Skip to content

The cross-harness, self-improving memory layer for AI agents. Join our community: https://discord.com/invite/zdNChS2fBu

docs: Beacon Cloud Pro plans, findings, and a Beacon Cloud changelog

Claude5b807ed90c87
diff --git a/docs/changelog/cli.mdx b/docs/changelog/cli.mdx
index 41c6246f..4026bd8a 100644
--- a/docs/changelog/cli.mdx
+++ b/docs/changelog/cli.mdx
@@ -9,6 +9,12 @@ Stay up to date with the latest changes to the Agent Beacon CLI.
---
+## Unreleased
+
+- **Dashboard output tokens count reasoning once** · The local dashboard's token view added reasoning tokens to output, but `gen_ai.usage.output_tokens` already includes them, so models that report reasoning had their output and total tokens overstated. Output and the total now count reasoning once, the split bar no longer shows reasoning as a separate segment, and a note below it gives the reasoning count included in output. `beacon token-usage` already counted it this way.
+
+---
+
## October 2026
### v1.3.44 · October 19, 2026
diff --git a/docs/changelog/cloud.mdx b/docs/changelog/cloud.mdx
new file mode 100644
index 00000000..5e0aaac9
--- /dev/null
+++ b/docs/changelog/cloud.mdx
@@ -0,0 +1,48 @@
+---
+title: Beacon Cloud Changelog
+description: Latest updates to Beacon Cloud at beacon.sh
+---
+
+## Latest updates
+
+Changes to the hosted Beacon Cloud dashboard, findings and MCP server at
+[beacon.sh](https://beacon.sh). Beacon Cloud updates continuously, so entries are grouped by date
+rather than version. CLI releases are in the [CLI changelog](/changelog/cli).
+
+---
+
+## October 2026
+
+### October 20, 2026
+
+- **Your first findings arrive by email** · Beacon Cloud now analyzes a new account as soon as its first sessions arrive, and sends one email with the first findings right after that analysis. Later findings go out in the daily digest on the free plan. See [Findings](/cloud/findings#your-first-findings).
+- **New devices show their upload in progress** · For a few minutes after a device connects, while its 30-day session backfill reaches the dashboard, an empty session list now says the device is connected and shows a spinner, instead of "No sessions yet".
+
+### October 19, 2026
+
+- **Beacon Cloud Pro** · Beacon Cloud stays free, and Pro ($20 a month, or $15 a month billed annually) adds unlimited findings, findings, feedback and memory over MCP, skills pulled from your sessions, the full evidence trail on every finding, real-time email alerts and priority support. The [pricing page](https://beacon.sh/pricing) compares Open Source, Beacon Cloud, Pro and Enterprise. See [Plans and pricing](/deployment/plans).
+- **Free accounts include 50 findings** · A free account gets 50 findings over its lifetime; Pro is unlimited. Once the allowance is used, new activity is no longer analyzed, while sessions keep uploading and stay searchable. Findings resume from the next new telemetry after an upgrade.
+- **Findings and memory MCP tools are part of Pro** · `beacon_findings_list`, `beacon_get_finding`, `beacon_finding_feedback` and the `beacon_memory_*` tools now need Beacon Cloud Pro. Called from a free account, they return an error naming Pro with a link to pricing, so your agent can explain. Session search, lenses and sharing stay on every plan, and an upgrade reaches your agents within a minute. See [Beacon Cloud MCP](/deployment/managed-mcp#tools).
+- **Fix prompt for an empty Agent Inventory** · When a device reports no inventory, the Agent Inventory page offers a prompt to paste into your agent to find and fix the cause.
+- **Trace Marketplace** · The Discover menu's **Agent sessions marketplace** is now **Trace Marketplace**.
+- **Setup prompt offers three plans** · The copy-and-paste setup prompt at [beacon.sh/start.md](https://beacon.sh/start.md) now offers Beacon Cloud, Beacon Cloud Pro and Local, asks whether to set up Beacon MCP and the Beacon Agent Skills before installing, and opens Beacon at the end. For Pro it opens the Billing page to finish upgrading; it never handles payment details.
+
+### October 18, 2026
+
+- **Memory over MCP** · Agents connected to [Beacon Cloud MCP](/deployment/managed-mcp#memory) can file a lesson from one of your sessions as a memory candidate once you confirm it, list and read candidates, approve, reject or supersede them, search and read approved memory, and render an approved memory as an Agent Skill (`beacon_memory_skill`) to save in your repository. The `beacon-memory-recall`, `beacon-memory-distill` and `beacon-memory-promote` skills use these tools when Beacon Cloud MCP is connected.
+
+### October 16, 2026
+
+- **Billing page** · [beacon.sh/dashboard/billing](https://beacon.sh/dashboard/billing) shows your plan, starts a Pro checkout or free trial, and cancels a subscription. A canceled subscription keeps Pro until the end of the paid period.
+- **Pricing page** · [beacon.sh/pricing](https://beacon.sh/pricing) lists the plans with a monthly and annual toggle and a full comparison table, and explains the three kinds of findings.
+- **Findings over MCP** · `beacon_findings_list`, `beacon_get_finding` and `beacon_finding_feedback` let your agent list your findings, read one with its evidence and recommendation, and record your feedback or set it resolved, dismissed or open.
+- **Findings at onboarding** · A new account's findings are produced from its first sessions instead of waiting for the next hourly run.
+- **Session History** · **Sessions** under Agent Activity is now a group; its **Session History** entry opens the session list. Existing `/dashboard/sessions` links are unchanged.
+- **Security headers** · beacon.sh, the API and the MCP host now send HSTS, `nosniff` and a referrer policy, and every page refuses to be framed.
+
+### October 15, 2026
+
+- **Download skill beside the finding title** · A skill finding's **Download skill** button now sits next to its title.
+- **MCP write access names session sharing** · The OAuth consent page and **MCP Access** now say that write access also lets an agent share your sessions, including publicly, and change or remove shared traces.
+- **A device can only share its own sessions** · An [auto-share](/sharing/agent-hooks) request sent with one device's key is honored only for a session that device recorded, and never changes the visibility of a trace that already exists.
+- **Revoked devices stay revoked** · A revoked machine can no longer enroll again under a new install id with the account token it still holds. Sign in again from your own browser, or **Reinstate device**, to allow it.
diff --git a/docs/cloud/findings.mdx b/docs/cloud/findings.mdx
new file mode 100644
index 00000000..7c2e407c
--- /dev/null
+++ b/docs/cloud/findings.mdx
@@ -0,0 +1,89 @@
+---
+title: "Findings"
+description: "Security risks, reusable workflows and habits Beacon Cloud notices in your sessions"
+---
+
+Every hour, Beacon Cloud reviews the new activity your connected devices forwarded and surfaces
+what is worth your attention as findings. They are on the **Findings** page at
+[beacon.sh/dashboard/findings](https://beacon.sh/dashboard/findings).
+
+Findings are separate from the local [`beacon scan`](/cli/scan) results, which run open
+[threat rules](/detections/index) on the machine and never leave it.
+
+## Kinds of findings
+
+| Kind | What it covers | Examples |
+| --- | --- | --- |
+| **Security** | Risky things your agents did | A secret pasted into a prompt or command, a destructive or privilege-raising command, an agent bypassing its approvals, prompt injection arriving through a tool result, a call to an unknown MCP server |
+| **Skill** | Workflows worth reusing | Steps you walk an agent through more than once, drafted as a reusable Agent Skill |
+| **Behavior** | Patterns in how you work with agents | Retry loops, abandoned sessions, approvals you always grant, expensive models used for simple tasks |
+
+Each finding shows what happened, how severe it is, which sessions and harnesses it came from,
+and a recommendation. A skill finding has a **Download skill** button that saves the drafted
+`SKILL.md`, and findings carry a prompt you can copy into your agent to fix the problem.
+
+## Review a finding
+
+- Filter the list by kind (security, skills, behavior) and severity. Findings that still need
+ review come first.
+- Open a finding to read its detail, the sessions it cites and the events it rests on. On
+ [Beacon Cloud Pro](/deployment/plans) the full evidence trail is shown.
+- Use **Mark as** to set a finding open, resolved or dismissed.
+- Mark it helpful or not helpful and add a note. The next analysis reads your feedback, so it
+ stops repeating what you rejected.
+
+A finding that recurs updates the one you already have instead of creating a duplicate.
+
+## Your first findings
+
+Beacon Cloud analyzes a new account soon after its first sessions arrive, including the 30 days of
+history a device uploads when it [connects](/cloud/devices). You get one email with your first
+findings right after that analysis. Later findings arrive in a daily digest on the free plan, or
+as real-time email alerts on Pro.
+
+## Plan limits
+
+| Plan | Findings |
+| --- | --- |
+| Beacon Cloud | 50 over the lifetime of the account |
+| Beacon Cloud Pro | Unlimited |
+| Enterprise | Unlimited, org-wide |
+
+Every finding counts toward the free allowance, whatever its status. Once a free account has used
+it, Beacon Cloud stops analyzing its new activity; its sessions keep uploading and stay
+searchable. After an upgrade, findings resume from the next new telemetry. See
+[Plans and pricing](/deployment/plans).
+
+## Findings from your agent
+
+On Beacon Cloud Pro, [Beacon Cloud MCP](/deployment/managed-mcp) lets the agent you are working in
+list your findings (`beacon_findings_list`), read one with its evidence (`beacon_get_finding`) and
+record your feedback or status (`beacon_finding_feedback`, which needs write access). Both
+`beacon_get_finding` and `beacon_finding_feedback` accept a finding's dashboard URL.
+
+## How analysis handles your data
+
+- Only activity from devices you connected is analyzed, in an isolated sandbox per account.
+- Events are projected to a compact, redacted record before analysis, so a secret is reported from
+ Beacon's redaction marker rather than its value.
+- Every finding must cite events from your own sessions.
+- On a device forwarding in Metadata-only mode, prompts, responses, tool arguments and output never
+ reach Beacon Cloud, so findings can only use what was sent. See
+ [What leaves your machine](/deployment/managed#what-leaves-your-machine).
+
+## Related
+
+<Columns cols={2}>
+ <Card title="Plans and pricing" icon="tag" href="/deployment/plans">
+ Free and Pro findings limits.
+ </Card>
+ <Card title="Sessions" icon="list" href="/cloud/sessions">
+ Open the sessions a finding cites.
+ </Card>
+ <Card title="Beacon Cloud MCP" icon="plug" href="/deployment/managed-mcp">
+ Read and review findings from your agent.
+ </Card>
+ <Card title="Local detections" icon="shield" href="/detections/index">
+ Offline threat rules with `beacon scan`.
+ </Card>
+</Columns>
diff --git a/docs/cloud/sessions.mdx b/docs/cloud/sessions.mdx
index a1998aa7..6c7fb4d2 100644
--- a/docs/cloud/sessions.mdx
+++ b/docs/cloud/sessions.mdx
@@ -56,4 +56,7 @@ read your history without you leaving the terminal.
<Card title="Beacon Cloud MCP" icon="plug" href="/deployment/managed-mcp">
Search your sessions from Claude Code, Cursor, Codex and more.
</Card>
+ <Card title="Findings" icon="magnifying-glass" href="/cloud/findings">
+ Risks, reusable workflows and habits found in your sessions.
+ </Card>
</Columns>
diff --git a/docs/concepts/beacon-skills.mdx b/docs/concepts/beacon-skills.mdx
index 8a1bed66..f99e8519 100644
--- a/docs/concepts/beacon-skills.mdx
+++ b/docs/concepts/beacon-skills.mdx
@@ -38,8 +38,8 @@ The plugin also registers Beacon's local MCP server (`beacon mcp serve`) in harn
that accept MCP servers from plugins. When the server is available, recall uses the
`get_memory_context` tool. Otherwise it falls back to `beacon memory list`.
-With [Beacon Cloud MCP](/deployment/managed-mcp#memory) connected (`beacon mcp connect`),
-the three memory skills also work on sessions forwarded to Beacon Cloud and on the memory
+With [Beacon Cloud MCP](/deployment/managed-mcp#memory) connected (`beacon mcp connect`) on
+[Beacon Cloud Pro](/deployment/plans), the three memory skills also work on sessions forwarded to Beacon Cloud and on the memory
approved there, without the CLI. Filing and reviewing candidates needs a connection with
write access. See [Memory in Beacon Cloud](/concepts/cross-harness-memory#memory-in-beacon-cloud).
diff --git a/docs/concepts/cross-harness-memory.mdx b/docs/concepts/cross-harness-memory.mdx
index 97d0a6f7..5569d7ed 100644
--- a/docs/concepts/cross-harness-memory.mdx
+++ b/docs/concepts/cross-harness-memory.mdx
@@ -103,7 +103,7 @@ retrieve later.
## Memory in Beacon Cloud
When an endpoint forwards its sessions to Beacon Cloud, the same loop runs over
-[Beacon Cloud MCP](/deployment/managed-mcp#memory), so any agent connected to it can turn a
+[Beacon Cloud MCP](/deployment/managed-mcp#memory) on [Beacon Cloud Pro](/deployment/plans), so any agent connected to it can turn a
forwarded session into memory, whatever machine or harness the session came from. Sessions
are read from Beacon Cloud, so the agent needs no local trace history or CLI:
diff --git a/docs/concepts/faq.mdx b/docs/concepts/faq.mdx
index 19b49e86..bbc1c539 100644
--- a/docs/concepts/faq.mdx
+++ b/docs/concepts/faq.mdx
@@ -30,7 +30,7 @@ Coverage depends on the runtime surface. See the [agent harness integration
model](/runtimes/integration-model) and [data inventory](/security/data-inventory)
for runtime-specific details.
-### Ca Beacon see the agent's full context window?
+### Can Beacon see the agent's full context window?
Only when the runtime exposes context-bearing telemetry. Beacon can retain
prompt text, tool results, command output, file activity, and related content
@@ -41,7 +41,7 @@ For cloud-agent surfaces, context coverage is often narrower than local endpoint
coverage because the cloud provider controls which hooks or telemetry events are
available.
-### Ca Beacon detect unexpected data entering the agent context?
+### Can Beacon detect unexpected data entering the agent context?
Beacon can help investigate this when the data appears in emitted prompts, tool
results, command output, file activity, or retained content. That can make it
@@ -151,6 +151,20 @@ Beacon Cloud adds centralized ingest, retention, search, detections,
governance, identity, approvals, access control, and investigation workflows on
top of the open-source Beacon foundation.
+### How much does Beacon Cloud cost?
+
+Beacon Cloud is free, and the open-source agent is free. Beacon Cloud Pro is $20 a month, or $15
+a month billed annually, and adds unlimited findings (the free plan includes 50), findings,
+feedback and memory over MCP, skills pulled from your sessions, the full evidence trail on every
+finding, real-time email alerts and priority support. Enterprise is custom. See
+[Plans and pricing](/deployment/plans).
+
+### Do I need to change anything on my machines to use Pro?
+
+No. Pro is a property of your beacon.sh account. Upgrade on
+[beacon.sh/dashboard/billing](https://beacon.sh/dashboard/billing), and your agents get the Pro
+MCP tools within about a minute, with the same connection.
+
### Does Beacon Cloud provide a central console?
Yes. Beacon Cloud provides the centralized operating layer for fleet-wide
diff --git a/docs/deployment/hosting-options.mdx b/docs/deployment/hosting-options.mdx
index 4d7de9e1..6405a8a7 100644
--- a/docs/deployment/hosting-options.mdx
+++ b/docs/deployment/hosting-options.mdx
@@ -3,20 +3,23 @@ title: "Hosting Options"
description: "Choose between local Beacon and Beacon Cloud"
---
-Both options are free. Run Beacon locally with full control of your data, or use [Beacon Cloud](/concepts/core-concepts#beacon-cloud) for hosted storage, search, analytics, and unlimited retention.
-
-| Capability | Local | Beacon Cloud |
-| --- | --- | --- |
-| Cross-harness agent telemetry | ✓ | ✓ |
-| Local, CI & cloud collection | ✓ | ✓ |
-| Unified agent session history | ✓ | ✓ |
-| Store data locally | ✓ | ✓ |
-| Forward to your own data stack | ✓ | ✓ |
-| Hosted ingest & storage | — | ✓ |
-| Search & analytics | — | ✓ |
-| Identity mapping | — | ✓ |
-| **Agent Session Retention** | **You manage** | **Unlimited** |
-| SSO & RBAC | — | ✓ |
+Run Beacon locally with full control of your data, or connect it to [Beacon Cloud](/deployment/managed) for one hosted timeline of every agent and machine, findings, sharing and MCP. Local and Beacon Cloud are free; [Beacon Cloud Pro](/deployment/plans) adds unlimited findings, memory and findings over MCP, and real-time alerts for $20 a month ($15 billed annually).
+
+| Capability | Local | Beacon Cloud | Beacon Cloud Pro |
+| --- | --- | --- | --- |
+| Price | $0 | $0 | $20/mo |
+| Cross-harness agent telemetry | ✓ | ✓ | ✓ |
+| Local, CI & cloud collection | ✓ | ✓ | ✓ |
+| Store data locally | ✓ | ✓ | ✓ |
+| Forward to your own data stack | ✓ | ✓ | ✓ |
+| Offline threat detection | ✓ | ✓ | ✓ |
+| Hosted timeline across agents and machines | — | ✓ | ✓ |
+| Share sessions by link | — | ✓ | ✓ |
+| [Findings](/cloud/findings) | Local rules only | 50 included | Unlimited |
+| MCP access | Local server | Session search, lenses, sharing | Plus findings, feedback and memory |
+| Alerts | — | Daily digest | Real-time email |
+
+Enterprise adds fleet rollout, approvals for risky actions, SSO, RBAC and audit logs. See [Plans and pricing](/deployment/plans) for the full comparison.
## Local
@@ -103,6 +106,9 @@ System-mode connect remains account-free and uses browser approval instead.
Beacon Cloud gives you the open-source Agent Beacon experience without having to run the backend yourself.
+Beacon Cloud is free. To upgrade to [Beacon Cloud Pro](/deployment/plans), open
+[beacon.sh/dashboard/billing](https://beacon.sh/dashboard/billing); nothing on the endpoint changes.
+
For cloud-hosted agent applications, install the [Observe SDK](/concepts/core-concepts#observe-sdk) and initialize hosted export with a Beacon API key:
```bash title="Set the hosted Observe API key"
@@ -122,6 +128,9 @@ See [Beacon Cloud](/deployment/managed) for managed platform capabilities and [S
## Related
<Columns cols={2}>
+ <Card title="Plans and pricing" icon="tag" href="/deployment/plans">
+ Compare Open Source, Beacon Cloud, Beacon Cloud Pro and Enterprise.
+ </Card>
<Card title="Beacon Cloud" icon="key" href="/deployment/managed">
Review managed ingest, governance, investigations, access control, and rollout support.
</Card>
diff --git a/docs/deployment/managed-mcp.mdx b/docs/deployment/managed-mcp.mdx
index 6f0b454c..3932d601 100644
--- a/docs/deployment/managed-mcp.mdx
+++ b/docs/deployment/managed-mcp.mdx
@@ -11,6 +11,9 @@ and [publish lenses](/cloud/lenses/lenses-mcp) for you.
The server is hosted at `https://mcp.beacon.sh`. It uses Streamable HTTP and OAuth, so there is
nothing to run locally and no key to paste.
+Session search, lenses and sharing work on every Beacon Cloud account. The findings and memory
+tools are part of [Beacon Cloud Pro](/deployment/plans).
+
## Connect
You need Beacon [connected to Beacon Cloud](/cloud/devices) so there is history to search. If you
@@ -111,7 +114,7 @@ List my five most recent Beacon sessions.
When your client signs in, the Beacon approval page asks what to allow:
- **Read** is always granted. The agent can search and read your sessions (prompts, responses,
- tool calls and output, commands and file edits) and your findings.
+ tool calls and output, commands and file edits) and, on Pro, your findings and memory.
- **Write** is optional and only offered when the client asks for it. Tick the checkbox to let the
agent share your sessions, create, upload, release and publish lenses under your account,
record your feedback on findings or resolve and dismiss them, and file and review memory
@@ -122,36 +125,40 @@ anyone else's data. A tool that needs write access is hidden from read-only conn
## Tools
-| Tool | What it does |
-| --- | --- |
-| `beacon_search_sessions` | Lists sessions by text and filters: time, harness, repository, model, device, needs review |
-| `beacon_grep` | Searches prompts, responses, commands, tool calls and results with a regular expression |
-| `beacon_read_session` | Reads a window of one session's timeline, or the events around one event |
-| `beacon_get_event` | Returns one event in full |
-| `beacon_lookup` | Lists the harnesses, repositories, models and devices you can filter on |
-| `beacon_usage` | Summarizes token usage and reported cost by model, harness, repository or day |
-| `beacon_lenses_list` | Lists your lenses, the lenses you added, or the marketplace |
-| `beacon_lenses_*` | Create, upload, release and update lenses (write access). See [Lenses with MCP](/cloud/lenses/lenses-mcp) |
-| `beacon_shared_traces_list` | Lists your shared traces with their link, visibility and view counts |
-| `beacon_share_session` | Shares one of your sessions as a trace and returns its link; direct (link-only) unless you ask for public or private (write access) |
-| `beacon_shared_trace_update` | Changes a shared trace's visibility, title or keep-updating setting, or unshares it after you confirm (write access) |
-| `beacon_findings_list` | Lists your findings, the ones that still need review first, filtered by severity or kind |
-| `beacon_get_finding` | Returns one finding in full: detail, recommendation, cited sessions and evidence, and the prompt in effect |
-| `beacon_finding_feedback` | Marks a finding helpful or not helpful with a note, and/or sets it resolved, dismissed or open (write access) |
-| `beacon_memory_candidate_create` | Files a lesson drafted from one of your sessions as a memory candidate, after you confirm it (write access) |
-| `beacon_memory_candidates_list` | Lists your memory candidates by state (awaiting review, approved, rejected, superseded) and repository |
-| `beacon_memory_candidate_get` | Returns one memory candidate in full, with the session evidence it rests on |
-| `beacon_memory_candidate_review` | Approves a candidate with the reviewed text, rejects it, or supersedes it with an existing memory (write access) |
-| `beacon_memory_search` | Searches your approved memory; every word must match |
-| `beacon_memory_get` | Returns one approved memory in full |
-| `beacon_memory_skill` | Renders an approved memory as an Agent Skill (`SKILL.md`) for the agent to save in your repository |
+| Tool | What it does | Plan |
+| --- | --- | --- |
+| `beacon_search_sessions` | Lists sessions by text and filters: time, harness, repository, model, device, needs review | All |
+| `beacon_grep` | Searches prompts, responses, commands, tool calls and results with a regular expression | All |
+| `beacon_read_session` | Reads a window of one session's timeline, or the events around one event | All |
+| `beacon_get_event` | Returns one event in full | All |
+| `beacon_lookup` | Lists the harnesses, repositories, models and devices you can filter on | All |
+| `beacon_usage` | Summarizes token usage and reported cost by model, harness, repository or day | All |
+| `beacon_lenses_list` | Lists your lenses, the lenses you added, or the marketplace | All |
+| `beacon_lenses_*` | Create, upload, release and update lenses (write access). See [Lenses with MCP](/cloud/lenses/lenses-mcp) | All |
+| `beacon_shared_traces_list` | Lists your shared traces with their link, visibility and view counts | All |
+| `beacon_share_session` | Shares one of your sessions as a trace and returns its link; direct (link-only) unless you ask for public or private (write access) | All |
+| `beacon_shared_trace_update` | Changes a shared trace's visibility, title or keep-updating setting, or unshares it after you confirm (write access) | All |
+| `beacon_findings_list` | Lists your findings, the ones that still need review first, filtered by severity or kind | Pro |
+| `beacon_get_finding` | Returns one finding in full: detail, recommendation, cited sessions and evidence, and the prompt in effect | Pro |
+| `beacon_finding_feedback` | Marks a finding helpful or not helpful with a note, and/or sets it resolved, dismissed or open (write access) | Pro |
+| `beacon_memory_candidate_create` | Files a lesson drafted from one of your sessions as a memory candidate, after you confirm it (write access) | Pro |
+| `beacon_memory_candidates_list` | Lists your memory candidates by state (awaiting review, approved, rejected, superseded) and repository | Pro |
+| `beacon_memory_candidate_get` | Returns one memory candidate in full, with the session evidence it rests on | Pro |
+| `beacon_memory_candidate_review` | Approves a candidate with the reviewed text, rejects it, or supersedes it with an existing memory (write access) | Pro |
+| `beacon_memory_search` | Searches your approved memory; every word must match | Pro |
+| `beacon_memory_get` | Returns one approved memory in full | Pro |
+| `beacon_memory_skill` | Renders an approved memory as an Agent Skill (`SKILL.md`) for the agent to save in your repository | Pro |
Time filters accept a relative window such as `24h`, `7d` or `2w`, or exact `after` and `before`
dates. `beacon_read_session` also accepts a dashboard session URL.
Agents work best when they search first and then read only the part of a session they need.
-Findings are what Beacon Cloud's hourly analysis noticed in your forwarded activity (security
+A Pro tool called from a free account returns an error saying the tool is part of Beacon Cloud Pro,
+with a link to [the pricing page](https://beacon.sh/pricing), so the agent can tell you why. An
+upgrade reaches your agents within about a minute, without reconnecting.
+
+Findings are what [Beacon Cloud's hourly analysis](/cloud/findings) noticed in your forwarded activity (security
issues, repeated workflows worth turning into skills, and behavioral insights), the same ones the
dashboard's **Findings** page shows. They are separate from the local `beacon scan` results.
Feedback and status set over MCP are the same review you give on the dashboard: the next analysis
@@ -160,6 +167,8 @@ reads your feedback and note, so it stops repeating what you rejected. `beacon_g
## Memory
+<Note>Memory over MCP is part of [Beacon Cloud Pro](/deployment/plans).</Note>
+
Memory turns lessons from your sessions into reviewed knowledge that any agent connected to
Beacon Cloud can recall, the same workflow as [`beacon memory`](/cli/memory) on a machine. The
agent reads a session, drafts the lesson, and shows it to you; it files the candidate only after
diff --git a/docs/deployment/managed.mdx b/docs/deployment/managed.mdx
index 992e824c..905d4692 100644
--- a/docs/deployment/managed.mdx
+++ b/docs/deployment/managed.mdx
@@ -17,15 +17,33 @@ so there is no database, bucket or pipeline to run.
- **Lenses.** Focused views of a session, such as files changed, token spend or security
findings. Use the built-in lenses, add more from the [marketplace](/cloud/lenses/adding-lenses),
[build your own](/cloud/lenses/creating-lenses), and manage them on the dashboard's **Lenses** page.
-- **MCP.** Let the agent you are working in search and read your past sessions, and publish lenses
- for you. See [Beacon Cloud MCP](/deployment/managed-mcp).
+- **MCP.** Let the agent you are working in search and read your past sessions, share them, and
+ publish lenses for you. On Pro it can also read your findings and keep memory. See
+ [Beacon Cloud MCP](/deployment/managed-mcp).
+- **Sharing.** Publish a session as a link with [`beacon share`](/sharing/index), from the
+ dashboard, or from your agent.
- **Analytics.** Token usage and cost by model, agent activity over time, and the harnesses,
models and repositories you use most.
-- **Findings and inventory.** Threat-rule findings with their evidence, plus the configs, MCP
- servers, skills and hooks each device reports.
+- **Findings.** Security risks, workflows worth turning into skills, and habits that cost you time
+ or money, found by an hourly review of your sessions. See [Findings](/cloud/findings).
+- **Inventory.** The configs, MCP servers, skills and hooks each device reports.
- **Profile.** An optional public page of aggregate activity. See
[Configure your profile](/manage/profile).
+## Plans
+
+Beacon Cloud is free. **Beacon Cloud Pro** ($20 a month, or $15 a month billed annually) adds:
+
+- Unlimited findings, where the free plan includes 50.
+- Findings, feedback and memory over MCP, so your agents can review findings and recall lessons
+ from your history.
+- Skills pulled from your sessions, the full evidence trail on every finding, real-time email
+ alerts and priority support.
+
+Upgrade, start a trial or cancel on [beacon.sh/dashboard/billing](https://beacon.sh/dashboard/billing).
+Your devices need no change. See [Plans and pricing](/deployment/plans) for the full comparison,
+including Enterprise.
+
## Get started
<Steps>
@@ -80,4 +98,10 @@ flow.
<Card title="Beacon Cloud MCP" icon="plug" href="/deployment/managed-mcp">
Bring your history into the agent you are using.
</Card>
+ <Card title="Findings" icon="magnifying-glass" href="/cloud/findings">
+ Review what Beacon Cloud noticed in your sessions.
+ </Card>
+ <Card title="Plans and pricing" icon="tag" href="/deployment/plans">
+ Compare Beacon Cloud, Pro and Enterprise.
+ </Card>
</Columns>
diff --git a/docs/deployment/plans.mdx b/docs/deployment/plans.mdx
new file mode 100644
index 00000000..4b9f716a
--- /dev/null
+++ b/docs/deployment/plans.mdx
@@ -0,0 +1,128 @@
+---
+title: "Plans and pricing"
+sidebarTitle: "Plans"
+description: "Compare Open Source, Beacon Cloud, Beacon Cloud Pro and Enterprise"
+---
+
+Beacon records your agent sessions on your machine whatever plan you choose. The plans differ in
+where that history goes and what Beacon does with it once it is there.
+
+- **Open Source** is the free, local-only agent. Sessions stay on the machine, you browse them in
+ the local dashboard, and you can forward them to your own Elastic, S3, GCS or OpenTelemetry
+ stack.
+- **Beacon Cloud** is free. Connected devices upload to [beacon.sh](https://beacon.sh), where every
+ agent and machine shares one timeline, and Beacon Cloud reviews your sessions for
+ [findings](/cloud/findings).
+- **Beacon Cloud Pro** is Beacon Cloud for people who work with agents every day: unlimited
+ findings, the full [MCP](/deployment/managed-mcp) toolset including findings and memory, and
+ real-time alerts. $20 a month, or $15 a month billed annually.
+- **Enterprise** adds fleet rollout, enforcement, SSO, RBAC and audit logs, with hosting in Beacon
+ Cloud or your own bucket. [Talk to us](https://beacon.sh/pricing) for pricing.
+
+Current prices are always on the [pricing page](https://beacon.sh/pricing).
+
+## Compare plans
+
+| | Open Source | Beacon Cloud | Beacon Cloud Pro | Enterprise |
+| --- | --- | --- | --- | --- |
+| **Price** | $0 | $0 | $20/mo ($15/mo annually) | Custom |
+| **Hosting** | You run it | Managed | Managed | Managed or your bucket |
+| **Agents** | 20+ | 20+ | 20+ | 20+, on endpoints, CI and cloud |
+| Prompts, commands, diffs and token usage | ✓ | ✓ | ✓ | ✓ |
+| Export to Elastic, S3 or OTel | ✓ | ✓ | ✓ | ✓ |
+| Offline threat detection (`beacon scan`) | ✓ | ✓ | ✓ | ✓ |
+| Every agent and machine in one timeline | — | ✓ | ✓ | ✓ |
+| [Findings](/cloud/findings) (risks, skills, habits) | Local rules only | 50 included | Unlimited | Unlimited, org-wide |
+| One-click skills and fix prompts | — | ✓ | ✓ | ✓ |
+| [MCP access](/deployment/managed-mcp) | — | Session search | Sessions, findings and feedback | Sessions, findings and feedback |
+| [Agent memories over MCP](/deployment/managed-mcp#memory) | — | — | ✓ | ✓ |
+| Skills pulled from your sessions | — | — | ✓ | ✓ |
+| [Share sessions by link](/sharing/index) | — | ✓ | ✓ | ✓ |
+| Evidence trail on every finding | — | — | ✓ | ✓ |
+| Alerts | — | Daily digest | Real-time email | Real-time and custom |
+| Block or require approval for risky actions | — | — | — | ✓ |
+| Fleet rollout (Jamf, Intune, Fleet) | — | — | — | ✓ |
+| SSO, RBAC, audit logs | — | — | — | ✓ |
+| Support | Community | Community | Priority | Dedicated SLA |
+
+The Beacon CLI, hooks, local dashboard, threat rules, session sharing commands and
+[Agent Skills](/concepts/beacon-skills) are the same open-source build on every plan. Nothing on
+the machine changes when you upgrade: Pro is a property of your beacon.sh account.
+
+## What Beacon Cloud Pro adds
+
+- **Unlimited findings.** A free account gets 50 findings over its lifetime. Pro has no limit, so
+ every new risk, skill opportunity and habit Beacon notices keeps showing up.
+- **Findings and feedback over MCP.** Your agents can list and read your findings, with their
+ evidence and recommendation, and record your feedback or resolve them, through
+ `beacon_findings_list`, `beacon_get_finding` and `beacon_finding_feedback`.
+- **Memory over MCP.** Agents can file lessons from your sessions as memory candidates, review
+ them with you, recall approved memory in later sessions on any machine or harness, and render a
+ memory as an Agent Skill. See [Memory](/deployment/managed-mcp#memory).
+- **Skills pulled from your sessions.** The `beacon_memory_skill` tool and the
+ `beacon-memory-promote` skill turn an approved memory into a `SKILL.md` your agents load
+ automatically.
+- **The full evidence trail** behind every finding, and **real-time email alerts** in place of the
+ daily digest.
+- **Priority support.**
+
+Session search, lenses and session sharing over MCP stay available on the free plan.
+
+## Upgrade, trial and cancel
+
+Open **Billing** at [beacon.sh/dashboard/billing](https://beacon.sh/dashboard/billing), or choose
+**Upgrade to Pro** on the [pricing page](https://beacon.sh/pricing). Pick monthly or annual billing
+and finish checkout in the browser. When a free trial is offered, the button reads
+**Start a free trial**, and a trial has every Pro feature.
+
+- Pro reaches your agents within about a minute of checkout. Reconnecting MCP is not needed.
+- Findings resume from your next new telemetry once you upgrade. Sessions analyzed while you were
+ at the free limit are not re-analyzed.
+- **Cancel subscription** on the Billing page keeps Pro until the end of the period you paid for,
+ then moves the account back to free Beacon Cloud. Your sessions, findings, memory, lenses and
+ shared traces are kept.
+- If a payment fails, the account stays on Pro while the payment is retried, and Billing shows it
+ as past due.
+
+Beacon never asks for payment details in the CLI or through an agent. When an agent sets Beacon
+up for you, it sends you to the Billing page to finish upgrading.
+
+## What a free account sees at a limit
+
+- **Findings.** After 50 findings, Beacon Cloud stops analyzing new activity for the account. A
+ finding you already have still updates when it recurs. Your sessions keep uploading and stay
+ searchable.
+- **MCP.** A findings or memory tool called from a free account returns an error that says the
+ tool is part of Beacon Cloud Pro and links to the pricing page, so your agent can tell you why.
+ Every other tool keeps working.
+
+## Choosing a plan
+
+- Choose **Open Source** when nothing may leave the machine, or when you forward to a data stack
+ you already run. See [Local](/deployment/open-source).
+- Choose **Beacon Cloud** to see every agent on every machine in one place, share sessions and try
+ findings. See [Beacon Cloud](/deployment/managed).
+- Choose **Beacon Cloud Pro** when your agents should learn from your history: memory, findings
+ and feedback over MCP, and no findings limit.
+- Choose **Enterprise** to roll Beacon out across a team or fleet with MDM, require approval for
+ risky actions, or keep the data in your own bucket.
+
+You can start local and connect later with `beacon login` and `beacon endpoint connect`, and you
+can upgrade or cancel Pro at any time without touching your devices.
+
+## Related
+
+<Columns cols={2}>
+ <Card title="Hosting options" icon="server" href="/deployment/hosting-options">
+ Install Beacon locally or connect it to Beacon Cloud.
+ </Card>
+ <Card title="Findings" icon="magnifying-glass" href="/cloud/findings">
+ What Beacon Cloud notices in your sessions.
+ </Card>
+ <Card title="Beacon Cloud MCP" icon="plug" href="/deployment/managed-mcp">
+ The tools your agents can use on each plan.
+ </Card>
+ <Card title="Connect devices" icon="laptop" href="/cloud/devices">
+ Enroll a machine in Beacon Cloud.
+ </Card>
+</Columns>
diff --git a/docs/docs.json b/docs/docs.json
index 0db9d80b..a1fe797b 100644
--- a/docs/docs.json
+++ b/docs/docs.json
@@ -57,7 +57,8 @@
"pages": [
"deployment/hosting-options",
"deployment/open-source",
- "deployment/managed"
+ "deployment/managed",
+ "deployment/plans"
]
},
{
@@ -72,6 +73,7 @@
]
},
"cloud/sessions",
+ "cloud/findings",
"deployment/managed-mcp",
{
"group": "Lenses",
@@ -630,6 +632,7 @@
"icon": "clock",
"pages": [
"changelog/cli",
+ "changelog/cloud",
"changelog/sdk"
]
}
@@ -697,6 +700,14 @@
"source": "/guides/claude-s3-system",
"destination": "/guides/macos-object-storage-system"
},
+ {
+ "source": "/pricing",
+ "destination": "/deployment/plans"
+ },
+ {
+ "source": "/cloud-changelog",
+ "destination": "/changelog/cloud"
+ },
{
"source": "/product-changelog",
"destination": "/changelog/cli"