to Claude Code</a></h3>- <p class="dek">The claude mcp add command, its scope flag, editing .mcp.json by hand, and how Munder Difflin's Capabilities screen grants an MCP server to one agent at a time.</p>+ <h3><a href="/blog/codex-max-plan-tips/">How to Make the Most of Your Codex Max Plan</a></h3>+ <p class="dek">There is no Codex Max plan. What ChatGPT Pro 5x and 20x give you in Codex, how the weekly limit works, and how to stretch it.</p><div class="foot"><span class="tag kind">Guides</span>- <a class="more" href="/blog/how-to-add-an-mcp-server-to-claude-code/" aria-label="Read: How to Add an MCP Server to Claude Code">Read →</a>+ <a class="more" href="/blog/codex-max-plan-tips/" aria-label="Read: How to Make the Most of Your Codex Max Plan">Read →</a></div></div></article><article class="card t-guides">- <a class="thumb t-guides" href="/blog/command-center-guide/" aria-hidden="true" tabindex="-1"><img src="/blog/assets/media/command-center-guide/hero.png" alt="" loading="lazy" decoding="async" /></a>+ <a class="thumb t-guides" href="/blog/how-to-use-claude-code-plan-mode/" aria-hidden="true" tabindex="-1"><img src="/blog/assets/media/how-to-use-claude-code-plan-mode/hero.png" alt="" loading="lazy" decoding="async" /></a><div class="body"><div class="meta">- <time datetime="2026-07-03">Jul 3, 2026</time>+ <time datetime="2026-09-11">Sep 11, 2026</time><span class="dot" aria-hidden="true"></span>- <span>4 min</span>+ <span>5 min</span></div>- <h3><a href="/blog/command-center-guide/">The Command Center: Kanban, Fleet and Budgets in One Place</a></h3>- <p class="dek">A guide to Munder Difflin's Command Center in 0.5.2: the kanban with task dependencies, the ask me tab, triggers, memory, live token use against each agent's budget, and when to watch the board instead of the floor.</p>+ <h3><a href="/blog/how-to-use-claude-code-plan-mode/">How to Use Claude Code Plan Mode</a></h3>+ <p class="dek">How Claude Code's plan mode works: turning it on, what it blocks, what a real headless plan mode run prints, and how to leave it.</p><div class="foot"><span class="tag kind">Guides</span>- <a class="more" href="/blog/command-center-guide/" aria-label="Read: The Command Center: Kanban, Fleet and Budgets in One Place">Read →</a>+ <a class="more" href="/blog/how-to-use-claude-code-plan-mode/" aria-label="Read: How to Use Claude Code Plan Mode">Read →</a></div></div></article>diff --git a/docs/blog/small-team-ai-agents-playbook/index.html b/docs/blog/small-team-ai-agents-playbook/index.htmlindex 09526839..121d0507 100644--- a/docs/blog/small-team-ai-agents-playbook/index.html+++ b/docs/blog/small-team-ai-agents-playbook/index.html@@ -309,50 +309,50 @@ it’s free and open source.</p><h2>Related in Guides</h2><div class="post-grid"><article class="card t-guides">- <a class="thumb t-guides" href="/blog/how-to-use-claude-code-plan-mode/" aria-hidden="true" tabindex="-1"><img src="/blog/assets/media/how-to-use-claude-code-plan-mode/hero.png" alt="" loading="lazy" decoding="async" /></a>+ <a class="thumb t-guides" href="/blog/claude-code-max-plan-tips/" aria-hidden="true" tabindex="-1"><img src="/blog/assets/media/claude-code-max-plan-tips/hero.png" alt="" loading="lazy" decoding="async" /></a><div class="body"><div class="meta">- <time datetime="2026-09-11">Sep 11, 2026</time>+ <time datetime="2026-09-14">Sep 14, 2026</time><span class="dot" aria-hidden="true"></span><span>5 min</span></div>- <h3><a href="/blog/how-to-use-claude-code-plan-mode/">How to Use Claude Code Plan Mode</a></h3>- <p class="dek">How Claude Code's plan mode works: turning it on, what it blocks, what a real headless plan mode run prints, and how to leave it.</p>+ <h3><a href="/blog/claude-code-max-plan-tips/">How to Get the Most Out of Your Claude Code Max Plan</a></h3>+ <p class="dek">Stretch a Claude Code Max plan: model choice, context hygiene, prompt caching, subagents and unattended runs, checked against Anthropic's own pages.</p><div class="foot"><span class="tag kind">Guides</span>- <a class="more" href="/blog/how-to-use-claude-code-plan-mode/" aria-label="Read: How to Use Claude Code Plan Mode">Read →</a>+ <a class="more" href="/blog/claude-code-max-plan-tips/" aria-label="Read: How to Get the Most Out of Your Claude Code Max Plan">Read →</a></div></div></article><article class="card t-guides">- <a class="thumb t-guides" href="/blog/how-to-add-an-mcp-server-to-claude-code/" aria-hidden="true" tabindex="-1"><img src="/blog/assets/media/how-to-add-an-mcp-server-to-claude-code/hero.png" alt="" loading="lazy" decoding="async" /></a>+ <a class="thumb t-guides" href="/blog/codex-max-plan-tips/" aria-hidden="true" tabindex="-1"><img src="/blog/assets/media/codex-max-plan-tips/hero.png" alt="" loading="lazy" decoding="async" /></a><div class="body"><div class="meta">- <time datetime="2026-09-10">Sep 10, 2026</time>+ <time datetime="2026-09-14">Sep 14, 2026</time><span class="dot" aria-hidden="true"></span><span>5 min</span></div>- <h3><a href="/blog/how-to-add-an-mcp-server-to-claude-code/">How to Add an MCP Server to Claude Code</a></h3>- <p class="dek">The claude mcp add command, its scope flag, editing .mcp.json by hand, and how Munder Difflin's Capabilities screen grants an MCP server to one agent at a time.</p>+ <h3><a href="/blog/codex-max-plan-tips/">How to Make the Most of Your Codex Max Plan</a></h3>+ <p class="dek">There is no Codex Max plan. What ChatGPT Pro 5x and 20x give you in Codex, how the weekly limit works, and how to stretch it.</p><div class="foot"><span class="tag kind">Guides</span>- <a class="more" href="/blog/how-to-add-an-mcp-server-to-claude-code/" aria-label="Read: How to Add an MCP Server to Claude Code">Read →</a>+ <a class="more" href="/blog/codex-max-plan-tips/" aria-label="Read: How to Make the Most of Your Codex Max Plan">Read →</a></div></div></article><article class="card t-guides">- <a class="thumb t-guides" href="/blog/command-center-guide/" aria-hidden="true" tabindex="-1"><img src="/blog/assets/media/command-center-guide/hero.png" alt="" loading="lazy" decoding="async" /></a>+ <a class="thumb t-guides" href="/blog/how-to-use-claude-code-plan-mode/" aria-hidden="true" tabindex="-1"><img src="/blog/assets/media/how-to-use-claude-code-plan-mode/hero.png" alt="" loading="lazy" decoding="async" /></a><div class="body"><div class="meta">- <time datetime="2026-07-03">Jul 3, 2026</time>+ <time datetime="2026-09-11">Sep 11, 2026</time><span class="dot" aria-hidden="true"></span>- <span>4 min</span>+ <span>5 min</span></div>- <h3><a href="/blog/command-center-guide/">The Command Center: Kanban, Fleet and Budgets in One Place</a></h3>- <p class="dek">A guide to Munder Difflin's Command Center in 0.5.2: the kanban with task dependencies, the ask me tab, triggers, memory, live token use against each agent's budget, and when to watch the board instead of the floor.</p>+ <h3><a href="/blog/how-to-use-claude-code-plan-mode/">How to Use Claude Code Plan Mode</a></h3>+ <p class="dek">How Claude Code's plan mode works: turning it on, what it blocks, what a real headless plan mode run prints, and how to leave it.</p><div class="foot"><span class="tag kind">Guides</span>- <a class="more" href="/blog/command-center-guide/" aria-label="Read: The Command Center: Kanban, Fleet and Budgets in One Place">Read →</a>+ <a class="more" href="/blog/how-to-use-claude-code-plan-mode/" aria-label="Read: How to Use Claude Code Plan Mode">Read →</a></div></div></article>diff --git a/docs/blog/tags/claude-code/index.html b/docs/blog/tags/claude-code/index.htmlindex 0eda6b00..ea276a94 100644--- a/docs/blog/tags/claude-code/index.html+++ b/docs/blog/tags/claude-code/index.html@@ -90,11 +90,59 @@<header class="page-head wrap"><p class="eyebrow">Tag</p><h1>#Claude Code</h1>- <p class="lead">49 posts tagged <strong>Claude Code</strong>.</p>+ <p class="lead">52 posts tagged <strong>Claude Code</strong>.</p></header><section class="wrap"><div class="post-grid"><article class="card t-guides">+ <a class="thumb t-guides" href="/blog/claude-code-max-plan-tips/" aria-hidden="true" tabindex="-1"><img src="/blog/assets/media/claude-code-max-plan-tips/hero.png" alt="" loading="lazy" decoding="async" /></a>+ <div class="body">+ <div class="meta">+ <time datetime="2026-09-14">Sep 14, 2026</time>+ <span class="dot" aria-hidden="true"></span>+ <span>5 min</span>+ </div>+ <h3><a href="/blog/claude-code-max-plan-tips/">How to Get the Most Out of Your Claude Code Max Plan</a></h3>+ <p class="dek">Stretch a Claude Code Max plan: model choice, context hygiene, prompt caching, subagents and unattended runs, checked against Anthropic's own pages.</p>+ <div class="foot">+ <span class="tag kind">Guides</span>+ <a class="more" href="/blog/claude-code-max-plan-tips/" aria-label="Read: How to Get the Most Out of Your Claude Code Max Plan">Read →</a>+ </div>+ </div>+</article>+<article class="card t-comparisons">+ <a class="thumb t-comparisons" href="/blog/herdr-alternatives/" aria-hidden="true" tabindex="-1"><img src="/blog/assets/media/herdr-alternatives/hero.png" alt="" loading="lazy" decoding="async" /></a>+ <div class="body">+ <div class="meta">+ <time datetime="2026-09-14">Sep 14, 2026</time>+ <span class="dot" aria-hidden="true"></span>+ <span>5 min</span>+ </div>+ <h3><a href="/blog/herdr-alternatives/">Herdr Alternatives: What to Pick and Who Each One Fits</a></h3>+ <p class="dek">Herdr alternatives checked on 14 Sep 2026: tmux, Claude Squad, cmux, Orca, Conductor, Superset, Emdash and Munder Difflin, and who each fits.</p>+ <div class="foot">+ <span class="tag kind">Comparisons</span>+ <a class="more" href="/blog/herdr-alternatives/" aria-label="Read: Herdr Alternatives: What to Pick and Who Each One Fits">Read →</a>+ </div>+ </div>+</article>+<article class="card t-comparisons">+ <a class="thumb t-comparisons" href="/blog/omniagent-alternatives/" aria-hidden="true" tabindex="-1"><span class="thumb-ph"><em class="ph-glyph" aria-hidden="true">✶</em><span>COMPARISONS</span></span></a>+ <div class="body">+ <div class="meta">+ <time datetime="2026-09-14">Sep 14, 2026</time>+ <span class="dot" aria-hidden="true"></span>+ <span>5 min</span>+ </div>+ <h3><a href="/blog/omniagent-alternatives/">OmniAgent Alternatives: What to Use Instead of Databricks Omnigent</a></h3>+ <p class="dek">OmniAgent is really Omnigent, the open source meta harness from Databricks. Alternatives checked on 14 Sep 2026, and who each one fits.</p>+ <div class="foot">+ <span class="tag kind">Comparisons</span>+ <a class="more" href="/blog/omniagent-alternatives/" aria-label="Read: OmniAgent Alternatives: What to Use Instead of Databricks Omnigent">Read →</a>+ </div>+ </div>+</article>+<article class="card t-guides"><a class="thumb t-guides" href="/blog/how-to-use-claude-code-plan-mode/" aria-hidden="true" tabindex="-1"><img src="/blog/assets/media/how-to-use-claude-code-plan-mode/hero.png" alt="" loading="lazy" decoding="async" /></a><div class="body"><div class="meta">@@ -212,7 +260,7 @@<div class="meta"><time datetime="2026-07-03">Jul 3, 2026</time><span class="dot" aria-hidden="true"></span>- <span>4 min</span>+ <span>5 min</span></div><h3><a href="/blog/tmux-and-scripts-vs-an-agent-harness/">Running Agents in tmux vs an Agent Harness</a></h3><p class="dek">tmux panes, git worktrees, shell scripts, and cron will absolutely run several Claude Code sessions at once. Here's what that DIY setup does well, where it breaks at scale, and what a purpose-built agent harness automates.</p>diff --git a/docs/blog/tags/codex/index.html b/docs/blog/tags/codex/index.htmlindex b73006e5..3117aca8 100644--- a/docs/blog/tags/codex/index.html+++ b/docs/blog/tags/codex/index.html@@ -90,11 +90,27 @@<header class="page-head wrap"><p class="eyebrow">Tag</p><h1>#Codex</h1>- <p class="lead">3 posts tagged <strong>Codex</strong>.</p>+ <p class="lead">4 posts tagged <strong>Codex</strong>.</p></header><section class="wrap"><div class="post-grid">- <article class="card t-comparisons">+ <article class="card t-guides">+ <a class="thumb t-guides" href="/blog/codex-max-plan-tips/" aria-hidden="true" tabindex="-1"><img src="/blog/assets/media/codex-max-plan-tips/hero.png" alt="" loading="lazy" decoding="async" /></a>+ <div class="body">+ <div class="meta">+ <time datetime="2026-09-14">Sep 14, 2026</time>+ <span class="dot" aria-hidden="true"></span>+ <span>5 min</span>+ </div>+ <h3><a href="/blog/codex-max-plan-tips/">How to Make the Most of Your Codex Max Plan</a></h3>+ <p class="dek">There is no Codex Max plan. What ChatGPT Pro 5x and 20x give you in Codex, how the weekly limit works, and how to stretch it.</p>+ <div class="foot">+ <span class="tag kind">Guides</span>+ <a class="more" href="/blog/codex-max-plan-tips/" aria-label="Read: How to Make the Most of Your Codex Max Plan">Read →</a>+ </div>+ </div>+</article>+<article class="card t-comparisons"><a class="thumb t-comparisons" href="/blog/codex-cli-vs-claude-code/" aria-hidden="true" tabindex="-1"><img src="/blog/assets/media/codex-cli-vs-claude-code/hero.png" alt="" loading="lazy" decoding="async" /></a><div class="body"><div class="meta">diff --git a/docs/blog/tags/comparisons/index.html b/docs/blog/tags/comparisons/index.htmlindex 8e4dae09..bb381a13 100644--- a/docs/blog/tags/comparisons/index.html+++ b/docs/blog/tags/comparisons/index.html@@ -90,11 +90,59 @@<header class="page-head wrap"><p class="eyebrow">Tag</p><h1>#Comparisons</h1>- <p class="lead">18 posts tagged <strong>Comparisons</strong>.</p>+ <p class="lead">21 posts tagged <strong>Comparisons</strong>.</p></header><section class="wrap"><div class="post-grid"><article class="card t-comparisons">+ <a class="thumb t-comparisons" href="/blog/grok-bot-alternatives/" aria-hidden="true" tabindex="-1"><img src="/blog/assets/media/grok-bot-alternatives/hero.png" alt="" loading="lazy" decoding="async" /></a>+ <div class="body">+ <div class="meta">+ <time datetime="2026-09-14">Sep 14, 2026</time>+ <span class="dot" aria-hidden="true"></span>+ <span>5 min</span>+ </div>+ <h3><a href="/blog/grok-bot-alternatives/">Grok Bot Alternatives: Six Picks, Grouped by What You Want</a></h3>+ <p class="dek">Grok Bot runs every Bot on one shared cloud computer. Six alternatives checked on 14 Sep 2026, grouped by hosting, privacy and model choice.</p>+ <div class="foot">+ <span class="tag kind">Comparisons</span>+ <a class="more" href="/blog/grok-bot-alternatives/" aria-label="Read: Grok Bot Alternatives: Six Picks, Grouped by What You Want">Read →</a>+ </div>+ </div>+</article>+<article class="card t-comparisons">+ <a class="thumb t-comparisons" href="/blog/herdr-alternatives/" aria-hidden="true" tabindex="-1"><img src="/blog/assets/media/herdr-alternatives/hero.png" alt="" loading="lazy" decoding="async" /></a>+ <div class="body">+ <div class="meta">+ <time datetime="2026-09-14">Sep 14, 2026</time>+ <span class="dot" aria-hidden="true"></span>+ <span>5 min</span>+ </div>+ <h3><a href="/blog/herdr-alternatives/">Herdr Alternatives: What to Pick and Who Each One Fits</a></h3>+ <p class="dek">Herdr alternatives checked on 14 Sep 2026: tmux, Claude Squad, cmux, Orca, Conductor, Superset, Emdash and Munder Difflin, and who each fits.</p>+ <div class="foot">+ <span class="tag kind">Comparisons</span>+ <a class="more" href="/blog/herdr-alternatives/" aria-label="Read: Herdr Alternatives: What to Pick and Who Each One Fits">Read →</a>+ </div>+ </div>+</article>+<article class="card t-comparisons">+ <a class="thumb t-comparisons" href="/blog/omniagent-alternatives/" aria-hidden="true" tabindex="-1"><span class="thumb-ph"><em class="ph-glyph" aria-hidden="true">✶</em><span>COMPARISONS</span></span></a>+ <div class="body">+ <div class="meta">+ <time datetime="2026-09-14">Sep 14, 2026</time>+ <span class="dot" aria-hidden="true"></span>+ <span>5 min</span>+ </div>+ <h3><a href="/blog/omniagent-alternatives/">OmniAgent Alternatives: What to Use Instead of Databricks Omnigent</a></h3>+ <p class="dek">OmniAgent is really Omnigent, the open source meta harness from Databricks. Alternatives checked on 14 Sep 2026, and who each one fits.</p>+ <div class="foot">+ <span class="tag kind">Comparisons</span>+ <a class="more" href="/blog/omniagent-alternatives/" aria-label="Read: OmniAgent Alternatives: What to Use Instead of Databricks Omnigent">Read →</a>+ </div>+ </div>+</article>+<article class="card t-comparisons"><a class="thumb t-comparisons" href="/blog/codex-cli-vs-claude-code/" aria-hidden="true" tabindex="-1"><img src="/blog/assets/media/codex-cli-vs-claude-code/hero.png" alt="" loading="lazy" decoding="async" /></a><div class="body"><div class="meta">@@ -180,7 +228,7 @@<div class="meta"><time datetime="2026-07-03">Jul 3, 2026</time><span class="dot" aria-hidden="true"></span>- <span>4 min</span>+ <span>5 min</span></div><h3><a href="/blog/tmux-and-scripts-vs-an-agent-harness/">Running Agents in tmux vs an Agent Harness</a></h3><p class="dek">tmux panes, git worktrees, shell scripts, and cron will absolutely run several Claude Code sessions at once. Here's what that DIY setup does well, where it breaks at scale, and what a purpose-built agent harness automates.</p>diff --git a/docs/blog/tags/cost/index.html b/docs/blog/tags/cost/index.htmlindex a663165d..423c626b 100644--- a/docs/blog/tags/cost/index.html+++ b/docs/blog/tags/cost/index.html@@ -90,11 +90,43 @@<header class="page-head wrap"><p class="eyebrow">Tag</p><h1>#Cost</h1>- <p class="lead">9 posts tagged <strong>Cost</strong>.</p>+ <p class="lead">11 posts tagged <strong>Cost</strong>.</p></header><section class="wrap"><div class="post-grid">- <article class="card t-concepts">+ <article class="card t-guides">+ <a class="thumb t-guides" href="/blog/claude-code-max-plan-tips/" aria-hidden="true" tabindex="-1"><img src="/blog/assets/media/claude-code-max-plan-tips/hero.png" alt="" loading="lazy" decoding="async" /></a>+ <div class="body">+ <div class="meta">+ <time datetime="2026-09-14">Sep 14, 2026</time>+ <span class="dot" aria-hidden="true"></span>+ <span>5 min</span>+ </div>+ <h3><a href="/blog/claude-code-max-plan-tips/">How to Get the Most Out of Your Claude Code Max Plan</a></h3>+ <p class="dek">Stretch a Claude Code Max plan: model choice, context hygiene, prompt caching, subagents and unattended runs, checked against Anthropic's own pages.</p>+ <div class="foot">+ <span class="tag kind">Guides</span>+ <a class="more" href="/blog/claude-code-max-plan-tips/" aria-label="Read: How to Get the Most Out of Your Claude Code Max Plan">Read →</a>+ </div>+ </div>+</article>+<article class="card t-guides">+ <a class="thumb t-guides" href="/blog/codex-max-plan-tips/" aria-hidden="true" tabindex="-1"><img src="/blog/assets/media/codex-max-plan-tips/hero.png" alt="" loading="lazy" decoding="async" /></a>+ <div class="body">+ <div class="meta">+ <time datetime="2026-09-14">Sep 14, 2026</time>+ <span class="dot" aria-hidden="true"></span>+ <span>5 min</span>+ </div>+ <h3><a href="/blog/codex-max-plan-tips/">How to Make the Most of Your Codex Max Plan</a></h3>+ <p class="dek">There is no Codex Max plan. What ChatGPT Pro 5x and 20x give you in Codex, how the weekly limit works, and how to stretch it.</p>+ <div class="foot">+ <span class="tag kind">Guides</span>+ <a class="more" href="/blog/codex-max-plan-tips/" aria-label="Read: How to Make the Most of Your Codex Max Plan">Read →</a>+ </div>+ </div>+</article>+<article class="card t-concepts"><a class="thumb t-concepts" href="/blog/how-much-does-claude-code-cost/" aria-hidden="true" tabindex="-1"><img src="/blog/assets/media/how-much-does-claude-code-cost/hero.png" alt="" loading="lazy" decoding="async" /></a><div class="body"><div class="meta">diff --git a/docs/blog/tags/git-worktrees/index.html b/docs/blog/tags/git-worktrees/index.htmlindex fb786b48..68d5cea5 100644--- a/docs/blog/tags/git-worktrees/index.html+++ b/docs/blog/tags/git-worktrees/index.html@@ -100,7 +100,7 @@<div class="meta"><time datetime="2026-07-03">Jul 3, 2026</time><span class="dot" aria-hidden="true"></span>- <span>4 min</span>+ <span>5 min</span></div><h3><a href="/blog/tmux-and-scripts-vs-an-agent-harness/">Running Agents in tmux vs an Agent Harness</a></h3><p class="dek">tmux panes, git worktrees, shell scripts, and cron will absolutely run several Claude Code sessions at once. Here's what that DIY setup does well, where it breaks at scale, and what a purpose-built agent harness automates.</p>diff --git a/docs/blog/tags/guides/index.html b/docs/blog/tags/guides/index.htmlindex 888b0519..365764cb 100644--- a/docs/blog/tags/guides/index.html+++ b/docs/blog/tags/guides/index.html@@ -90,11 +90,43 @@<header class="page-head wrap"><p class="eyebrow">Tag</p><h1>#Guides</h1>- <p class="lead">25 posts tagged <strong>Guides</strong>.</p>+ <p class="lead">27 posts tagged <strong>Guides</strong>.</p></header><section class="wrap"><div class="post-grid"><article class="card t-guides">+ <a class="thumb t-guides" href="/blog/claude-code-max-plan-tips/" aria-hidden="true" tabindex="-1"><img src="/blog/assets/media/claude-code-max-plan-tips/hero.png" alt="" loading="lazy" decoding="async" /></a>+ <div class="body">+ <div class="meta">+ <time datetime="2026-09-14">Sep 14, 2026</time>+ <span class="dot" aria-hidden="true"></span>+ <span>5 min</span>+ </div>+ <h3><a href="/blog/claude-code-max-plan-tips/">How to Get the Most Out of Your Claude Code Max Plan</a></h3>+ <p class="dek">Stretch a Claude Code Max plan: model choice, context hygiene, prompt caching, subagents and unattended runs, checked against Anthropic's own pages.</p>+ <div class="foot">+ <span class="tag kind">Guides</span>+ <a class="more" href="/blog/claude-code-max-plan-tips/" aria-label="Read: How to Get the Most Out of Your Claude Code Max Plan">Read →</a>+ </div>+ </div>+</article>+<article class="card t-guides">+ <a class="thumb t-guides" href="/blog/codex-max-plan-tips/" aria-hidden="true" tabindex="-1"><img src="/blog/assets/media/codex-max-plan-tips/hero.png" alt="" loading="lazy" decoding="async" /></a>+ <div class="body">+ <div class="meta">+ <time datetime="2026-09-14">Sep 14, 2026</time>+ <span class="dot" aria-hidden="true"></span>+ <span>5 min</span>+ </div>+ <h3><a href="/blog/codex-max-plan-tips/">How to Make the Most of Your Codex Max Plan</a></h3>+ <p class="dek">There is no Codex Max plan. What ChatGPT Pro 5x and 20x give you in Codex, how the weekly limit works, and how to stretch it.</p>+ <div class="foot">+ <span class="tag kind">Guides</span>+ <a class="more" href="/blog/codex-max-plan-tips/" aria-label="Read: How to Make the Most of Your Codex Max Plan">Read →</a>+ </div>+ </div>+</article>+<article class="card t-guides"><a class="thumb t-guides" href="/blog/how-to-use-claude-code-plan-mode/" aria-hidden="true" tabindex="-1"><img src="/blog/assets/media/how-to-use-claude-code-plan-mode/hero.png" alt="" loading="lazy" decoding="async" /></a><div class="body"><div class="meta">diff --git a/docs/blog/tags/local-first/index.html b/docs/blog/tags/local-first/index.htmlindex fa0d6fca..a6067ef5 100644--- a/docs/blog/tags/local-first/index.html+++ b/docs/blog/tags/local-first/index.html@@ -90,11 +90,27 @@<header class="page-head wrap"><p class="eyebrow">Tag</p><h1>#Local-First</h1>- <p class="lead">13 posts tagged <strong>Local-First</strong>.</p>+ <p class="lead">14 posts tagged <strong>Local-First</strong>.</p></header><section class="wrap"><div class="post-grid">- <article class="card t-guides">+ <article class="card t-comparisons">+ <a class="thumb t-comparisons" href="/blog/grok-bot-alternatives/" aria-hidden="true" tabindex="-1"><img src="/blog/assets/media/grok-bot-alternatives/hero.png" alt="" loading="lazy" decoding="async" /></a>+ <div class="body">+ <div class="meta">+ <time datetime="2026-09-14">Sep 14, 2026</time>+ <span class="dot" aria-hidden="true"></span>+ <span>5 min</span>+ </div>+ <h3><a href="/blog/grok-bot-alternatives/">Grok Bot Alternatives: Six Picks, Grouped by What You Want</a></h3>+ <p class="dek">Grok Bot runs every Bot on one shared cloud computer. Six alternatives checked on 14 Sep 2026, grouped by hosting, privacy and model choice.</p>+ <div class="foot">+ <span class="tag kind">Comparisons</span>+ <a class="more" href="/blog/grok-bot-alternatives/" aria-label="Read: Grok Bot Alternatives: Six Picks, Grouped by What You Want">Read →</a>+ </div>+ </div>+</article>+<article class="card t-guides"><a class="thumb t-guides" href="/blog/how-to-use-the-built-in-monaco-ide/" aria-hidden="true" tabindex="-1"><img src="/blog/assets/media/how-to-use-the-built-in-monaco-ide/hero.png" alt="" loading="lazy" decoding="async" /></a><div class="body"><div class="meta">diff --git a/docs/blog/tags/memory/index.html b/docs/blog/tags/memory/index.htmlindex 62cc8f8e..a30ee93f 100644--- a/docs/blog/tags/memory/index.html+++ b/docs/blog/tags/memory/index.html@@ -90,11 +90,27 @@<header class="page-head wrap"><p class="eyebrow">Tag</p><h1>#Memory</h1>- <p class="lead">8 posts tagged <strong>Memory</strong>.</p>+ <p class="lead">9 posts tagged <strong>Memory</strong>.</p></header><section class="wrap"><div class="post-grid">- <article class="card t-internals">+ <article class="card t-comparisons">+ <a class="thumb t-comparisons" href="/blog/grok-bot-alternatives/" aria-hidden="true" tabindex="-1"><img src="/blog/assets/media/grok-bot-alternatives/hero.png" alt="" loading="lazy" decoding="async" /></a>+ <div class="body">+ <div class="meta">+ <time datetime="2026-09-14">Sep 14, 2026</time>+ <span class="dot" aria-hidden="true"></span>+ <span>5 min</span>+ </div>+ <h3><a href="/blog/grok-bot-alternatives/">Grok Bot Alternatives: Six Picks, Grouped by What You Want</a></h3>+ <p class="dek">Grok Bot runs every Bot on one shared cloud computer. Six alternatives checked on 14 Sep 2026, grouped by hosting, privacy and model choice.</p>+ <div class="foot">+ <span class="tag kind">Comparisons</span>+ <a class="more" href="/blog/grok-bot-alternatives/" aria-label="Read: Grok Bot Alternatives: Six Picks, Grouped by What You Want">Read →</a>+ </div>+ </div>+</article>+<article class="card t-internals"><a class="thumb t-internals" href="/blog/compressing-agent-memory/" aria-hidden="true" tabindex="-1"><img src="/blog/assets/media/compressing-agent-memory/hero.png" alt="" loading="lazy" decoding="async" /></a><div class="body"><div class="meta">diff --git a/docs/blog/tags/model-routing/index.html b/docs/blog/tags/model-routing/index.htmlindex a15117bf..e27d20ca 100644--- a/docs/blog/tags/model-routing/index.html+++ b/docs/blog/tags/model-routing/index.html@@ -90,11 +90,27 @@<header class="page-head wrap"><p class="eyebrow">Tag</p><h1>#Model Routing</h1>- <p class="lead">3 posts tagged <strong>Model Routing</strong>.</p>+ <p class="lead">4 posts tagged <strong>Model Routing</strong>.</p></header><section class="wrap"><div class="post-grid">- <article class="card t-concepts">+ <article class="card t-guides">+ <a class="thumb t-guides" href="/blog/codex-max-plan-tips/" aria-hidden="true" tabindex="-1"><img src="/blog/assets/media/codex-max-plan-tips/hero.png" alt="" loading="lazy" decoding="async" /></a>+ <div class="body">+ <div class="meta">+ <time datetime="2026-09-14">Sep 14, 2026</time>+ <span class="dot" aria-hidden="true"></span>+ <span>5 min</span>+ </div>+ <h3><a href="/blog/codex-max-plan-tips/">How to Make the Most of Your Codex Max Plan</a></h3>+ <p class="dek">There is no Codex Max plan. What ChatGPT Pro 5x and 20x give you in Codex, how the weekly limit works, and how to stretch it.</p>+ <div class="foot">+ <span class="tag kind">Guides</span>+ <a class="more" href="/blog/codex-max-plan-tips/" aria-label="Read: How to Make the Most of Your Codex Max Plan">Read →</a>+ </div>+ </div>+</article>+<article class="card t-concepts"><a class="thumb t-concepts" href="/blog/the-clone-army-trap-mixed-swarm-vs-identical-agents/" aria-hidden="true" tabindex="-1"><img src="/blog/assets/media/the-clone-army-trap-mixed-swarm-vs-identical-agents/hero.png" alt="" loading="lazy" decoding="async" /></a><div class="body"><div class="meta">diff --git a/docs/blog/tags/multi-agent/index.html b/docs/blog/tags/multi-agent/index.htmlindex b8af9a9f..f5037269 100644--- a/docs/blog/tags/multi-agent/index.html+++ b/docs/blog/tags/multi-agent/index.html@@ -90,11 +90,43 @@<header class="page-head wrap"><p class="eyebrow">Tag</p><h1>#Multi-Agent</h1>- <p class="lead">86 posts tagged <strong>Multi-Agent</strong>.</p>+ <p class="lead">88 posts tagged <strong>Multi-Agent</strong>.</p></header><section class="wrap"><div class="post-grid"><article class="card t-comparisons">+ <a class="thumb t-comparisons" href="/blog/herdr-alternatives/" aria-hidden="true" tabindex="-1"><img src="/blog/assets/media/herdr-alternatives/hero.png" alt="" loading="lazy" decoding="async" /></a>+ <div class="body">+ <div class="meta">+ <time datetime="2026-09-14">Sep 14, 2026</time>+ <span class="dot" aria-hidden="true"></span>+ <span>5 min</span>+ </div>+ <h3><a href="/blog/herdr-alternatives/">Herdr Alternatives: What to Pick and Who Each One Fits</a></h3>+ <p class="dek">Herdr alternatives checked on 14 Sep 2026: tmux, Claude Squad, cmux, Orca, Conductor, Superset, Emdash and Munder Difflin, and who each fits.</p>+ <div class="foot">+ <span class="tag kind">Comparisons</span>+ <a class="more" href="/blog/herdr-alternatives/" aria-label="Read: Herdr Alternatives: What to Pick and Who Each One Fits">Read →</a>+ </div>+ </div>+</article>+<article class="card t-comparisons">+ <a class="thumb t-comparisons" href="/blog/omniagent-alternatives/" aria-hidden="true" tabindex="-1"><span class="thumb-ph"><em class="ph-glyph" aria-hidden="true">✶</em><span>COMPARISONS</span></span></a>+ <div class="body">+ <div class="meta">+ <time datetime="2026-09-14">Sep 14, 2026</time>+ <span class="dot" aria-hidden="true"></span>+ <span>5 min</span>+ </div>+ <h3><a href="/blog/omniagent-alternatives/">OmniAgent Alternatives: What to Use Instead of Databricks Omnigent</a></h3>+ <p class="dek">OmniAgent is really Omnigent, the open source meta harness from Databricks. Alternatives checked on 14 Sep 2026, and who each one fits.</p>+ <div class="foot">+ <span class="tag kind">Comparisons</span>+ <a class="more" href="/blog/omniagent-alternatives/" aria-label="Read: OmniAgent Alternatives: What to Use Instead of Databricks Omnigent">Read →</a>+ </div>+ </div>+</article>+<article class="card t-comparisons"><a class="thumb t-comparisons" href="/blog/codex-cli-vs-claude-code/" aria-hidden="true" tabindex="-1"><img src="/blog/assets/media/codex-cli-vs-claude-code/hero.png" alt="" loading="lazy" decoding="async" /></a><div class="body"><div class="meta">@@ -356,7 +388,7 @@<div class="meta"><time datetime="2026-07-03">Jul 3, 2026</time><span class="dot" aria-hidden="true"></span>- <span>4 min</span>+ <span>5 min</span></div><h3><a href="/blog/tmux-and-scripts-vs-an-agent-harness/">Running Agents in tmux vs an Agent Harness</a></h3><p class="dek">tmux panes, git worktrees, shell scripts, and cron will absolutely run several Claude Code sessions at once. Here's what that DIY setup does well, where it breaks at scale, and what a purpose-built agent harness automates.</p>diff --git a/docs/blog/tags/open-source/index.html b/docs/blog/tags/open-source/index.htmlindex 1d96bd82..9d87cfcc 100644--- a/docs/blog/tags/open-source/index.html+++ b/docs/blog/tags/open-source/index.html@@ -90,11 +90,59 @@<header class="page-head wrap"><p class="eyebrow">Tag</p><h1>#Open Source</h1>- <p class="lead">23 posts tagged <strong>Open Source</strong>.</p>+ <p class="lead">26 posts tagged <strong>Open Source</strong>.</p></header><section class="wrap"><div class="post-grid">- <article class="card t-story">+ <article class="card t-comparisons">+ <a class="thumb t-comparisons" href="/blog/grok-bot-alternatives/" aria-hidden="true" tabindex="-1"><img src="/blog/assets/media/grok-bot-alternatives/hero.png" alt="" loading="lazy" decoding="async" /></a>+ <div class="body">+ <div class="meta">+ <time datetime="2026-09-14">Sep 14, 2026</time>+ <span class="dot" aria-hidden="true"></span>+ <span>5 min</span>+ </div>+ <h3><a href="/blog/grok-bot-alternatives/">Grok Bot Alternatives: Six Picks, Grouped by What You Want</a></h3>+ <p class="dek">Grok Bot runs every Bot on one shared cloud computer. Six alternatives checked on 14 Sep 2026, grouped by hosting, privacy and model choice.</p>+ <div class="foot">+ <span class="tag kind">Comparisons</span>+ <a class="more" href="/blog/grok-bot-alternatives/" aria-label="Read: Grok Bot Alternatives: Six Picks, Grouped by What You Want">Read →</a>+ </div>+ </div>+</article>+<article class="card t-comparisons">+ <a class="thumb t-comparisons" href="/blog/herdr-alternatives/" aria-hidden="true" tabindex="-1"><img src="/blog/assets/media/herdr-alternatives/hero.png" alt="" loading="lazy" decoding="async" /></a>+ <div class="body">+ <div class="meta">+ <time datetime="2026-09-14">Sep 14, 2026</time>+ <span class="dot" aria-hidden="true"></span>+ <span>5 min</span>+ </div>+ <h3><a href="/blog/herdr-alternatives/">Herdr Alternatives: What to Pick and Who Each One Fits</a></h3>+ <p class="dek">Herdr alternatives checked on 14 Sep 2026: tmux, Claude Squad, cmux, Orca, Conductor, Superset, Emdash and Munder Difflin, and who each fits.</p>+ <div class="foot">+ <span class="tag kind">Comparisons</span>+ <a class="more" href="/blog/herdr-alternatives/" aria-label="Read: Herdr Alternatives: What to Pick and Who Each One Fits">Read →</a>+ </div>+ </div>+</article>+<article class="card t-comparisons">+ <a class="thumb t-comparisons" href="/blog/omniagent-alternatives/" aria-hidden="true" tabindex="-1"><span class="thumb-ph"><em class="ph-glyph" aria-hidden="true">✶</em><span>COMPARISONS</span></span></a>+ <div class="body">+ <div class="meta">+ <time datetime="2026-09-14">Sep 14, 2026</time>+ <span class="dot" aria-hidden="true"></span>+ <span>5 min</span>+ </div>+ <h3><a href="/blog/omniagent-alternatives/">OmniAgent Alternatives: What to Use Instead of Databricks Omnigent</a></h3>+ <p class="dek">OmniAgent is really Omnigent, the open source meta harness from Databricks. Alternatives checked on 14 Sep 2026, and who each one fits.</p>+ <div class="foot">+ <span class="tag kind">Comparisons</span>+ <a class="more" href="/blog/omniagent-alternatives/" aria-label="Read: OmniAgent Alternatives: What to Use Instead of Databricks Omnigent">Read →</a>+ </div>+ </div>+</article>+<article class="card t-story"><a class="thumb t-story" href="/blog/launching-munder-difflin-v0-4-6/" aria-hidden="true" tabindex="-1"><img src="/blog/assets/media/launching-munder-difflin-v0-4-6/hero.png" alt="" loading="lazy" decoding="async" /></a><div class="body"><div class="meta">diff --git a/docs/blog/tags/security/index.html b/docs/blog/tags/security/index.htmlindex 34074683..58ecf2ce 100644--- a/docs/blog/tags/security/index.html+++ b/docs/blog/tags/security/index.html@@ -90,11 +90,27 @@<header class="page-head wrap"><p class="eyebrow">Tag</p><h1>#Security</h1>- <p class="lead">7 posts tagged <strong>Security</strong>.</p>+ <p class="lead">8 posts tagged <strong>Security</strong>.</p></header><section class="wrap"><div class="post-grid">- <article class="card t-guides">+ <article class="card t-comparisons">+ <a class="thumb t-comparisons" href="/blog/grok-bot-alternatives/" aria-hidden="true" tabindex="-1"><img src="/blog/assets/media/grok-bot-alternatives/hero.png" alt="" loading="lazy" decoding="async" /></a>+ <div class="body">+ <div class="meta">+ <time datetime="2026-09-14">Sep 14, 2026</time>+ <span class="dot" aria-hidden="true"></span>+ <span>5 min</span>+ </div>+ <h3><a href="/blog/grok-bot-alternatives/">Grok Bot Alternatives: Six Picks, Grouped by What You Want</a></h3>+ <p class="dek">Grok Bot runs every Bot on one shared cloud computer. Six alternatives checked on 14 Sep 2026, grouped by hosting, privacy and model choice.</p>+ <div class="foot">+ <span class="tag kind">Comparisons</span>+ <a class="more" href="/blog/grok-bot-alternatives/" aria-label="Read: Grok Bot Alternatives: Six Picks, Grouped by What You Want">Read →</a>+ </div>+ </div>+</article>+<article class="card t-guides"><a class="thumb t-guides" href="/blog/how-to-hire-from-the-agent-gallery/" aria-hidden="true" tabindex="-1"><img src="/blog/assets/media/how-to-hire-from-the-agent-gallery/hero.png" alt="" loading="lazy" decoding="async" /></a><div class="body"><div class="meta">diff --git a/docs/blog/tags/tmux/index.html b/docs/blog/tags/tmux/index.htmlindex 1ad9ba05..ec6a2189 100644--- a/docs/blog/tags/tmux/index.html+++ b/docs/blog/tags/tmux/index.html@@ -100,7 +100,7 @@<div class="meta"><time datetime="2026-07-03">Jul 3, 2026</time><span class="dot" aria-hidden="true"></span>- <span>4 min</span>+ <span>5 min</span></div><h3><a href="/blog/tmux-and-scripts-vs-an-agent-harness/">Running Agents in tmux vs an Agent Harness</a></h3><p class="dek">tmux panes, git worktrees, shell scripts, and cron will absolutely run several Claude Code sessions at once. Here's what that DIY setup does well, where it breaks at scale, and what a purpose-built agent harness automates.</p>diff --git a/docs/blog/tags/tools/index.html b/docs/blog/tags/tools/index.htmlindex 41686c36..1e8a9417 100644--- a/docs/blog/tags/tools/index.html+++ b/docs/blog/tags/tools/index.html@@ -90,11 +90,43 @@<header class="page-head wrap"><p class="eyebrow">Tag</p><h1>#Tools</h1>- <p class="lead">10 posts tagged <strong>Tools</strong>.</p>+ <p class="lead">12 posts tagged <strong>Tools</strong>.</p></header><section class="wrap"><div class="post-grid"><article class="card t-comparisons">+ <a class="thumb t-comparisons" href="/blog/herdr-alternatives/" aria-hidden="true" tabindex="-1"><img src="/blog/assets/media/herdr-alternatives/hero.png" alt="" loading="lazy" decoding="async" /></a>+ <div class="body">+ <div class="meta">+ <time datetime="2026-09-14">Sep 14, 2026</time>+ <span class="dot" aria-hidden="true"></span>+ <span>5 min</span>+ </div>+ <h3><a href="/blog/herdr-alternatives/">Herdr Alternatives: What to Pick and Who Each One Fits</a></h3>+ <p class="dek">Herdr alternatives checked on 14 Sep 2026: tmux, Claude Squad, cmux, Orca, Conductor, Superset, Emdash and Munder Difflin, and who each fits.</p>+ <div class="foot">+ <span class="tag kind">Comparisons</span>+ <a class="more" href="/blog/herdr-alternatives/" aria-label="Read: Herdr Alternatives: What to Pick and Who Each One Fits">Read →</a>+ </div>+ </div>+</article>+<article class="card t-comparisons">+ <a class="thumb t-comparisons" href="/blog/omniagent-alternatives/" aria-hidden="true" tabindex="-1"><span class="thumb-ph"><em class="ph-glyph" aria-hidden="true">✶</em><span>COMPARISONS</span></span></a>+ <div class="body">+ <div class="meta">+ <time datetime="2026-09-14">Sep 14, 2026</time>+ <span class="dot" aria-hidden="true"></span>+ <span>5 min</span>+ </div>+ <h3><a href="/blog/omniagent-alternatives/">OmniAgent Alternatives: What to Use Instead of Databricks Omnigent</a></h3>+ <p class="dek">OmniAgent is really Omnigent, the open source meta harness from Databricks. Alternatives checked on 14 Sep 2026, and who each one fits.</p>+ <div class="foot">+ <span class="tag kind">Comparisons</span>+ <a class="more" href="/blog/omniagent-alternatives/" aria-label="Read: OmniAgent Alternatives: What to Use Instead of Databricks Omnigent">Read →</a>+ </div>+ </div>+</article>+<article class="card t-comparisons"><a class="thumb t-comparisons" href="/blog/qm-vs-munder-difflin/" aria-hidden="true" tabindex="-1"><img src="/blog/assets/media/qm-vs-munder-difflin/hero.png" alt="" loading="lazy" decoding="async" /></a><div class="body"><div class="meta">diff --git a/docs/blog/tags/workflow/index.html b/docs/blog/tags/workflow/index.htmlindex b877f1bc..ae6eedb4 100644--- a/docs/blog/tags/workflow/index.html+++ b/docs/blog/tags/workflow/index.html@@ -90,11 +90,27 @@<header class="page-head wrap"><p class="eyebrow">Tag</p><h1>#Workflow</h1>- <p class="lead">7 posts tagged <strong>Workflow</strong>.</p>+ <p class="lead">8 posts tagged <strong>Workflow</strong>.</p></header><section class="wrap"><div class="post-grid">- <article class="card t-use-cases">+ <article class="card t-guides">+ <a class="thumb t-guides" href="/blog/claude-code-max-plan-tips/" aria-hidden="true" tabindex="-1"><img src="/blog/assets/media/claude-code-max-plan-tips/hero.png" alt="" loading="lazy" decoding="async" /></a>+ <div class="body">+ <div class="meta">+ <time datetime="2026-09-14">Sep 14, 2026</time>+ <span class="dot" aria-hidden="true"></span>+ <span>5 min</span>+ </div>+ <h3><a href="/blog/claude-code-max-plan-tips/">How to Get the Most Out of Your Claude Code Max Plan</a></h3>+ <p class="dek">Stretch a Claude Code Max plan: model choice, context hygiene, prompt caching, subagents and unattended runs, checked against Anthropic's own pages.</p>+ <div class="foot">+ <span class="tag kind">Guides</span>+ <a class="more" href="/blog/claude-code-max-plan-tips/" aria-label="Read: How to Get the Most Out of Your Claude Code Max Plan">Read →</a>+ </div>+ </div>+</article>+<article class="card t-use-cases"><a class="thumb t-use-cases" href="/blog/agents-ran-our-launch-week-analytics/" aria-hidden="true" tabindex="-1"><img src="/blog/assets/media/agents-ran-our-launch-week-analytics/hero.png" alt="" loading="lazy" decoding="async" /></a><div class="body"><div class="meta">diff --git a/docs/blog/the-lethal-trifecta-for-coding-agents/index.html b/docs/blog/the-lethal-trifecta-for-coding-agents/index.htmlindex 781263f5..702e4ab2 100644--- a/docs/blog/the-lethal-trifecta-for-coding-agents/index.html+++ b/docs/blog/the-lethal-trifecta-for-coding-agents/index.html@@ -327,50 +327,50 @@ secrets; it’s free and open source.</p><h2>Related in Guides</h2><div class="post-grid"><article class="card t-guides">- <a class="thumb t-guides" href="/blog/how-to-use-claude-code-plan-mode/" aria-hidden="true" tabindex="-1"><img src="/blog/assets/media/how-to-use-claude-code-plan-mode/hero.png" alt="" loading="lazy" decoding="async" /></a>+ <a class="thumb t-guides" href="/blog/claude-code-max-plan-tips/" aria-hidden="true" tabindex="-1"><img src="/blog/assets/media/claude-code-max-plan-tips/hero.png" alt="" loading="lazy" decoding="async" /></a><div class="body"><div class="meta">- <time datetime="2026-09-11">Sep 11, 2026</time>+ <time datetime="2026-09-14">Sep 14, 2026</time><span class="dot" aria-hidden="true"></span><span>5 min</span></div>- <h3><a href="/blog/how-to-use-claude-code-plan-mode/">How to Use Claude Code Plan Mode</a></h3>- <p class="dek">How Claude Code's plan mode works: turning it on, what it blocks, what a real headless plan mode run prints, and how to leave it.</p>+ <h3><a href="/blog/claude-code-max-plan-tips/">How to Get the Most Out of Your Claude Code Max Plan</a></h3>+ <p class="dek">Stretch a Claude Code Max plan: model choice, context hygiene, prompt caching, subagents and unattended runs, checked against Anthropic's own pages.</p><div class="foot"><span class="tag kind">Guides</span>- <a class="more" href="/blog/how-to-use-claude-code-plan-mode/" aria-label="Read: How to Use Claude Code Plan Mode">Read →</a>+ <a class="more" href="/blog/claude-code-max-plan-tips/" aria-label="Read: How to Get the Most Out of Your Claude Code Max Plan">Read →</a></div></div></article><article class="card t-guides">- <a class="thumb t-guides" href="/blog/how-to-add-an-mcp-server-to-claude-code/" aria-hidden="true" tabindex="-1"><img src="/blog/assets/media/how-to-add-an-mcp-server-to-claude-code/hero.png" alt="" loading="lazy" decoding="async" /></a>+ <a class="thumb t-guides" href="/blog/codex-max-plan-tips/" aria-hidden="true" tabindex="-1"><img src="/blog/assets/media/codex-max-plan-tips/hero.png" alt="" loading="lazy" decoding="async" /></a><div class="body"><div class="meta">- <time datetime="2026-09-10">Sep 10, 2026</time>+ <time datetime="2026-09-14">Sep 14, 2026</time><span class="dot" aria-hidden="true"></span><span>5 min</span></div>- <h3><a href="/blog/how-to-add-an-mcp-server-to-claude-code/">How to Add an MCP Server to Claude Code</a></h3>- <p class="dek">The claude mcp add command, its scope flag, editing .mcp.json by hand, and how Munder Difflin's Capabilities screen grants an MCP server to one agent at a time.</p>+ <h3><a href="/blog/codex-max-plan-tips/">How to Make the Most of Your Codex Max Plan</a></h3>+ <p class="dek">There is no Codex Max plan. What ChatGPT Pro 5x and 20x give you in Codex, how the weekly limit works, and how to stretch it.</p><div class="foot"><span class="tag kind">Guides</span>- <a class="more" href="/blog/how-to-add-an-mcp-server-to-claude-code/" aria-label="Read: How to Add an MCP Server to Claude Code">Read →</a>+ <a class="more" href="/blog/codex-max-plan-tips/" aria-label="Read: How to Make the Most of Your Codex Max Plan">Read →</a></div></div></article><article class="card t-guides">- <a class="thumb t-guides" href="/blog/command-center-guide/" aria-hidden="true" tabindex="-1"><img src="/blog/assets/media/command-center-guide/hero.png" alt="" loading="lazy" decoding="async" /></a>+ <a class="thumb t-guides" href="/blog/how-to-use-claude-code-plan-mode/" aria-hidden="true" tabindex="-1"><img src="/blog/assets/media/how-to-use-claude-code-plan-mode/hero.png" alt="" loading="lazy" decoding="async" /></a><div class="body"><div class="meta">- <time datetime="2026-07-03">Jul 3, 2026</time>+ <time datetime="2026-09-11">Sep 11, 2026</time><span class="dot" aria-hidden="true"></span>- <span>4 min</span>+ <span>5 min</span></div>- <h3><a href="/blog/command-center-guide/">The Command Center: Kanban, Fleet and Budgets in One Place</a></h3>- <p class="dek">A guide to Munder Difflin's Command Center in 0.5.2: the kanban with task dependencies, the ask me tab, triggers, memory, live token use against each agent's budget, and when to watch the board instead of the floor.</p>+ <h3><a href="/blog/how-to-use-claude-code-plan-mode/">How to Use Claude Code Plan Mode</a></h3>+ <p class="dek">How Claude Code's plan mode works: turning it on, what it blocks, what a real headless plan mode run prints, and how to leave it.</p><div class="foot"><span class="tag kind">Guides</span>- <a class="more" href="/blog/command-center-guide/" aria-label="Read: The Command Center: Kanban, Fleet and Budgets in One Place">Read →</a>+ <a class="more" href="/blog/how-to-use-claude-code-plan-mode/" aria-label="Read: How to Use Claude Code Plan Mode">Read →</a></div></div></article>diff --git a/docs/blog/the-multi-agent-cost-playbook/index.html b/docs/blog/the-multi-agent-cost-playbook/index.htmlindex 085cfdb8..4a134f5f 100644--- a/docs/blog/the-multi-agent-cost-playbook/index.html+++ b/docs/blog/the-multi-agent-cost-playbook/index.html@@ -309,50 +309,50 @@ to run a fleet that doesn’t bankrupt you — it’s free and open source.</p><h2>Related in Guides</h2><div class="post-grid"><article class="card t-guides">- <a class="thumb t-guides" href="/blog/how-to-use-claude-code-plan-mode/" aria-hidden="true" tabindex="-1"><img src="/blog/assets/media/how-to-use-claude-code-plan-mode/hero.png" alt="" loading="lazy" decoding="async" /></a>+ <a class="thumb t-guides" href="/blog/claude-code-max-plan-tips/" aria-hidden="true" tabindex="-1"><img src="/blog/assets/media/claude-code-max-plan-tips/hero.png" alt="" loading="lazy" decoding="async" /></a><div class="body"><div class="meta">- <time datetime="2026-09-11">Sep 11, 2026</time>+ <time datetime="2026-09-14">Sep 14, 2026</time><span class="dot" aria-hidden="true"></span><span>5 min</span></div>- <h3><a href="/blog/how-to-use-claude-code-plan-mode/">How to Use Claude Code Plan Mode</a></h3>- <p class="dek">How Claude Code's plan mode works: turning it on, what it blocks, what a real headless plan mode run prints, and how to leave it.</p>+ <h3><a href="/blog/claude-code-max-plan-tips/">How to Get the Most Out of Your Claude Code Max Plan</a></h3>+ <p class="dek">Stretch a Claude Code Max plan: model choice, context hygiene, prompt caching, subagents and unattended runs, checked against Anthropic's own pages.</p><div class="foot"><span class="tag kind">Guides</span>- <a class="more" href="/blog/how-to-use-claude-code-plan-mode/" aria-label="Read: How to Use Claude Code Plan Mode">Read →</a>+ <a class="more" href="/blog/claude-code-max-plan-tips/" aria-label="Read: How to Get the Most Out of Your Claude Code Max Plan">Read →</a></div></div></article><article class="card t-guides">- <a class="thumb t-guides" href="/blog/how-to-add-an-mcp-server-to-claude-code/" aria-hidden="true" tabindex="-1"><img src="/blog/assets/media/how-to-add-an-mcp-server-to-claude-code/hero.png" alt="" loading="lazy" decoding="async" /></a>+ <a class="thumb t-guides" href="/blog/codex-max-plan-tips/" aria-hidden="true" tabindex="-1"><img src="/blog/assets/media/codex-max-plan-tips/hero.png" alt="" loading="lazy" decoding="async" /></a><div class="body"><div class="meta">- <time datetime="2026-09-10">Sep 10, 2026</time>+ <time datetime="2026-09-14">Sep 14, 2026</time><span class="dot" aria-hidden="true"></span><span>5 min</span></div>- <h3><a href="/blog/how-to-add-an-mcp-server-to-claude-code/">How to Add an MCP Server to Claude Code</a></h3>- <p class="dek">The claude mcp add command, its scope flag, editing .mcp.json by hand, and how Munder Difflin's Capabilities screen grants an MCP server to one agent at a time.</p>+ <h3><a href="/blog/codex-max-plan-tips/">How to Make the Most of Your Codex Max Plan</a></h3>+ <p class="dek">There is no Codex Max plan. What ChatGPT Pro 5x and 20x give you in Codex, how the weekly limit works, and how to stretch it.</p><div class="foot"><span class="tag kind">Guides</span>- <a class="more" href="/blog/how-to-add-an-mcp-server-to-claude-code/" aria-label="Read: How to Add an MCP Server to Claude Code">Read →</a>+ <a class="more" href="/blog/codex-max-plan-tips/" aria-label="Read: How to Make the Most of Your Codex Max Plan">Read →</a></div></div></article><article class="card t-guides">- <a class="thumb t-guides" href="/blog/command-center-guide/" aria-hidden="true" tabindex="-1"><img src="/blog/assets/media/command-center-guide/hero.png" alt="" loading="lazy" decoding="async" /></a>+ <a class="thumb t-guides" href="/blog/how-to-use-claude-code-plan-mode/" aria-hidden="true" tabindex="-1"><img src="/blog/assets/media/how-to-use-claude-code-plan-mode/hero.png" alt="" loading="lazy" decoding="async" /></a><div class="body"><div class="meta">- <time datetime="2026-07-03">Jul 3, 2026</time>+ <time datetime="2026-09-11">Sep 11, 2026</time><span class="dot" aria-hidden="true"></span>- <span>4 min</span>+ <span>5 min</span></div>- <h3><a href="/blog/command-center-guide/">The Command Center: Kanban, Fleet and Budgets in One Place</a></h3>- <p class="dek">A guide to Munder Difflin's Command Center in 0.5.2: the kanban with task dependencies, the ask me tab, triggers, memory, live token use against each agent's budget, and when to watch the board instead of the floor.</p>+ <h3><a href="/blog/how-to-use-claude-code-plan-mode/">How to Use Claude Code Plan Mode</a></h3>+ <p class="dek">How Claude Code's plan mode works: turning it on, what it blocks, what a real headless plan mode run prints, and how to leave it.</p><div class="foot"><span class="tag kind">Guides</span>- <a class="more" href="/blog/command-center-guide/" aria-label="Read: The Command Center: Kanban, Fleet and Budgets in One Place">Read →</a>+ <a class="more" href="/blog/how-to-use-claude-code-plan-mode/" aria-label="Read: How to Use Claude Code Plan Mode">Read →</a></div></div></article>diff --git a/docs/blog/tmux-and-scripts-vs-an-agent-harness/index.html b/docs/blog/tmux-and-scripts-vs-an-agent-harness/index.htmlindex e5ba4a78..656096e4 100644--- a/docs/blog/tmux-and-scripts-vs-an-agent-harness/index.html+++ b/docs/blog/tmux-and-scripts-vs-an-agent-harness/index.html@@ -161,7 +161,7 @@<span class="dot" aria-hidden="true">·</span><time datetime="2026-07-03">Jul 3, 2026</time><span class="dot" aria-hidden="true">·</span>- <span>4 min read</span>+ <span>5 min read</span><span class="tag kind">Comparisons</span></div></header>@@ -181,7 +181,7 @@<p><strong>Scrollback archaeology.</strong> “What did the fleet do overnight?” becomes an hour of <code>Ctrl+B [</code> and paging through six buffers, reconstructing a timeline by hand. There’s no event log, no board, no cost attribution — just bytes.</p><p><strong>Crash recovery is manual.</strong> A wedged session, a dead pane after a reboot, a cron job that fired while the machine slept — each is a small manual rebuild: recreate the worktree, relaunch the CLI, re-explain the task. Nothing <a href="/blog/recovering-from-agent-failures/">resumes or self-heals</a>.</p><p><strong>Cron is a trigger with no feedback loop.</strong> Cron can start a session on a schedule, but it can’t watch the result, retry a failure, or route the output anywhere. And there’s no path at all from “a teammate posted in Slack” or “a webhook fired” to “an agent picked it up.”</p>-<p>None of these are tmux’s fault. tmux is a terminal multiplexer, and it’s excellent at multiplexing terminals. Everything above is a <em>coordination</em> problem, and coordination is a different program — one you end up writing yourself, script by script, incident by incident.</p>+<p>None of these are tmux’s fault. tmux is a terminal multiplexer, and it’s excellent at multiplexing terminals. Everything above is a <em>coordination</em> problem, and coordination is a different program — one you end up writing yourself, script by script, incident by incident. Agent aware multiplexers such as herdr sit in between, and our <a href="/blog/herdr-alternatives/">herdr alternatives</a> post compares them with the rest.</p><figure class="fig fig-inline"><img src="/blog/assets/media/tmux-and-scripts-vs-an-agent-harness/note-1.png" alt="Hand-drawn sketch from “Running Agents in tmux vs an Agent Harness”" loading="lazy" decoding="async" /></figure><h2 id="what-a-harness-automates" tabindex="-1">What a harness automates <a class="anchor" href="#what-a-harness-automates" aria-hidden="true">#</a></h2><p>This is the layer <a href="/">Munder Difflin</a> is. Our landing page has a <a href="/#compare">full comparison table</a>, but it maps almost one-to-one onto the breakage list:</p>@@ -264,50 +264,50 @@<h2>Related in Comparisons</h2><div class="post-grid"><article class="card t-comparisons">- <a class="thumb t-comparisons" href="/blog/codex-cli-vs-claude-code/" aria-hidden="true" tabindex="-1"><img src="/blog/assets/media/codex-cli-vs-claude-code/hero.png" alt="" loading="lazy" decoding="async" /></a>+ <a class="thumb t-comparisons" href="/blog/grok-bot-alternatives/" aria-hidden="true" tabindex="-1"><img src="/blog/assets/media/grok-bot-alternatives/hero.png" alt="" loading="lazy" decoding="async" /></a><div class="body"><div class="meta">- <time datetime="2026-09-10">Sep 10, 2026</time>+ <time datetime="2026-09-14">Sep 14, 2026</time><span class="dot" aria-hidden="true"></span><span>5 min</span></div>- <h3><a href="/blog/codex-cli-vs-claude-code/">Codex CLI vs Claude Code</a></h3>- <p class="dek">Codex CLI and Claude Code compared firsthand: sandbox and approval flags, AGENTS.md vs CLAUDE.md, real pricing, and where each terminal agent wins.</p>+ <h3><a href="/blog/grok-bot-alternatives/">Grok Bot Alternatives: Six Picks, Grouped by What You Want</a></h3>+ <p class="dek">Grok Bot runs every Bot on one shared cloud computer. Six alternatives checked on 14 Sep 2026, grouped by hosting, privacy and model choice.</p><div class="foot"><span class="tag kind">Comparisons</span>- <a class="more" href="/blog/codex-cli-vs-claude-code/" aria-label="Read: Codex CLI vs Claude Code">Read →</a>+ <a class="more" href="/blog/grok-bot-alternatives/" aria-label="Read: Grok Bot Alternatives: Six Picks, Grouped by What You Want">Read →</a></div></div></article><article class="card t-comparisons">- <a class="thumb t-comparisons" href="/blog/qm-vs-munder-difflin/" aria-hidden="true" tabindex="-1"><img src="/blog/assets/media/qm-vs-munder-difflin/hero.png" alt="" loading="lazy" decoding="async" /></a>+ <a class="thumb t-comparisons" href="/blog/herdr-alternatives/" aria-hidden="true" tabindex="-1"><img src="/blog/assets/media/herdr-alternatives/hero.png" alt="" loading="lazy" decoding="async" /></a><div class="body"><div class="meta">- <time datetime="2026-08-06">Aug 6, 2026</time>+ <time datetime="2026-09-14">Sep 14, 2026</time><span class="dot" aria-hidden="true"></span>- <span>4 min</span>+ <span>5 min</span></div>- <h3><a href="/blog/qm-vs-munder-difflin/">qm vs Munder Difflin: YC's Multiplayer Harness or an Office of Your Clones?</a></h3>- <p class="dek">An honest September 2026 comparison of YC's qm and Munder Difflin. qm is a multiplayer agent harness a company deploys for Slack and the web. Munder Difflin runs an office of your clones on your own machine, with Teams to connect them.</p>+ <h3><a href="/blog/herdr-alternatives/">Herdr Alternatives: What to Pick and Who Each One Fits</a></h3>+ <p class="dek">Herdr alternatives checked on 14 Sep 2026: tmux, Claude Squad, cmux, Orca, Conductor, Superset, Emdash and Munder Difflin, and who each fits.</p><div class="foot"><span class="tag kind">Comparisons</span>- <a class="more" href="/blog/qm-vs-munder-difflin/" aria-label="Read: qm vs Munder Difflin: YC's Multiplayer Harness or an Office of Your Clones?">Read →</a>+ <a class="more" href="/blog/herdr-alternatives/" aria-label="Read: Herdr Alternatives: What to Pick and Who Each One Fits">Read →</a></div></div></article><article class="card t-comparisons">- <a class="thumb t-comparisons" href="/blog/crewai-autogen-vs-a-local-agent-harness/" aria-hidden="true" tabindex="-1"><img src="/blog/assets/media/crewai-autogen-vs-a-local-agent-harness/hero.png" alt="" loading="lazy" decoding="async" /></a>+ <a class="thumb t-comparisons" href="/blog/omniagent-alternatives/" aria-hidden="true" tabindex="-1"><span class="thumb-ph"><em class="ph-glyph" aria-hidden="true">✶</em><span>COMPARISONS</span></span></a><div class="body"><div class="meta">- <time datetime="2026-07-03">Jul 3, 2026</time>+ <time datetime="2026-09-14">Sep 14, 2026</time><span class="dot" aria-hidden="true"></span><span>5 min</span></div>- <h3><a href="/blog/crewai-autogen-vs-a-local-agent-harness/">CrewAI and AutoGen vs a Local Agent Harness: Framework or App?</a></h3>- <p class="dek">CrewAI, AutoGen (now Microsoft Agent Framework), and LangGraph are frameworks — Python you write to build your own agent system. A multi-agent harness is an app you download that runs a team on your repos today. Here's how to tell which one you actually need.</p>+ <h3><a href="/blog/omniagent-alternatives/">OmniAgent Alternatives: What to Use Instead of Databricks Omnigent</a></h3>+ <p class="dek">OmniAgent is really Omnigent, the open source meta harness from Databricks. Alternatives checked on 14 Sep 2026, and who each one fits.</p><div class="foot"><span class="tag kind">Comparisons</span>- <a class="more" href="/blog/crewai-autogen-vs-a-local-agent-harness/" aria-label="Read: CrewAI and AutoGen vs a Local Agent Harness: Framework or App?">Read →</a>+ <a class="more" href="/blog/omniagent-alternatives/" aria-label="Read: OmniAgent Alternatives: What to Use Instead of Databricks Omnigent">Read →</a></div></div></article>diff --git a/docs/blog/topics/comparisons/index.html b/docs/blog/topics/comparisons/index.htmlindex 28dfb1df..9998ef3c 100644--- a/docs/blog/topics/comparisons/index.html+++ b/docs/blog/topics/comparisons/index.html@@ -99,13 +99,13 @@<div class="filters" role="navigation" aria-label="Topics"><a class="chip" href="/blog/">All</a>- <a class="chip" href="/blog/topics/guides/">guides<span class="ct">36</span></a>+ <a class="chip" href="/blog/topics/guides/">guides<span class="ct">38</span></a><a class="chip" href="/blog/topics/concepts/">concepts<span class="ct">23</span></a>- <a class="chip" href="/blog/topics/internals/">internals<span class="ct">19</span></a>+ <a class="chip" href="/blog/topics/comparisons/" aria-current="page">comparisons<span class="ct">21</span></a>- <a class="chip" href="/blog/topics/comparisons/" aria-current="page">comparisons<span class="ct">18</span></a>+ <a class="chip" href="/blog/topics/internals/">internals<span class="ct">19</span></a><a class="chip" href="/blog/topics/story/">story<span class="ct">18</span></a>@@ -136,6 +136,54 @@</div></div></article>+<article class="card t-comparisons">+ <a class="thumb t-comparisons" href="/blog/grok-bot-alternatives/" aria-hidden="true" tabindex="-1"><img src="/blog/assets/media/grok-bot-alternatives/hero.png" alt="" loading="lazy" decoding="async" /></a>+ <div class="body">+ <div class="meta">+ <time datetime="2026-09-14">Sep 14, 2026</time>+ <span class="dot" aria-hidden="true"></span>+ <span>5 min</span>+ </div>+ <h3><a href="/blog/grok-bot-alternatives/">Grok Bot Alternatives: Six Picks, Grouped by What You Want</a></h3>+ <p class="dek">Grok Bot runs every Bot on one shared cloud computer. Six alternatives checked on 14 Sep 2026, grouped by hosting, privacy and model choice.</p>+ <div class="foot">+ <span class="tag kind">Comparisons</span>+ <a class="more" href="/blog/grok-bot-alternatives/" aria-label="Read: Grok Bot Alternatives: Six Picks, Grouped by What You Want">Read →</a>+ </div>+ </div>+</article>+<article class="card t-comparisons">+ <a class="thumb t-comparisons" href="/blog/herdr-alternatives/" aria-hidden="true" tabindex="-1"><img src="/blog/assets/media/herdr-alternatives/hero.png" alt="" loading="lazy" decoding="async" /></a>+ <div class="body">+ <div class="meta">+ <time datetime="2026-09-14">Sep 14, 2026</time>+ <span class="dot" aria-hidden="true"></span>+ <span>5 min</span>+ </div>+ <h3><a href="/blog/herdr-alternatives/">Herdr Alternatives: What to Pick and Who Each One Fits</a></h3>+ <p class="dek">Herdr alternatives checked on 14 Sep 2026: tmux, Claude Squad, cmux, Orca, Conductor, Superset, Emdash and Munder Difflin, and who each fits.</p>+ <div class="foot">+ <span class="tag kind">Comparisons</span>+ <a class="more" href="/blog/herdr-alternatives/" aria-label="Read: Herdr Alternatives: What to Pick and Who Each One Fits">Read →</a>+ </div>+ </div>+</article>+<article class="card t-comparisons">+ <a class="thumb t-comparisons" href="/blog/omniagent-alternatives/" aria-hidden="true" tabindex="-1"><span class="thumb-ph"><em class="ph-glyph" aria-hidden="true">✶</em><span>COMPARISONS</span></span></a>+ <div class="body">+ <div class="meta">+ <time datetime="2026-09-14">Sep 14, 2026</time>+ <span class="dot" aria-hidden="true"></span>+ <span>5 min</span>+ </div>+ <h3><a href="/blog/omniagent-alternatives/">OmniAgent Alternatives: What to Use Instead of Databricks Omnigent</a></h3>+ <p class="dek">OmniAgent is really Omnigent, the open source meta harness from Databricks. Alternatives checked on 14 Sep 2026, and who each one fits.</p>+ <div class="foot">+ <span class="tag kind">Comparisons</span>+ <a class="more" href="/blog/omniagent-alternatives/" aria-label="Read: OmniAgent Alternatives: What to Use Instead of Databricks Omnigent">Read →</a>+ </div>+ </div>+</article><article class="card t-comparisons"><a class="thumb t-comparisons" href="/blog/codex-cli-vs-claude-code/" aria-hidden="true" tabindex="-1"><img src="/blog/assets/media/codex-cli-vs-claude-code/hero.png" alt="" loading="lazy" decoding="async" /></a><div class="body">@@ -222,7 +270,7 @@<div class="meta"><time datetime="2026-07-03">Jul 3, 2026</time><span class="dot" aria-hidden="true"></span>- <span>4 min</span>+ <span>5 min</span></div><h3><a href="/blog/tmux-and-scripts-vs-an-agent-harness/">Running Agents in tmux vs an Agent Harness</a></h3><p class="dek">tmux panes, git worktrees, shell scripts, and cron will absolutely run several Claude Code sessions at once. Here's what that DIY setup does well, where it breaks at scale, and what a purpose-built agent harness automates.</p>diff --git a/docs/blog/topics/concepts/index.html b/docs/blog/topics/concepts/index.htmlindex 721d329c..42804b30 100644--- a/docs/blog/topics/concepts/index.html+++ b/docs/blog/topics/concepts/index.html@@ -99,13 +99,13 @@<div class="filters" role="navigation" aria-label="Topics"><a class="chip" href="/blog/">All</a>- <a class="chip" href="/blog/topics/guides/">guides<span class="ct">36</span></a>+ <a class="chip" href="/blog/topics/guides/">guides<span class="ct">38</span></a><a class="chip" href="/blog/topics/concepts/" aria-current="page">concepts<span class="ct">23</span></a>- <a class="chip" href="/blog/topics/internals/">internals<span class="ct">19</span></a>+ <a class="chip" href="/blog/topics/comparisons/">comparisons<span class="ct">21</span></a>- <a class="chip" href="/blog/topics/comparisons/">comparisons<span class="ct">18</span></a>+ <a class="chip" href="/blog/topics/internals/">internals<span class="ct">19</span></a><a class="chip" href="/blog/topics/story/">story<span class="ct">18</span></a>diff --git a/docs/blog/topics/guides/index.html b/docs/blog/topics/guides/index.htmlindex b3904762..f68d23b6 100644--- a/docs/blog/topics/guides/index.html+++ b/docs/blog/topics/guides/index.html@@ -99,13 +99,13 @@<div class="filters" role="navigation" aria-label="Topics"><a class="chip" href="/blog/">All</a>- <a class="chip" href="/blog/topics/guides/" aria-current="page">guides<span class="ct">36</span></a>+ <a class="chip" href="/blog/topics/guides/" aria-current="page">guides<span class="ct">38</span></a><a class="chip" href="/blog/topics/concepts/">concepts<span class="ct">23</span></a>- <a class="chip" href="/blog/topics/internals/">internals<span class="ct">19</span></a>+ <a class="chip" href="/blog/topics/comparisons/">comparisons<span class="ct">21</span></a>- <a class="chip" href="/blog/topics/comparisons/">comparisons<span class="ct">18</span></a>+ <a class="chip" href="/blog/topics/internals/">internals<span class="ct">19</span></a><a class="chip" href="/blog/topics/story/">story<span class="ct">18</span></a>@@ -184,6 +184,38 @@</div></div></article>+<article class="card t-guides">+ <a class="thumb t-guides" href="/blog/claude-code-max-plan-tips/" aria-hidden="true" tabindex="-1"><img src="/blog/assets/media/claude-code-max-plan-tips/hero.png" alt="" loading="lazy" decoding="async" /></a>+ <div class="body">+ <div class="meta">+ <time datetime="2026-09-14">Sep 14, 2026</time>+ <span class="dot" aria-hidden="true"></span>+ <span>5 min</span>+ </div>+ <h3><a href="/blog/claude-code-max-plan-tips/">How to Get the Most Out of Your Claude Code Max Plan</a></h3>+ <p class="dek">Stretch a Claude Code Max plan: model choice, context hygiene, prompt caching, subagents and unattended runs, checked against Anthropic's own pages.</p>+ <div class="foot">+ <span class="tag kind">Guides</span>+ <a class="more" href="/blog/claude-code-max-plan-tips/" aria-label="Read: How to Get the Most Out of Your Claude Code Max Plan">Read →</a>+ </div>+ </div>+</article>+<article class="card t-guides">+ <a class="thumb t-guides" href="/blog/codex-max-plan-tips/" aria-hidden="true" tabindex="-1"><img src="/blog/assets/media/codex-max-plan-tips/hero.png" alt="" loading="lazy" decoding="async" /></a>+ <div class="body">+ <div class="meta">+ <time datetime="2026-09-14">Sep 14, 2026</time>+ <span class="dot" aria-hidden="true"></span>+ <span>5 min</span>+ </div>+ <h3><a href="/blog/codex-max-plan-tips/">How to Make the Most of Your Codex Max Plan</a></h3>+ <p class="dek">There is no Codex Max plan. What ChatGPT Pro 5x and 20x give you in Codex, how the weekly limit works, and how to stretch it.</p>+ <div class="foot">+ <span class="tag kind">Guides</span>+ <a class="more" href="/blog/codex-max-plan-tips/" aria-label="Read: How to Make the Most of Your Codex Max Plan">Read →</a>+ </div>+ </div>+</article><article class="card t-guides"><a class="thumb t-guides" href="/blog/how-to-use-claude-code-plan-mode/" aria-hidden="true" tabindex="-1"><img src="/blog/assets/media/how-to-use-claude-code-plan-mode/hero.png" alt="" loading="lazy" decoding="async" /></a><div class="body">diff --git a/docs/blog/topics/index.html b/docs/blog/topics/index.htmlindex 7ea628fa..613baf9c 100644--- a/docs/blog/topics/index.html+++ b/docs/blog/topics/index.html@@ -102,7 +102,7 @@<span class="thumb t-guides" aria-hidden="true">GUIDES</span><div class="body"><h3 style="color:var(--ink)">guides</h3>- <p class="dek">36 posts.</p>+ <p class="dek">38 posts.</p><div class="foot"><span class="more">View topic →</span></div></div></a>@@ -116,20 +116,20 @@</div></a>- <a class="card" href="/blog/topics/internals/" style="text-decoration:none">- <span class="thumb t-internals" aria-hidden="true">INTERNALS</span>+ <a class="card" href="/blog/topics/comparisons/" style="text-decoration:none">+ <span class="thumb t-comparisons" aria-hidden="true">COMPARISONS</span><div class="body">- <h3 style="color:var(--ink)">internals</h3>- <p class="dek">19 posts.</p>+ <h3 style="color:var(--ink)">comparisons</h3>+ <p class="dek">21 posts.</p><div class="foot"><span class="more">View topic →</span></div></div></a>- <a class="card" href="/blog/topics/comparisons/" style="text-decoration:none">- <span class="thumb t-comparisons" aria-hidden="true">COMPARISONS</span>+ <a class="card" href="/blog/topics/internals/" style="text-decoration:none">+ <span class="thumb t-internals" aria-hidden="true">INTERNALS</span><div class="body">- <h3 style="color:var(--ink)">comparisons</h3>- <p class="dek">18 posts.</p>+ <h3 style="color:var(--ink)">internals</h3>+ <p class="dek">19 posts.</p><div class="foot"><span class="more">View topic →</span></div></div></a>@@ -176,15 +176,17 @@<div class="filters" style="padding-top:36px"><span class="eyebrow" style="align-self:center">Tags</span>- <a class="chip" href="/blog/tags/multi-agent/">Multi-Agent<span class="ct">86</span></a>+ <a class="chip" href="/blog/tags/multi-agent/">Multi-Agent<span class="ct">88</span></a>++ <a class="chip" href="/blog/tags/claude-code/">Claude Code<span class="ct">52</span></a>- <a class="chip" href="/blog/tags/claude-code/">Claude Code<span class="ct">49</span></a>+ <a class="chip" href="/blog/tags/guides/">Guides<span class="ct">27</span></a><a class="chip" href="/blog/tags/internals/">Internals<span class="ct">26</span></a>- <a class="chip" href="/blog/tags/guides/">Guides<span class="ct">25</span></a>+ <a class="chip" href="/blog/tags/open-source/">Open Source<span class="ct">26</span></a>- <a class="chip" href="/blog/tags/open-source/">Open Source<span class="ct">23</span></a>+ <a class="chip" href="/blog/tags/comparisons/">Comparisons<span class="ct">21</span></a><a class="chip" href="/blog/tags/concepts/">Concepts<span class="ct">20</span></a>@@ -192,29 +194,27 @@<a class="chip" href="/blog/tags/story/">Story<span class="ct">19</span></a>- <a class="chip" href="/blog/tags/comparisons/">Comparisons<span class="ct">18</span></a>-<a class="chip" href="/blog/tags/release/">Release<span class="ct">15</span></a>+ <a class="chip" href="/blog/tags/local-first/">Local-First<span class="ct">14</span></a>+<a class="chip" href="/blog/tags/getting-started/">Getting Started<span class="ct">13</span></a>- <a class="chip" href="/blog/tags/local-first/">Local-First<span class="ct">13</span></a>+ <a class="chip" href="/blog/tags/tools/">Tools<span class="ct">12</span></a><a class="chip" href="/blog/tags/automation/">Automation<span class="ct">12</span></a>- <a class="chip" href="/blog/tags/use-cases/">Use Cases<span class="ct">10</span></a>+ <a class="chip" href="/blog/tags/cost/">Cost<span class="ct">11</span></a>- <a class="chip" href="/blog/tags/tools/">Tools<span class="ct">10</span></a>+ <a class="chip" href="/blog/tags/use-cases/">Use Cases<span class="ct">10</span></a>- <a class="chip" href="/blog/tags/cost/">Cost<span class="ct">9</span></a>+ <a class="chip" href="/blog/tags/memory/">Memory<span class="ct">9</span></a>- <a class="chip" href="/blog/tags/memory/">Memory<span class="ct">8</span></a>+ <a class="chip" href="/blog/tags/workflow/">Workflow<span class="ct">8</span></a><a class="chip" href="/blog/tags/human-in-the-loop/">Human-in-the-Loop<span class="ct">8</span></a>- <a class="chip" href="/blog/tags/workflow/">Workflow<span class="ct">7</span></a>-- <a class="chip" href="/blog/tags/security/">Security<span class="ct">7</span></a>+ <a class="chip" href="/blog/tags/security/">Security<span class="ct">8</span></a><a class="chip" href="/blog/tags/mempalace/">MemPalace<span class="ct">6</span></a>@@ -238,6 +238,10 @@<a class="chip" href="/blog/tags/debugging/">Debugging<span class="ct">4</span></a>+ <a class="chip" href="/blog/tags/model-routing/">Model Routing<span class="ct">4</span></a>++ <a class="chip" href="/blog/tags/codex/">Codex<span class="ct">4</span></a>+<a class="chip" href="/blog/tags/cli-agents/">CLI Agents<span class="ct">4</span></a><a class="chip" href="/blog/tags/voice/">Voice<span class="ct">4</span></a>@@ -248,16 +252,12 @@<a class="chip" href="/blog/tags/terminals/">Terminals<span class="ct">3</span></a>- <a class="chip" href="/blog/tags/model-routing/">Model Routing<span class="ct">3</span></a>-<a class="chip" href="/blog/tags/agentic-ai/">Agentic AI<span class="ct">3</span></a><a class="chip" href="/blog/tags/aeo/">AEO<span class="ct">3</span></a><a class="chip" href="/blog/tags/seo/">SEO<span class="ct">3</span></a>- <a class="chip" href="/blog/tags/codex/">Codex<span class="ct">3</span></a>-<a class="chip" href="/blog/tags/launch/">Launch<span class="ct">3</span></a><a class="chip" href="/blog/tags/god/">GOD<span class="ct">2</span></a>diff --git a/docs/blog/topics/internals/index.html b/docs/blog/topics/internals/index.htmlindex fc77cee5..ba687041 100644--- a/docs/blog/topics/internals/index.html+++ b/docs/blog/topics/internals/index.html@@ -99,13 +99,13 @@<div class="filters" role="navigation" aria-label="Topics"><a class="chip" href="/blog/">All</a>- <a class="chip" href="/blog/topics/guides/">guides<span class="ct">36</span></a>+ <a class="chip" href="/blog/topics/guides/">guides<span class="ct">38</span></a><a class="chip" href="/blog/topics/concepts/">concepts<span class="ct">23</span></a>- <a class="chip" href="/blog/topics/internals/" aria-current="page">internals<span class="ct">19</span></a>+ <a class="chip" href="/blog/topics/comparisons/">comparisons<span class="ct">21</span></a>- <a class="chip" href="/blog/topics/comparisons/">comparisons<span class="ct">18</span></a>+ <a class="chip" href="/blog/topics/internals/" aria-current="page">internals<span class="ct">19</span></a><a class="chip" href="/blog/topics/story/">story<span class="ct">18</span></a>diff --git a/docs/blog/topics/memory/index.html b/docs/blog/topics/memory/index.htmlindex 72574d81..2625df1c 100644--- a/docs/blog/topics/memory/index.html+++ b/docs/blog/topics/memory/index.html@@ -99,13 +99,13 @@<div class="filters" role="navigation" aria-label="Topics"><a class="chip" href="/blog/">All</a>- <a class="chip" href="/blog/topics/guides/">guides<span class="ct">36</span></a>+ <a class="chip" href="/blog/topics/guides/">guides<span class="ct">38</span></a><a class="chip" href="/blog/topics/concepts/">concepts<span class="ct">23</span></a>- <a class="chip" href="/blog/topics/internals/">internals<span class="ct">19</span></a>+ <a class="chip" href="/blog/topics/comparisons/">comparisons<span class="ct">21</span></a>- <a class="chip" href="/blog/topics/comparisons/">comparisons<span class="ct">18</span></a>+ <a class="chip" href="/blog/topics/internals/">internals<span class="ct">19</span></a><a class="chip" href="/blog/topics/story/">story<span class="ct">18</span></a>diff --git a/docs/blog/topics/orchestration/index.html b/docs/blog/topics/orchestration/index.htmlindex d50925a7..be8d4e5c 100644--- a/docs/blog/topics/orchestration/index.html+++ b/docs/blog/topics/orchestration/index.html@@ -99,13 +99,13 @@<div class="filters" role="navigation" aria-label="Topics"><a class="chip" href="/blog/">All</a>- <a class="chip" href="/blog/topics/guides/">guides<span class="ct">36</span></a>+ <a class="chip" href="/blog/topics/guides/">guides<span class="ct">38</span></a><a class="chip" href="/blog/topics/concepts/">concepts<span class="ct">23</span></a>- <a class="chip" href="/blog/topics/internals/">internals<span class="ct">19</span></a>+ <a class="chip" href="/blog/topics/comparisons/">comparisons<span class="ct">21</span></a>- <a class="chip" href="/blog/topics/comparisons/">comparisons<span class="ct">18</span></a>+ <a class="chip" href="/blog/topics/internals/">internals<span class="ct">19</span></a><a class="chip" href="/blog/topics/story/">story<span class="ct">18</span></a>diff --git a/docs/blog/topics/story/index.html b/docs/blog/topics/story/index.htmlindex d631de29..163ebedd 100644--- a/docs/blog/topics/story/index.html+++ b/docs/blog/topics/story/index.html@@ -99,13 +99,13 @@<div class="filters" role="navigation" aria-label="Topics"><a class="chip" href="/blog/">All</a>- <a class="chip" href="/blog/topics/guides/">guides<span class="ct">36</span></a>+ <a class="chip" href="/blog/topics/guides/">guides<span class="ct">38</span></a><a class="chip" href="/blog/topics/concepts/">concepts<span class="ct">23</span></a>- <a class="chip" href="/blog/topics/internals/">internals<span class="ct">19</span></a>+ <a class="chip" href="/blog/topics/comparisons/">comparisons<span class="ct">21</span></a>- <a class="chip" href="/blog/topics/comparisons/">comparisons<span class="ct">18</span></a>+ <a class="chip" href="/blog/topics/internals/">internals<span class="ct">19</span></a><a class="chip" href="/blog/topics/story/" aria-current="page">story<span class="ct">18</span></a>diff --git a/docs/blog/topics/use-cases/index.html b/docs/blog/topics/use-cases/index.htmlindex 31145899..c060655f 100644--- a/docs/blog/topics/use-cases/index.html+++ b/docs/blog/topics/use-cases/index.html@@ -99,13 +99,13 @@<div class="filters" role="navigation" aria-label="Topics"><a class="chip" href="/blog/">All</a>- <a class="chip" href="/blog/topics/guides/">guides<span class="ct">36</span></a>+ <a class="chip" href="/blog/topics/guides/">guides<span class="ct">38</span></a><a class="chip" href="/blog/topics/concepts/">concepts<span class="ct">23</span></a>- <a class="chip" href="/blog/topics/internals/">internals<span class="ct">19</span></a>+ <a class="chip" href="/blog/topics/comparisons/">comparisons<span class="ct">21</span></a>- <a class="chip" href="/blog/topics/comparisons/">comparisons<span class="ct">18</span></a>+ <a class="chip" href="/blog/topics/internals/">internals<span class="ct">19</span></a><a class="chip" href="/blog/topics/story/">story<span class="ct">18</span></a>diff --git a/docs/blog/trigger-ai-agents-from-github-webhook/index.html b/docs/blog/trigger-ai-agents-from-github-webhook/index.htmlindex e2d2c776..182fae5d 100644--- a/docs/blog/trigger-ai-agents-from-github-webhook/index.html+++ b/docs/blog/trigger-ai-agents-from-github-webhook/index.html@@ -357,50 +357,50 @@ open source.</p><h2>Related in Guides</h2><div class="post-grid"><article class="card t-guides">- <a class="thumb t-guides" href="/blog/how-to-use-claude-code-plan-mode/" aria-hidden="true" tabindex="-1"><img src="/blog/assets/media/how-to-use-claude-code-plan-mode/hero.png" alt="" loading="lazy" decoding="async" /></a>+ <a class="thumb t-guides" href="/blog/claude-code-max-plan-tips/" aria-hidden="true" tabindex="-1"><img src="/blog/assets/media/claude-code-max-plan-tips/hero.png" alt="" loading="lazy" decoding="async" /></a><div class="body"><div class="meta">- <time datetime="2026-09-11">Sep 11, 2026</time>+ <time datetime="2026-09-14">Sep 14, 2026</time><span class="dot" aria-hidden="true"></span><span>5 min</span></div>- <h3><a href="/blog/how-to-use-claude-code-plan-mode/">How to Use Claude Code Plan Mode</a></h3>- <p class="dek">How Claude Code's plan mode works: turning it on, what it blocks, what a real headless plan mode run prints, and how to leave it.</p>+ <h3><a href="/blog/claude-code-max-plan-tips/">How to Get the Most Out of Your Claude Code Max Plan</a></h3>+ <p class="dek">Stretch a Claude Code Max plan: model choice, context hygiene, prompt caching, subagents and unattended runs, checked against Anthropic's own pages.</p><div class="foot"><span class="tag kind">Guides</span>- <a class="more" href="/blog/how-to-use-claude-code-plan-mode/" aria-label="Read: How to Use Claude Code Plan Mode">Read →</a>+ <a class="more" href="/blog/claude-code-max-plan-tips/" aria-label="Read: How to Get the Most Out of Your Claude Code Max Plan">Read →</a></div></div></article><article class="card t-guides">- <a class="thumb t-guides" href="/blog/how-to-add-an-mcp-server-to-claude-code/" aria-hidden="true" tabindex="-1"><img src="/blog/assets/media/how-to-add-an-mcp-server-to-claude-code/hero.png" alt="" loading="lazy" decoding="async" /></a>+ <a class="thumb t-guides" href="/blog/codex-max-plan-tips/" aria-hidden="true" tabindex="-1"><img src="/blog/assets/media/codex-max-plan-tips/hero.png" alt="" loading="lazy" decoding="async" /></a><div class="body"><div class="meta">- <time datetime="2026-09-10">Sep 10, 2026</time>+ <time datetime="2026-09-14">Sep 14, 2026</time><span class="dot" aria-hidden="true"></span><span>5 min</span></div>- <h3><a href="/blog/how-to-add-an-mcp-server-to-claude-code/">How to Add an MCP Server to Claude Code</a></h3>- <p class="dek">The claude mcp add command, its scope flag, editing .mcp.json by hand, and how Munder Difflin's Capabilities screen grants an MCP server to one agent at a time.</p>+ <h3><a href="/blog/codex-max-plan-tips/">How to Make the Most of Your Codex Max Plan</a></h3>+ <p class="dek">There is no Codex Max plan. What ChatGPT Pro 5x and 20x give you in Codex, how the weekly limit works, and how to stretch it.</p><div class="foot"><span class="tag kind">Guides</span>- <a class="more" href="/blog/how-to-add-an-mcp-server-to-claude-code/" aria-label="Read: How to Add an MCP Server to Claude Code">Read →</a>+ <a class="more" href="/blog/codex-max-plan-tips/" aria-label="Read: How to Make the Most of Your Codex Max Plan">Read →</a></div></div></article><article class="card t-guides">- <a class="thumb t-guides" href="/blog/command-center-guide/" aria-hidden="true" tabindex="-1"><img src="/blog/assets/media/command-center-guide/hero.png" alt="" loading="lazy" decoding="async" /></a>+ <a class="thumb t-guides" href="/blog/how-to-use-claude-code-plan-mode/" aria-hidden="true" tabindex="-1"><img src="/blog/assets/media/how-to-use-claude-code-plan-mode/hero.png" alt="" loading="lazy" decoding="async" /></a><div class="body"><div class="meta">- <time datetime="2026-07-03">Jul 3, 2026</time>+ <time datetime="2026-09-11">Sep 11, 2026</time><span class="dot" aria-hidden="true"></span>- <span>4 min</span>+ <span>5 min</span></div>- <h3><a href="/blog/command-center-guide/">The Command Center: Kanban, Fleet and Budgets in One Place</a></h3>- <p class="dek">A guide to Munder Difflin's Command Center in 0.5.2: the kanban with task dependencies, the ask me tab, triggers, memory, live token use against each agent's budget, and when to watch the board instead of the floor.</p>+ <h3><a href="/blog/how-to-use-claude-code-plan-mode/">How to Use Claude Code Plan Mode</a></h3>+ <p class="dek">How Claude Code's plan mode works: turning it on, what it blocks, what a real headless plan mode run prints, and how to leave it.</p><div class="foot"><span class="tag kind">Guides</span>- <a class="more" href="/blog/command-center-guide/" aria-label="Read: The Command Center: Kanban, Fleet and Budgets in One Place">Read →</a>+ <a class="more" href="/blog/how-to-use-claude-code-plan-mode/" aria-label="Read: How to Use Claude Code Plan Mode">Read →</a></div></div></article>diff --git a/docs/blog/trigger-ai-agents-from-slack/index.html b/docs/blog/trigger-ai-agents-from-slack/index.htmlindex bea11fba..b5f6599a 100644--- a/docs/blog/trigger-ai-agents-from-slack/index.html+++ b/docs/blog/trigger-ai-agents-from-slack/index.html@@ -304,50 +304,50 @@ it’s free and open source.</p><h2>Related in Guides</h2><div class="post-grid"><article class="card t-guides">- <a class="thumb t-guides" href="/blog/how-to-use-claude-code-plan-mode/" aria-hidden="true" tabindex="-1"><img src="/blog/assets/media/how-to-use-claude-code-plan-mode/hero.png" alt="" loading="lazy" decoding="async" /></a>+ <a class="thumb t-guides" href="/blog/claude-code-max-plan-tips/" aria-hidden="true" tabindex="-1"><img src="/blog/assets/media/claude-code-max-plan-tips/hero.png" alt="" loading="lazy" decoding="async" /></a><div class="body"><div class="meta">- <time datetime="2026-09-11">Sep 11, 2026</time>+ <time datetime="2026-09-14">Sep 14, 2026</time><span class="dot" aria-hidden="true"></span><span>5 min</span></div>- <h3><a href="/blog/how-to-use-claude-code-plan-mode/">How to Use Claude Code Plan Mode</a></h3>- <p class="dek">How Claude Code's plan mode works: turning it on, what it blocks, what a real headless plan mode run prints, and how to leave it.</p>+ <h3><a href="/blog/claude-code-max-plan-tips/">How to Get the Most Out of Your Claude Code Max Plan</a></h3>+ <p class="dek">Stretch a Claude Code Max plan: model choice, context hygiene, prompt caching, subagents and unattended runs, checked against Anthropic's own pages.</p><div class="foot"><span class="tag kind">Guides</span>- <a class="more" href="/blog/how-to-use-claude-code-plan-mode/" aria-label="Read: How to Use Claude Code Plan Mode">Read →</a>+ <a class="more" href="/blog/claude-code-max-plan-tips/" aria-label="Read: How to Get the Most Out of Your Claude Code Max Plan">Read →</a></div></div></article><article class="card t-guides">- <a class="thumb t-guides" href="/blog/how-to-add-an-mcp-server-to-claude-code/" aria-hidden="true" tabindex="-1"><img src="/blog/assets/media/how-to-add-an-mcp-server-to-claude-code/hero.png" alt="" loading="lazy" decoding="async" /></a>+ <a class="thumb t-guides" href="/blog/codex-max-plan-tips/" aria-hidden="true" tabindex="-1"><img src="/blog/assets/media/codex-max-plan-tips/hero.png" alt="" loading="lazy" decoding="async" /></a><div class="body"><div class="meta">- <time datetime="2026-09-10">Sep 10, 2026</time>+ <time datetime="2026-09-14">Sep 14, 2026</time><span class="dot" aria-hidden="true"></span><span>5 min</span></div>- <h3><a href="/blog/how-to-add-an-mcp-server-to-claude-code/">How to Add an MCP Server to Claude Code</a></h3>- <p class="dek">The claude mcp add command, its scope flag, editing .mcp.json by hand, and how Munder Difflin's Capabilities screen grants an MCP server to one agent at a time.</p>+ <h3><a href="/blog/codex-max-plan-tips/">How to Make the Most of Your Codex Max Plan</a></h3>+ <p class="dek">There is no Codex Max plan. What ChatGPT Pro 5x and 20x give you in Codex, how the weekly limit works, and how to stretch it.</p><div class="foot"><span class="tag kind">Guides</span>- <a class="more" href="/blog/how-to-add-an-mcp-server-to-claude-code/" aria-label="Read: How to Add an MCP Server to Claude Code">Read →</a>+ <a class="more" href="/blog/codex-max-plan-tips/" aria-label="Read: How to Make the Most of Your Codex Max Plan">Read →</a></div></div></article><article class="card t-guides">- <a class="thumb t-guides" href="/blog/command-center-guide/" aria-hidden="true" tabindex="-1"><img src="/blog/assets/media/command-center-guide/hero.png" alt="" loading="lazy" decoding="async" /></a>+ <a class="thumb t-guides" href="/blog/how-to-use-claude-code-plan-mode/" aria-hidden="true" tabindex="-1"><img src="/blog/assets/media/how-to-use-claude-code-plan-mode/hero.png" alt="" loading="lazy" decoding="async" /></a><div class="body"><div class="meta">- <time datetime="2026-07-03">Jul 3, 2026</time>+ <time datetime="2026-09-11">Sep 11, 2026</time><span class="dot" aria-hidden="true"></span>- <span>4 min</span>+ <span>5 min</span></div>- <h3><a href="/blog/command-center-guide/">The Command Center: Kanban, Fleet and Budgets in One Place</a></h3>- <p class="dek">A guide to Munder Difflin's Command Center in 0.5.2: the kanban with task dependencies, the ask me tab, triggers, memory, live token use against each agent's budget, and when to watch the board instead of the floor.</p>+ <h3><a href="/blog/how-to-use-claude-code-plan-mode/">How to Use Claude Code Plan Mode</a></h3>+ <p class="dek">How Claude Code's plan mode works: turning it on, what it blocks, what a real headless plan mode run prints, and how to leave it.</p><div class="foot"><span class="tag kind">Guides</span>- <a class="more" href="/blog/command-center-guide/" aria-label="Read: The Command Center: Kanban, Fleet and Budgets in One Place">Read →</a>+ <a class="more" href="/blog/how-to-use-claude-code-plan-mode/" aria-label="Read: How to Use Claude Code Plan Mode">Read →</a></div></div></article>diff --git a/docs/blog/vibe-kanban-alternative/index.html b/docs/blog/vibe-kanban-alternative/index.htmlindex 2fbd3eaa..0907dad2 100644--- a/docs/blog/vibe-kanban-alternative/index.html+++ b/docs/blog/vibe-kanban-alternative/index.html@@ -254,50 +254,50 @@ routing happen for you — free and open source.</p><h2>Related in Comparisons</h2><div class="post-grid"><article class="card t-comparisons">- <a class="thumb t-comparisons" href="/blog/codex-cli-vs-claude-code/" aria-hidden="true" tabindex="-1"><img src="/blog/assets/media/codex-cli-vs-claude-code/hero.png" alt="" loading="lazy" decoding="async" /></a>+ <a class="thumb t-comparisons" href="/blog/grok-bot-alternatives/" aria-hidden="true" tabindex="-1"><img src="/blog/assets/media/grok-bot-alternatives/hero.png" alt="" loading="lazy" decoding="async" /></a><div class="body"><div class="meta">- <time datetime="2026-09-10">Sep 10, 2026</time>+ <time datetime="2026-09-14">Sep 14, 2026</time><span class="dot" aria-hidden="true"></span><span>5 min</span></div>- <h3><a href="/blog/codex-cli-vs-claude-code/">Codex CLI vs Claude Code</a></h3>- <p class="dek">Codex CLI and Claude Code compared firsthand: sandbox and approval flags, AGENTS.md vs CLAUDE.md, real pricing, and where each terminal agent wins.</p>+ <h3><a href="/blog/grok-bot-alternatives/">Grok Bot Alternatives: Six Picks, Grouped by What You Want</a></h3>+ <p class="dek">Grok Bot runs every Bot on one shared cloud computer. Six alternatives checked on 14 Sep 2026, grouped by hosting, privacy and model choice.</p><div class="foot"><span class="tag kind">Comparisons</span>- <a class="more" href="/blog/codex-cli-vs-claude-code/" aria-label="Read: Codex CLI vs Claude Code">Read →</a>+ <a class="more" href="/blog/grok-bot-alternatives/" aria-label="Read: Grok Bot Alternatives: Six Picks, Grouped by What You Want">Read →</a></div></div></article><article class="card t-comparisons">- <a class="thumb t-comparisons" href="/blog/qm-vs-munder-difflin/" aria-hidden="true" tabindex="-1"><img src="/blog/assets/media/qm-vs-munder-difflin/hero.png" alt="" loading="lazy" decoding="async" /></a>+ <a class="thumb t-comparisons" href="/blog/herdr-alternatives/" aria-hidden="true" tabindex="-1"><img src="/blog/assets/media/herdr-alternatives/hero.png" alt="" loading="lazy" decoding="async" /></a><div class="body"><div class="meta">- <time datetime="2026-08-06">Aug 6, 2026</time>+ <time datetime="2026-09-14">Sep 14, 2026</time><span class="dot" aria-hidden="true"></span>- <span>4 min</span>+ <span>5 min</span></div>- <h3><a href="/blog/qm-vs-munder-difflin/">qm vs Munder Difflin: YC's Multiplayer Harness or an Office of Your Clones?</a></h3>- <p class="dek">An honest September 2026 comparison of YC's qm and Munder Difflin. qm is a multiplayer agent harness a company deploys for Slack and the web. Munder Difflin runs an office of your clones on your own machine, with Teams to connect them.</p>+ <h3><a href="/blog/herdr-alternatives/">Herdr Alternatives: What to Pick and Who Each One Fits</a></h3>+ <p class="dek">Herdr alternatives checked on 14 Sep 2026: tmux, Claude Squad, cmux, Orca, Conductor, Superset, Emdash and Munder Difflin, and who each fits.</p><div class="foot"><span class="tag kind">Comparisons</span>- <a class="more" href="/blog/qm-vs-munder-difflin/" aria-label="Read: qm vs Munder Difflin: YC's Multiplayer Harness or an Office of Your Clones?">Read →</a>+ <a class="more" href="/blog/herdr-alternatives/" aria-label="Read: Herdr Alternatives: What to Pick and Who Each One Fits">Read →</a></div></div></article><article class="card t-comparisons">- <a class="thumb t-comparisons" href="/blog/crewai-autogen-vs-a-local-agent-harness/" aria-hidden="true" tabindex="-1"><img src="/blog/assets/media/crewai-autogen-vs-a-local-agent-harness/hero.png" alt="" loading="lazy" decoding="async" /></a>+ <a class="thumb t-comparisons" href="/blog/omniagent-alternatives/" aria-hidden="true" tabindex="-1"><span class="thumb-ph"><em class="ph-glyph" aria-hidden="true">✶</em><span>COMPARISONS</span></span></a><div class="body"><div class="meta">- <time datetime="2026-07-03">Jul 3, 2026</time>+ <time datetime="2026-09-14">Sep 14, 2026</time><span class="dot" aria-hidden="true"></span><span>5 min</span></div>- <h3><a href="/blog/crewai-autogen-vs-a-local-agent-harness/">CrewAI and AutoGen vs a Local Agent Harness: Framework or App?</a></h3>- <p class="dek">CrewAI, AutoGen (now Microsoft Agent Framework), and LangGraph are frameworks — Python you write to build your own agent system. A multi-agent harness is an app you download that runs a team on your repos today. Here's how to tell which one you actually need.</p>+ <h3><a href="/blog/omniagent-alternatives/">OmniAgent Alternatives: What to Use Instead of Databricks Omnigent</a></h3>+ <p class="dek">OmniAgent is really Omnigent, the open source meta harness from Databricks. Alternatives checked on 14 Sep 2026, and who each one fits.</p><div class="foot"><span class="tag kind">Comparisons</span>- <a class="more" href="/blog/crewai-autogen-vs-a-local-agent-harness/" aria-label="Read: CrewAI and AutoGen vs a Local Agent Harness: Framework or App?">Read →</a>+ <a class="more" href="/blog/omniagent-alternatives/" aria-label="Read: OmniAgent Alternatives: What to Use Instead of Databricks Omnigent">Read →</a></div></div></article>diff --git a/docs/blog/whats-new-in-agentic-ai-june-2026/index.html b/docs/blog/whats-new-in-agentic-ai-june-2026/index.htmlindex 88711732..10cee6b0 100644--- a/docs/blog/whats-new-in-agentic-ai-june-2026/index.html+++ b/docs/blog/whats-new-in-agentic-ai-june-2026/index.html@@ -364,50 +364,50 @@ hive run; it’s free and open source.</p><h2>Related in Guides</h2><div class="post-grid"><article class="card t-guides">- <a class="thumb t-guides" href="/blog/how-to-use-claude-code-plan-mode/" aria-hidden="true" tabindex="-1"><img src="/blog/assets/media/how-to-use-claude-code-plan-mode/hero.png" alt="" loading="lazy" decoding="async" /></a>+ <a class="thumb t-guides" href="/blog/claude-code-max-plan-tips/" aria-hidden="true" tabindex="-1"><img src="/blog/assets/media/claude-code-max-plan-tips/hero.png" alt="" loading="lazy" decoding="async" /></a><div class="body"><div class="meta">- <time datetime="2026-09-11">Sep 11, 2026</time>+ <time datetime="2026-09-14">Sep 14, 2026</time><span class="dot" aria-hidden="true"></span><span>5 min</span></div>- <h3><a href="/blog/how-to-use-claude-code-plan-mode/">How to Use Claude Code Plan Mode</a></h3>- <p class="dek">How Claude Code's plan mode works: turning it on, what it blocks, what a real headless plan mode run prints, and how to leave it.</p>+ <h3><a href="/blog/claude-code-max-plan-tips/">How to Get the Most Out of Your Claude Code Max Plan</a></h3>+ <p class="dek">Stretch a Claude Code Max plan: model choice, context hygiene, prompt caching, subagents and unattended runs, checked against Anthropic's own pages.</p><div class="foot"><span class="tag kind">Guides</span>- <a class="more" href="/blog/how-to-use-claude-code-plan-mode/" aria-label="Read: How to Use Claude Code Plan Mode">Read →</a>+ <a class="more" href="/blog/claude-code-max-plan-tips/" aria-label="Read: How to Get the Most Out of Your Claude Code Max Plan">Read →</a></div></div></article><article class="card t-guides">- <a class="thumb t-guides" href="/blog/how-to-add-an-mcp-server-to-claude-code/" aria-hidden="true" tabindex="-1"><img src="/blog/assets/media/how-to-add-an-mcp-server-to-claude-code/hero.png" alt="" loading="lazy" decoding="async" /></a>+ <a class="thumb t-guides" href="/blog/codex-max-plan-tips/" aria-hidden="true" tabindex="-1"><img src="/blog/assets/media/codex-max-plan-tips/hero.png" alt="" loading="lazy" decoding="async" /></a><div class="body"><div class="meta">- <time datetime="2026-09-10">Sep 10, 2026</time>+ <time datetime="2026-09-14">Sep 14, 2026</time><span class="dot" aria-hidden="true"></span><span>5 min</span></div>- <h3><a href="/blog/how-to-add-an-mcp-server-to-claude-code/">How to Add an MCP Server to Claude Code</a></h3>- <p class="dek">The claude mcp add command, its scope flag, editing .mcp.json by hand, and how Munder Difflin's Capabilities screen grants an MCP server to one agent at a time.</p>+ <h3><a href="/blog/codex-max-plan-tips/">How to Make the Most of Your Codex Max Plan</a></h3>+ <p class="dek">There is no Codex Max plan. What ChatGPT Pro 5x and 20x give you in Codex, how the weekly limit works, and how to stretch it.</p><div class="foot"><span class="tag kind">Guides</span>- <a class="more" href="/blog/how-to-add-an-mcp-server-to-claude-code/" aria-label="Read: How to Add an MCP Server to Claude Code">Read →</a>+ <a class="more" href="/blog/codex-max-plan-tips/" aria-label="Read: How to Make the Most of Your Codex Max Plan">Read →</a></div></div></article><article class="card t-guides">- <a class="thumb t-guides" href="/blog/command-center-guide/" aria-hidden="true" tabindex="-1"><img src="/blog/assets/media/command-center-guide/hero.png" alt="" loading="lazy" decoding="async" /></a>+ <a class="thumb t-guides" href="/blog/how-to-use-claude-code-plan-mode/" aria-hidden="true" tabindex="-1"><img src="/blog/assets/media/how-to-use-claude-code-plan-mode/hero.png" alt="" loading="lazy" decoding="async" /></a><div class="body"><div class="meta">- <time datetime="2026-07-03">Jul 3, 2026</time>+ <time datetime="2026-09-11">Sep 11, 2026</time><span class="dot" aria-hidden="true"></span>- <span>4 min</span>+ <span>5 min</span></div>- <h3><a href="/blog/command-center-guide/">The Command Center: Kanban, Fleet and Budgets in One Place</a></h3>- <p class="dek">A guide to Munder Difflin's Command Center in 0.5.2: the kanban with task dependencies, the ask me tab, triggers, memory, live token use against each agent's budget, and when to watch the board instead of the floor.</p>+ <h3><a href="/blog/how-to-use-claude-code-plan-mode/">How to Use Claude Code Plan Mode</a></h3>+ <p class="dek">How Claude Code's plan mode works: turning it on, what it blocks, what a real headless plan mode run prints, and how to leave it.</p><div class="foot"><span class="tag kind">Guides</span>- <a class="more" href="/blog/command-center-guide/" aria-label="Read: The Command Center: Kanban, Fleet and Budgets in One Place">Read →</a>+ <a class="more" href="/blog/how-to-use-claude-code-plan-mode/" aria-label="Read: How to Use Claude Code Plan Mode">Read →</a></div></div></article>diff --git a/docs/blog/why-local-first-matters-for-ai-agents/index.html b/docs/blog/why-local-first-matters-for-ai-agents/index.htmlindex 378b3c52..bd914619 100644--- a/docs/blog/why-local-first-matters-for-ai-agents/index.html+++ b/docs/blog/why-local-first-matters-for-ai-agents/index.html@@ -204,7 +204,7 @@ agents to a team, that difference compounds.</p><h2 id="what-you-give-up-in-the-cloud" tabindex="-1">What you give up in the cloud <a class="anchor" href="#what-you-give-up-in-the-cloud" aria-hidden="true">#</a></h2><p>It’s only fair to name the trade. Cloud platforms can offer zero-setup onboarding, managed scaling,and team features out of the box. If you need a hosted, shared, always-on service for a distributed-team, that convenience is real.</p>+team, that convenience is real. The same trade shows up in personal assistants, as our look at <a href="/blog/grok-bot-alternatives/">Grok Bot alternatives</a> shows.</p><p>But for an individual developer or a small team running agents against their own code, theconvenience rarely outweighs handing over control, privacy, and predictable cost. You can have thecoordination <em>and</em> keep it local.</p>diff --git a/docs/blog/your-first-hour-with-munder-difflin/index.html b/docs/blog/your-first-hour-with-munder-difflin/index.htmlindex 09dfad46..e37ac8b6 100644--- a/docs/blog/your-first-hour-with-munder-difflin/index.html+++ b/docs/blog/your-first-hour-with-munder-difflin/index.html@@ -326,50 +326,50 @@ schedule. That is the whole distance from “a CLI in a terminal” to “an off<h2>Related in Guides</h2><div class="post-grid"><article class="card t-guides">- <a class="thumb t-guides" href="/blog/how-to-use-claude-code-plan-mode/" aria-hidden="true" tabindex="-1"><img src="/blog/assets/media/how-to-use-claude-code-plan-mode/hero.png" alt="" loading="lazy" decoding="async" /></a>+ <a class="thumb t-guides" href="/blog/claude-code-max-plan-tips/" aria-hidden="true" tabindex="-1"><img src="/blog/assets/media/claude-code-max-plan-tips/hero.png" alt="" loading="lazy" decoding="async" /></a><div class="body"><div class="meta">- <time datetime="2026-09-11">Sep 11, 2026</time>+ <time datetime="2026-09-14">Sep 14, 2026</time><span class="dot" aria-hidden="true"></span><span>5 min</span></div>- <h3><a href="/blog/how-to-use-claude-code-plan-mode/">How to Use Claude Code Plan Mode</a></h3>- <p class="dek">How Claude Code's plan mode works: turning it on, what it blocks, what a real headless plan mode run prints, and how to leave it.</p>+ <h3><a href="/blog/claude-code-max-plan-tips/">How to Get the Most Out of Your Claude Code Max Plan</a></h3>+ <p class="dek">Stretch a Claude Code Max plan: model choice, context hygiene, prompt caching, subagents and unattended runs, checked against Anthropic's own pages.</p><div class="foot"><span class="tag kind">Guides</span>- <a class="more" href="/blog/how-to-use-claude-code-plan-mode/" aria-label="Read: How to Use Claude Code Plan Mode">Read →</a>+ <a class="more" href="/blog/claude-code-max-plan-tips/" aria-label="Read: How to Get the Most Out of Your Claude Code Max Plan">Read →</a></div></div></article><article class="card t-guides">- <a class="thumb t-guides" href="/blog/how-to-add-an-mcp-server-to-claude-code/" aria-hidden="true" tabindex="-1"><img src="/blog/assets/media/how-to-add-an-mcp-server-to-claude-code/hero.png" alt="" loading="lazy" decoding="async" /></a>+ <a class="thumb t-guides" href="/blog/codex-max-plan-tips/" aria-hidden="true" tabindex="-1"><img src="/blog/assets/media/codex-max-plan-tips/hero.png" alt="" loading="lazy" decoding="async" /></a><div class="body"><div class="meta">- <time datetime="2026-09-10">Sep 10, 2026</time>+ <time datetime="2026-09-14">Sep 14, 2026</time><span class="dot" aria-hidden="true"></span><span>5 min</span></div>- <h3><a href="/blog/how-to-add-an-mcp-server-to-claude-code/">How to Add an MCP Server to Claude Code</a></h3>- <p class="dek">The claude mcp add command, its scope flag, editing .mcp.json by hand, and how Munder Difflin's Capabilities screen grants an MCP server to one agent at a time.</p>+ <h3><a href="/blog/codex-max-plan-tips/">How to Make the Most of Your Codex Max Plan</a></h3>+ <p class="dek">There is no Codex Max plan. What ChatGPT Pro 5x and 20x give you in Codex, how the weekly limit works, and how to stretch it.</p><div class="foot"><span class="tag kind">Guides</span>- <a class="more" href="/blog/how-to-add-an-mcp-server-to-claude-code/" aria-label="Read: How to Add an MCP Server to Claude Code">Read →</a>+ <a class="more" href="/blog/codex-max-plan-tips/" aria-label="Read: How to Make the Most of Your Codex Max Plan">Read →</a></div></div></article><article class="card t-guides">- <a class="thumb t-guides" href="/blog/command-center-guide/" aria-hidden="true" tabindex="-1"><img src="/blog/assets/media/command-center-guide/hero.png" alt="" loading="lazy" decoding="async" /></a>+ <a class="thumb t-guides" href="/blog/how-to-use-claude-code-plan-mode/" aria-hidden="true" tabindex="-1"><img src="/blog/assets/media/how-to-use-claude-code-plan-mode/hero.png" alt="" loading="lazy" decoding="async" /></a><div class="body"><div class="meta">- <time datetime="2026-07-03">Jul 3, 2026</time>+ <time datetime="2026-09-11">Sep 11, 2026</time><span class="dot" aria-hidden="true"></span>- <span>4 min</span>+ <span>5 min</span></div>- <h3><a href="/blog/command-center-guide/">The Command Center: Kanban, Fleet and Budgets in One Place</a></h3>- <p class="dek">A guide to Munder Difflin's Command Center in 0.5.2: the kanban with task dependencies, the ask me tab, triggers, memory, live token use against each agent's budget, and when to watch the board instead of the floor.</p>+ <h3><a href="/blog/how-to-use-claude-code-plan-mode/">How to Use Claude Code Plan Mode</a></h3>+ <p class="dek">How Claude Code's plan mode works: turning it on, what it blocks, what a real headless plan mode run prints, and how to leave it.</p><div class="foot"><span class="tag kind">Guides</span>- <a class="more" href="/blog/command-center-guide/" aria-label="Read: The Command Center: Kanban, Fleet and Budgets in One Place">Read →</a>+ <a class="more" href="/blog/how-to-use-claude-code-plan-mode/" aria-label="Read: How to Use Claude Code Plan Mode">Read →</a></div></div></article>diff --git a/docs/sitemap.xml b/docs/sitemap.xmlindex b587b9db..6826f02c 100644--- a/docs/sitemap.xml+++ b/docs/sitemap.xml@@ -10,7 +10,7 @@<urlset xmlns="http://www.sitemaps.org/schemas/sitemap/0.9"><url><loc>https://munderdiffl.in/</loc>- <lastmod>2026-09-11</lastmod>+ <lastmod>2026-09-14</lastmod><changefreq>weekly</changefreq><priority>1.0</priority></url>@@ -20,6 +20,36 @@<url><loc>https://munderdiffl.in/blog/</loc><changefreq>daily</changefreq><priority>0.9</priority></url><url><loc>https://munderdiffl.in/blog/topics/</loc><changefreq>weekly</changefreq><priority>0.6</priority></url><url><loc>https://munderdiffl.in/blog/about/</loc><changefreq>monthly</changefreq><priority>0.4</priority></url>+ <url>+ <loc>https://munderdiffl.in/blog/claude-code-max-plan-tips/</loc>+ <lastmod>2026-09-14</lastmod>+ <changefreq>monthly</changefreq>+ <priority>0.8</priority>+ </url>+ <url>+ <loc>https://munderdiffl.in/blog/codex-max-plan-tips/</loc>+ <lastmod>2026-09-14</lastmod>+ <changefreq>monthly</changefreq>+ <priority>0.8</priority>+ </url>+ <url>+ <loc>https://munderdiffl.in/blog/grok-bot-alternatives/</loc>+ <lastmod>2026-09-14</lastmod>+ <changefreq>monthly</changefreq>+ <priority>0.8</priority>+ </url>+ <url>+ <loc>https://munderdiffl.in/blog/herdr-alternatives/</loc>+ <lastmod>2026-09-14</lastmod>+ <changefreq>monthly</changefreq>+ <priority>0.8</priority>+ </url>+ <url>+ <loc>https://munderdiffl.in/blog/omniagent-alternatives/</loc>+ <lastmod>2026-09-14</lastmod>+ <changefreq>monthly</changefreq>+ <priority>0.8</priority>+ </url><url><loc>https://munderdiffl.in/blog/how-to-use-claude-code-plan-mode/</loc><lastmod>2026-09-11</lastmod>@@ -844,31 +874,31 @@</url><url><loc>https://munderdiffl.in/blog/topics/guides/</loc><changefreq>weekly</changefreq><priority>0.5</priority></url><url><loc>https://munderdiffl.in/blog/topics/concepts/</loc><changefreq>weekly</changefreq><priority>0.5</priority></url>- <url><loc>https://munderdiffl.in/blog/topics/internals/</loc><changefreq>weekly</changefreq><priority>0.5</priority></url><url><loc>https://munderdiffl.in/blog/topics/comparisons/</loc><changefreq>weekly</changefreq><priority>0.5</priority></url>+ <url><loc>https://munderdiffl.in/blog/topics/internals/</loc><changefreq>weekly</changefreq><priority>0.5</priority></url><url><loc>https://munderdiffl.in/blog/topics/story/</loc><changefreq>weekly</changefreq><priority>0.5</priority></url><url><loc>https://munderdiffl.in/blog/topics/orchestration/</loc><changefreq>weekly</changefreq><priority>0.5</priority></url><url><loc>https://munderdiffl.in/blog/topics/use-cases/</loc><changefreq>weekly</changefreq><priority>0.5</priority></url><url><loc>https://munderdiffl.in/blog/topics/memory/</loc><changefreq>weekly</changefreq><priority>0.5</priority></url><url><loc>https://munderdiffl.in/blog/tags/multi-agent/</loc><changefreq>weekly</changefreq><priority>0.3</priority></url><url><loc>https://munderdiffl.in/blog/tags/claude-code/</loc><changefreq>weekly</changefreq><priority>0.3</priority></url>- <url><loc>https://munderdiffl.in/blog/tags/internals/</loc><changefreq>weekly</changefreq><priority>0.3</priority></url><url><loc>https://munderdiffl.in/blog/tags/guides/</loc><changefreq>weekly</changefreq><priority>0.3</priority></url>+ <url><loc>https://munderdiffl.in/blog/tags/internals/</loc><changefreq>weekly</changefreq><priority>0.3</priority></url><url><loc>https://munderdiffl.in/blog/tags/open-source/</loc><changefreq>weekly</changefreq><priority>0.3</priority></url>+ <url><loc>https://munderdiffl.in/blog/tags/comparisons/</loc><changefreq>weekly</changefreq><priority>0.3</priority></url><url><loc>https://munderdiffl.in/blog/tags/concepts/</loc><changefreq>weekly</changefreq><priority>0.3</priority></url><url><loc>https://munderdiffl.in/blog/tags/orchestration/</loc><changefreq>weekly</changefreq><priority>0.3</priority></url><url><loc>https://munderdiffl.in/blog/tags/story/</loc><changefreq>weekly</changefreq><priority>0.3</priority></url>- <url><loc>https://munderdiffl.in/blog/tags/comparisons/</loc><changefreq>weekly</changefreq><priority>0.3</priority></url><url><loc>https://munderdiffl.in/blog/tags/release/</loc><changefreq>weekly</changefreq><priority>0.3</priority></url>- <url><loc>https://munderdiffl.in/blog/tags/getting-started/</loc><changefreq>weekly</changefreq><priority>0.3</priority></url><url><loc>https://munderdiffl.in/blog/tags/local-first/</loc><changefreq>weekly</changefreq><priority>0.3</priority></url>- <url><loc>https://munderdiffl.in/blog/tags/automation/</loc><changefreq>weekly</changefreq><priority>0.3</priority></url>- <url><loc>https://munderdiffl.in/blog/tags/use-cases/</loc><changefreq>weekly</changefreq><priority>0.3</priority></url>+ <url><loc>https://munderdiffl.in/blog/tags/getting-started/</loc><changefreq>weekly</changefreq><priority>0.3</priority></url><url><loc>https://munderdiffl.in/blog/tags/tools/</loc><changefreq>weekly</changefreq><priority>0.3</priority></url>+ <url><loc>https://munderdiffl.in/blog/tags/automation/</loc><changefreq>weekly</changefreq><priority>0.3</priority></url><url><loc>https://munderdiffl.in/blog/tags/cost/</loc><changefreq>weekly</changefreq><priority>0.3</priority></url>+ <url><loc>https://munderdiffl.in/blog/tags/use-cases/</loc><changefreq>weekly</changefreq><priority>0.3</priority></url><url><loc>https://munderdiffl.in/blog/tags/memory/</loc><changefreq>weekly</changefreq><priority>0.3</priority></url>- <url><loc>https://munderdiffl.in/blog/tags/human-in-the-loop/</loc><changefreq>weekly</changefreq><priority>0.3</priority></url><url><loc>https://munderdiffl.in/blog/tags/workflow/</loc><changefreq>weekly</changefreq><priority>0.3</priority></url>+ <url><loc>https://munderdiffl.in/blog/tags/human-in-the-loop/</loc><changefreq>weekly</changefreq><priority>0.3</priority></url><url><loc>https://munderdiffl.in/blog/tags/security/</loc><changefreq>weekly</changefreq><priority>0.3</priority></url><url><loc>https://munderdiffl.in/blog/tags/mempalace/</loc><changefreq>weekly</changefreq><priority>0.3</priority></url><url><loc>https://munderdiffl.in/blog/tags/mcp/</loc><changefreq>weekly</changefreq><priority>0.3</priority></url>@@ -881,16 +911,16 @@<url><loc>https://munderdiffl.in/blog/tags/architecture/</loc><changefreq>weekly</changefreq><priority>0.3</priority></url><url><loc>https://munderdiffl.in/blog/tags/reliability/</loc><changefreq>weekly</changefreq><priority>0.3</priority></url><url><loc>https://munderdiffl.in/blog/tags/debugging/</loc><changefreq>weekly</changefreq><priority>0.3</priority></url>+ <url><loc>https://munderdiffl.in/blog/tags/model-routing/</loc><changefreq>weekly</changefreq><priority>0.3</priority></url>+ <url><loc>https://munderdiffl.in/blog/tags/codex/</loc><changefreq>weekly</changefreq><priority>0.3</priority></url><url><loc>https://munderdiffl.in/blog/tags/cli-agents/</loc><changefreq>weekly</changefreq><priority>0.3</priority></url><url><loc>https://munderdiffl.in/blog/tags/voice/</loc><changefreq>weekly</changefreq><priority>0.3</priority></url><url><loc>https://munderdiffl.in/blog/tags/engines/</loc><changefreq>weekly</changefreq><priority>0.3</priority></url><url><loc>https://munderdiffl.in/blog/tags/ide/</loc><changefreq>weekly</changefreq><priority>0.3</priority></url><url><loc>https://munderdiffl.in/blog/tags/terminals/</loc><changefreq>weekly</changefreq><priority>0.3</priority></url>- <url><loc>https://munderdiffl.in/blog/tags/model-routing/</loc><changefreq>weekly</changefreq><priority>0.3</priority></url><url><loc>https://munderdiffl.in/blog/tags/agentic-ai/</loc><changefreq>weekly</changefreq><priority>0.3</priority></url><url><loc>https://munderdiffl.in/blog/tags/aeo/</loc><changefreq>weekly</changefreq><priority>0.3</priority></url><url><loc>https://munderdiffl.in/blog/tags/seo/</loc><changefreq>weekly</changefreq><priority>0.3</priority></url>- <url><loc>https://munderdiffl.in/blog/tags/codex/</loc><changefreq>weekly</changefreq><priority>0.3</priority></url><url><loc>https://munderdiffl.in/blog/tags/launch/</loc><changefreq>weekly</changefreq><priority>0.3</priority></url><url><loc>https://munderdiffl.in/blog/tags/god/</loc><changefreq>weekly</changefreq><priority>0.3</priority></url><url><loc>https://munderdiffl.in/blog/tags/messaging/</loc><changefreq>weekly</changefreq><priority>0.3</priority></url>