An agentic browser harness: an AI side panel & orb in your own logged-in Chrome, Edge, Arc, Brave or even Firefox run by the agent/subscription you already use (Claude Code, Codex, Antigravity). Free, open source, no API key. Also an MCP server.
TypeScript agentic-browseragentic-browsingagy-cliaiai-agentai-browser-extensionai-toolsbrave-extensionbrowser-agentbrowser-automationbrowser-extensionbrowser-usebrowserskillchrome-extensionclaude-codecodexfirefox-addonmcp-servernanobrowserweb-automation
docs(agents): Qwen Code beside the other six, why a provider has to be configured first, and the two things sealing does not cover
Shahriare2f560f80add
diff --git a/.github/ISSUE_TEMPLATE/bug_report.yml b/.github/ISSUE_TEMPLATE/bug_report.ymlindex a044512..6bfd6c6 100644--- a/.github/ISSUE_TEMPLATE/bug_report.yml+++ b/.github/ISSUE_TEMPLATE/bug_report.yml@@ -42,7 +42,7 @@ body:attributes:label: Agentdescription: Which agent CLI runs your side panel, if the bug involves a run.- placeholder: claude / codex / agy, and its version+ placeholder: claude / codex / agy / vibe / grok / cursor-agent / qwen, and its version- type: inputid: environmentattributes:diff --git a/README.md b/README.mdindex 40547df..59784af 100644--- a/README.md+++ b/README.md@@ -8,7 +8,7 @@[](https://nodejs.org)[](LICENSE)-Hand your real, logged-in browser to the AI agent you already run. Browsentic is a browser extension with an AI side panel, plus a small local daemon: open the panel beside any tab, say what you want and it drives the page, ask a question and it reads the page and answers. It runs on the agent CLI you already have logged in — six are supported — and doubles as an [MCP server](docs/guide/mcp-clients.md) so any MCP client can drive the same browser. No account, no API key, no cloud service.+Hand your real, logged-in browser to the AI agent you already run. Browsentic is a browser extension with an AI side panel, plus a small local daemon: open the panel beside any tab, say what you want and it drives the page, ask a question and it reads the page and answers. It runs on the agent CLI you already have logged in — seven are supported — and doubles as an [MCP server](docs/guide/mcp-clients.md) so any MCP client can drive the same browser. No account, no API key, no cloud service.<p><strong>Works in</strong> @@ -25,7 +25,8 @@ Hand your real, logged-in browser to the AI agent you already run. Browsentic is<img src="https://browsentic.com/icons/antigravity.svg" width="18" height="18" alt=""> <a href="https://antigravity.google/docs/cli/install">Antigravity</a> · <img src="https://browsentic.com/icons/mistral.svg" width="18" height="18" alt=""> <a href="https://github.com/mistralai/mistral-vibe">Mistral Vibe</a> <sup>beta</sup> · <picture><source media="(prefers-color-scheme: dark)" srcset="https://browsentic.com/icons/xai-dark.svg"><img src="https://browsentic.com/icons/xai.svg" width="18" height="18" alt=""></picture> <a href="https://docs.x.ai/build/overview">Grok Build</a> <sup>beta</sup> · - <picture><source media="(prefers-color-scheme: dark)" srcset="https://browsentic.com/icons/cursor-dark.svg"><img src="https://browsentic.com/icons/cursor.svg" width="18" height="18" alt=""></picture> <a href="https://cursor.com/docs/cli/overview">Cursor CLI</a> <sup>beta</sup>+ <picture><source media="(prefers-color-scheme: dark)" srcset="https://browsentic.com/icons/cursor-dark.svg"><img src="https://browsentic.com/icons/cursor.svg" width="18" height="18" alt=""></picture> <a href="https://cursor.com/docs/cli/overview">Cursor CLI</a> <sup>beta</sup> · + <picture><source media="(prefers-color-scheme: dark)" srcset="https://browsentic.com/icons/qwen-dark.svg"><img src="https://browsentic.com/icons/qwen.svg" width="18" height="18" alt=""></picture> <a href="https://qwenlm.github.io/qwen-code-docs/en/">Qwen Code</a> <sup>beta</sup></p>## Quick Start@@ -42,13 +43,13 @@ curl -fsSL https://browsentic.com/install.sh | shnpx browsentic setup```-Either way two steps are left, both inside the browser: **Load unpacked** `~/browsentic/extension/chrome-mv3` at `chrome://extensions`, then paste the pairing code into the Browsentic popup. On Firefox, run `npx browsentic setup --browser firefox` instead: it links the signed `.xpi` from the [release](https://github.com/imshaikot/browsentic/releases/latest), and there is no folder to load. You also need one agent CLI logged in — `claude`, `codex`, `agy`, `vibe` (beta), `grok` (beta) or `cursor-agent` (beta). Windows and Linux follow the same two steps; the folder is under your home directory there too. Details, updating and building from source are in the [install guide](docs/guide/install.md).+Either way two steps are left, both inside the browser: **Load unpacked** `~/browsentic/extension/chrome-mv3` at `chrome://extensions`, then paste the pairing code into the Browsentic popup. On Firefox, run `npx browsentic setup --browser firefox` instead: it links the signed `.xpi` from the [release](https://github.com/imshaikot/browsentic/releases/latest), and there is no folder to load. You also need one agent CLI logged in — `claude`, `codex`, `agy`, `vibe` (beta), `grok` (beta), `cursor-agent` (beta) or `qwen` (beta). Windows and Linux follow the same two steps; the folder is under your home directory there too. Details, updating and building from source are in the [install guide](docs/guide/install.md).## Key Capabilities- **A Side Panel, Not a Terminal**: Open it beside any tab, type or dictate, and watch every action land on a timeline with approvals where you are looking. The terminal is optional: the same daemon doubles as an MCP server for Claude Code, Cursor or Zed- **Your Real Browser, Not a Headless One**: Drives the tab in front of you, in your own profile, with your own logins and sessions-- **Bring Your Own Agent**: Runs on the agent CLI you already have and are already signed in to — switch between Claude Code, Codex, Antigravity, Mistral Vibe, Grok Build and Cursor CLI with one click, and pick the model each one runs+- **Bring Your Own Agent**: Runs on the agent CLI you already have and are already signed in to — switch between Claude Code, Codex, Antigravity, Mistral Vibe, Grok Build, Cursor CLI and Qwen Code with one click, and pick the model each one runs- **52 Page Capabilities**: Reading, clicking, typing, dragging, on-site search, form submission, navigation, stepping into iframes, screenshots, file upload and download, captchas, theming and accessibility, console and network diagnostics, background progress monitoring, scheduled and repeating jobs, pointing at an element, and calling the tools a WebMCP site registers for agents- **Live Tools, Off By Default**: For work that repeats twenty times or needs something no tool covers, flip the **Live tool** switch and the agent may write a small script for the page — you read the code in the panel and approve it before a line of it runs- **Keep What It Wrote**: A script that worked can be kept as a tool of your own, named after the site it belongs to (`youtube.com:watch:darken-page-except-video-player`) and run later by typing `/`. The code stays in the browser; no MCP client can reach itdiff --git a/SECURITY.md b/SECURITY.mdindex b861737..e341b06 100644--- a/SECURITY.md+++ b/SECURITY.md@@ -48,8 +48,9 @@ other liability arising from the software or its use. In plain language, that me- **You are responsible for what you approve and where you point it.** The approval gate namesthe action; deciding is yours. Actions taken in your browser — purchases, submissions,messages, deletions — are actions taken on your accounts, by you.-- **The agent is not part of this project.** Browsentic spawns Claude Code, Codex, or- Antigravity and contains them as well as each CLI's own flags allow, but their behaviour,+- **The agent is not part of this project.** Browsentic spawns whichever agent CLI you chose —+ Claude Code, Codex, Antigravity, Mistral Vibe, Grok Build, Cursor CLI or Qwen Code — and+ contains each as well as its own flags allow, but their behaviour,their terms, and what they do with your prompts are governed by their vendors, not by thisrepository.- **Automating a website may breach that website's terms of service.** Whether a site permitsdiff --git a/docs/README.md b/docs/README.mdindex 616a43a..049e65b 100644--- a/docs/README.md+++ b/docs/README.md@@ -19,7 +19,7 @@ Start here if you want to run Browsentic on your own machine.| [Pair](guide/pair.md) | Connect your browser with a single-use code || [First run](guide/first-run.md) | A tour of the side panel and your first instruction || [Features](guide/features/) | One page per capability — what it does and when to reach for it |-| [Choosing an agent](guide/agents.md) | Claude Code, Codex, Antigravity or Grok Build |+| [Choosing an agent](guide/agents.md) | The seven agent CLIs the side panel can run on || [MCP clients](guide/mcp-clients.md) | Optional: drive the same browser from Claude Code, Cursor, Zed or Gemini CLI || [Configuration](guide/configuration.md) | Every key in `~/.browsentic/config.json` || [Approvals](guide/approvals.md) | What asks before it acts, and how to change that |diff --git a/docs/guide/README.md b/docs/guide/README.mdindex cb3dfd2..abd1f91 100644--- a/docs/guide/README.md+++ b/docs/guide/README.md@@ -33,7 +33,7 @@ service.| | || --- | --- |-| [Choosing an agent](agents.md) | Claude Code, Codex, Antigravity or Grok Build — switching, and what each needs |+| [Choosing an agent](agents.md) | The seven agent CLIs the side panel can run on — switching, and what each needs || [MCP clients](mcp-clients.md) | Optional: registering Browsentic with Claude Code, Cursor, Zed, Codex or Gemini CLI || [Configuration](configuration.md) | Every key in `~/.browsentic/config.json` || [Approvals](approvals.md) | The gate — what asks first, and how to tune it |diff --git a/docs/guide/agents.md b/docs/guide/agents.mdindex bf4bfdf..73919cc 100644--- a/docs/guide/agents.md+++ b/docs/guide/agents.md@@ -1,7 +1,7 @@# Choosing an agent-The side panel runs on an agent CLI you already have logged in. Six are supported — Mistral Vibe,-Grok Build and Cursor CLI in beta — and switching is a click.+The side panel runs on an agent CLI you already have logged in. Seven are supported — Mistral Vibe,+Grok Build, Cursor CLI and Qwen Code in beta — and switching is a click.This is only about the **side panel**. Driving Browsentic *from* another tool is[MCP clients](mcp-clients.md), and that direction is fully agent-agnostic.@@ -32,18 +32,18 @@ agents cannot resume each other's sessions, so the next instruction starts a fre----## The six+## The seven-| | Claude Code | Codex | Antigravity | Mistral Vibe (beta) | Grok Build (beta) | Cursor CLI (beta) |-| --- | --- | --- | --- | --- | --- | --- |-| Vendor | Anthropic | OpenAI | Google | Mistral AI | xAI | Anysphere |-| Binary | `claude` | `codex` | `agy` | `vibe` | `grok` | `cursor-agent` |-| Install | `npm i -g @anthropic-ai/claude-code` | `npm i -g @openai/codex` | [antigravity.google/docs/cli/install](https://antigravity.google/docs/cli/install) | `uv tool install mistral-vibe` | `curl -fsSL https://x.ai/cli/install.sh \| bash` | `curl https://cursor.com/install -fsS \| bash` |-| Default model | `claude-sonnet-5` | the CLI's own | the CLI's own | the CLI's own | the CLI's own | the CLI's own |-| Effort names | `low`…`max` | `low`…`xhigh` | `low`…`high` | none — set `thinking` in Vibe's own config | `low`…`xhigh` | none — put it in the model id, e.g. `claude-opus-4-8[effort=high]` |-| Kept off your machine by | a per-run tool allowlist plus an explicit deny list | a read-only sandbox (`sandbox_mode="read-only"`) | its own permission rules | a per-run tool allowlist — its shell and file tools are never loaded | a per-run tool list, approvals that refuse anything not granted up front, and a kernel sandbox that keeps its writes in its own folder | per-run deny rules, where a deny beats every allow; a kernel sandbox is asked for too but not depended on |+| | Claude Code | Codex | Antigravity | Mistral Vibe (beta) | Grok Build (beta) | Cursor CLI (beta) | Qwen Code (beta) |+| --- | --- | --- | --- | --- | --- | --- | --- |+| Vendor | Anthropic | OpenAI | Google | Mistral AI | xAI | Anysphere | Alibaba |+| Binary | `claude` | `codex` | `agy` | `vibe` | `grok` | `cursor-agent` | `qwen` |+| Install | `npm i -g @anthropic-ai/claude-code` | `npm i -g @openai/codex` | [antigravity.google/docs/cli/install](https://antigravity.google/docs/cli/install) | `uv tool install mistral-vibe` | `curl -fsSL https://x.ai/cli/install.sh \| bash` | `curl https://cursor.com/install -fsS \| bash` | `npm i -g @qwen-code/qwen-code` |+| Default model | `claude-sonnet-5` | the CLI's own | the CLI's own | the CLI's own | the CLI's own | the CLI's own | the CLI's own |+| Effort names | `low`…`max` | `low`…`xhigh` | `low`…`high` | none — set `thinking` in Vibe's own config | `low`…`xhigh` | none — put it in the model id, e.g. `claude-opus-4-8[effort=high]` | none — the model id is the only lever |+| Kept off your machine by | a per-run tool allowlist plus an explicit deny list | a read-only sandbox (`sandbox_mode="read-only"`) | its own permission rules | a per-run tool allowlist — its shell and file tools are never loaded | a per-run tool list, approvals that refuse anything not granted up front, and a kernel sandbox that keeps its writes in its own folder | per-run deny rules, where a deny beats every allow; a kernel sandbox is asked for too but not depended on | `--safe-mode`, which drops every setting of your own, plus deny rules for the shell, the disk and the tools that reach either |-All six get the same system prompt, the same `browsentic` MCP server pointed back at the daemon,+All seven get the same system prompt, the same `browsentic` MCP server pointed back at the daemon,and the same [approval gate](approvals.md). What differs is how well each one can be fenced off fromthe rest of your machine — see [internals/guardrails.md § Spawn containment](../internals/guardrails.md#spawn-containment)for exactly what each flag buys.@@ -136,6 +136,44 @@ Expect rough edges there, and please report them.---+### Qwen Code is in beta++Browsentic's Qwen runner was written against `qwen-code` 0.24.4's own source rather than against a+running binary: no Qwen provider was configured on the machine it was built on, so nothing here has+been through a real turn. The flags, the stream shapes and the containment all come from the repo.+Expect rough edges, and please report them.++- **Configure a provider first.** Qwen OAuth's free tier ended on 2026-04-15 and its requests are+ now rejected, so "install it and log in" is no longer enough. Run `qwen` and use `/auth`, or+ export `OPENAI_API_KEY` with `OPENAI_BASE_URL` pointed at your endpoint. Until then the popup+ says *needs setup* and a run fails with *No auth type is selected*.+- **Only some keys reach a run.** Browsentic keeps `QWEN_*`, `DASHSCOPE_*`, `BAILIAN_*` and+ `OPENAI_*` in the run's environment and seals the rest away, so the `anthropic` and `gemini` auth+ types Qwen also accepts will not find their keys. That is deliberate: handing one vendor's agent+ another vendor's credential is what [sealing](../internals/guardrails.md#the-environment-a-run-sees)+ exists to prevent.+- **Every setting of your own is switched off for the run.** Browsentic passes `--safe-mode`, which+ drops your hooks, extensions, bundled skills, `settings.json` MCP servers, `.mcp.json` and+ permission rules, and passes its own MCP server as an explicit argument instead. Your own+ `browsentic` entry cannot load beside it, and nothing you configured for Qwen widens a run.+- **The bundled browser-use and computer-use skills are denied.** Qwen ships a skill that drives+ your Chrome through an extension of its own — a second browser Browsentic never sees — and one+ that runs `qwen mcp add` and `npm install` by itself on first use. Both reach the model through+ the `skill` tool, which a run does not get. The side panel's `/` picker still lists your own+ skills from `~/.qwen/skills` and `~/.agents/skills`; it reads them off disk itself.+- **The run is stopped if the deny list did not take.** Qwen prints every tool and MCP server that+ actually registered, and Browsentic reads that line back before the model has spoken. Anything it+ did not ask for ends the run with `AGENT_UNSAFE` rather than letting it act.+- **Reasoning effort has no flag.** Set `agents.qwen.model` instead.+- **Two things sealing does not cover.** Qwen loads the first `.env` it finds walking up from its+ working directory, then `~/.qwen/.env` and `~/.env`, for variables not already set — so a key+ Browsentic sealed away can come back from disk. It reaches the model provider, not the model,+ because the shell and file tools are denied. And an `@path` in what you type is expanded by Qwen+ into the prompt before the run starts, which reads a file without a tool call; that is your own+ typed text, but it is worth knowing.++---+## Per-agent settingsIn `~/.browsentic/config.json`:@@ -149,7 +187,8 @@ In `~/.browsentic/config.json`:"antigravity": { "bin": "agy" },"vibe": { "bin": "vibe" },"grok": { "bin": "grok", "model": "grok-4.7" },- "cursor": { "bin": "cursor-agent", "model": "composer-2.5" }+ "cursor": { "bin": "cursor-agent", "model": "composer-2.5" },+ "qwen": { "bin": "qwen", "model": "qwen3-coder-plus" }}}```@@ -173,7 +212,7 @@ Claude runner's settings.| Symptom | Fix || --- | --- || `AGENT_MISSING` | The daemon's `PATH` differs from your shell's. Set `agents.<name>.bin` to an absolute path. |-| `AGENT_NEEDS_PERMISSION` | Antigravity has no rule for Browsentic's tools: press the button, or `browsentic agent fix antigravity`. Grok Build is not signed in: run `grok login`. |+| `AGENT_NEEDS_PERMISSION` | Antigravity has no rule for Browsentic's tools: press the button, or `browsentic agent fix antigravity`. Grok Build is not signed in: run `grok login`. Qwen Code has no model provider: run `qwen` and use `/auth`. || Codex: "not logged in" | The daemon inherits no session. Run `codex login`, then retry. || Codex answers about the page without opening it, or from a web search | Update Browsentic. Codex hides the browser tools until the model searches for them, and an older Browsentic left Codex's own web search switched on, which the model reached for first. || Mistral Vibe: a follow-up turn says *this agent run is no longer active* | Update Browsentic, then start a new conversation. An older one gave each turn its own folder, and Vibe keeps re-reading the first turn's, so a conversation begun before the update stays broken. |@@ -183,6 +222,9 @@ Claude runner's settings.| Cursor CLI: *Authentication required* | The daemon inherits no session. Run `cursor-agent login`, or set `CURSOR_API_KEY`, then retry. || Cursor CLI on Windows | Cursor's sandbox has no Windows backend, so only the deny rules apply there. The browser still works; the machine is less fenced off than on macOS or Linux. || `AGENT_UNSAFE`: *Grok Build offered this run …* | Grok offered tools Browsentic never asks for, so the run was stopped before the model saw them. Update Grok Build and Browsentic, and report it if it persists. |+| Qwen Code: *No auth type is selected* | Qwen has no provider configured, and its OAuth free tier has ended. Run `qwen` and use `/auth`, or export `OPENAI_API_KEY` with `OPENAI_BASE_URL`. |+| Qwen Code cannot find a key you have exported | Only `QWEN_*`, `DASHSCOPE_*`, `BAILIAN_*` and `OPENAI_*` reach a run; `ANTHROPIC_*` and `GEMINI_*` are sealed away. Point Qwen at one of the first four. |+| `AGENT_UNSAFE`: *Qwen Code registered …* or *loaded the MCP server …* | Qwen's own `init` line named a tool or a server Browsentic denied, so the run was stopped. Update Qwen Code and Browsentic, and report it if it persists. |---diff --git a/docs/guide/configuration.md b/docs/guide/configuration.mdindex fbb5f9d..82b9ea8 100644--- a/docs/guide/configuration.md+++ b/docs/guide/configuration.md@@ -49,7 +49,7 @@ Nothing here is required; this shows every key in one place.| Key | Default | Notes || --- | --- | --- |-| `agent` | `claude` | Which CLI the side panel runs on: `claude`, `codex`, `antigravity`, `vibe`, `grok` or `cursor` |+| `agent` | `claude` | Which CLI the side panel runs on: `claude`, `codex`, `antigravity`, `vibe`, `grok`, `cursor` or `qwen` || `agents.<name>.bin` | the CLI's own command name | Absolute path to the binary || `agents.<name>.model` | `claude-sonnet-5` for Claude, else the CLI's default | Passed as `--model`; the agent picker's model select writes it || `agents.<name>.effort` | unset | That CLI's reasoning-effort flag; an unaccepted value is dropped |diff --git a/docs/guide/features/conversations.md b/docs/guide/features/conversations.mdindex 2c0ca95..3fc27a5 100644--- a/docs/guide/features/conversations.md+++ b/docs/guide/features/conversations.md@@ -105,7 +105,8 @@ plus whether it can resume where it left off.The card also shows token counts, straight from the agent CLI's own reporting: roughly how manytokens the model's context window held after its last reply, and how many it generated on the last-run. Claude Code, Codex and Grok Build report these; Antigravity does not, and the card says so.+run. Claude Code, Codex, Grok Build, Cursor CLI and Qwen Code report these; Antigravity and Mistral Vibe+do not, and the card says so.It is answered by the extension itself, without waking an agent, so it also works mid-run. The carddescribes what this browser holds; the agent's own working memory lives with the agent.diff --git a/docs/guide/features/skills.md b/docs/guide/features/skills.mdindex 19ade9e..59512ad 100644--- a/docs/guide/features/skills.md+++ b/docs/guide/features/skills.md@@ -87,9 +87,19 @@ browsentic skills # everything the router can see, tagged with where it came## The agent's own skills-The `/` picker also lists the skills the active agent CLI keeps for itself — Claude Code's-`~/.claude/skills/`, Codex's `~/.codex/skills/` and `~/.codex/prompts/`, the roots in Antigravity's-`skills.txt`, and Grok Build's `~/.grok/skills/`, `~/.agents/skills/` and the Claude Code skills it also loads. Picking one attaches it to that message: the daemon reads the file at spawn time and+The `/` picker also lists the skills the active agent CLI keeps for itself:++| Agent | Where it looks |+| --- | --- |+| Claude Code | `~/.claude/skills/` |+| Codex | `~/.codex/skills/`, `~/.codex/prompts/` |+| Antigravity | the roots listed in `~/.gemini/antigravity/skills.txt` |+| Mistral Vibe | `~/.vibe/skills/`, `~/.agents/skills/` |+| Grok Build | `~/.grok/skills/`, `~/.agents/skills/`, and the Claude Code skills it also loads |+| Cursor CLI | `~/.cursor/skills/`, `~/.agents/skills/` |+| Qwen Code | `~/.qwen/skills/`, `~/.agents/skills/` |++Picking one attaches it to that message: the daemon reads the file at spawn time andappends it to the system prompt, clearly marked, with a note that browser tools are all the runhas.diff --git a/docs/guide/first-run.md b/docs/guide/first-run.mdindex 4d209a9..5ee5a2c 100644--- a/docs/guide/first-run.md+++ b/docs/guide/first-run.md@@ -72,6 +72,6 @@ Check in this order:## Where to go next- **[Features](features/)** — one page per capability-- **[Choosing an agent](agents.md)** — if you would rather run Codex, Antigravity or Grok Build+- **[Choosing an agent](agents.md)** — if you would rather run one of the other six- **[Configuration](configuration.md)** — `~/.browsentic/config.json`- **[Limits](limits.md)** — worth reading early rather than discoveringdiff --git a/docs/guide/install.md b/docs/guide/install.mdindex 60f0a1a..36b99d8 100644--- a/docs/guide/install.md+++ b/docs/guide/install.md@@ -15,7 +15,7 @@ AI agent you already run locally.| **Node** | 20 or newer | `node --version` || **Browser** | Chrome or another Chromium browser (Edge, Brave, Arc), or Firefox 140 or newer | — || **System** | macOS, Windows or Linux. macOS also has an [app](mac-app.md) | — |-| **Agent** | One of [Claude Code](https://claude.com/claude-code), [Codex](https://developers.openai.com/codex/cli), [Antigravity](https://antigravity.google/docs/cli/install), [Mistral Vibe](https://github.com/mistralai/mistral-vibe) (beta) or [Grok Build](https://docs.x.ai/build/overview) (beta) on your `PATH`, logged in | `claude --version`, `codex --version`, `agy --version`, `vibe --version`, `grok --version` |+| **Agent** | One of [Claude Code](https://claude.com/claude-code), [Codex](https://developers.openai.com/codex/cli), [Antigravity](https://antigravity.google/docs/cli/install), [Mistral Vibe](https://github.com/mistralai/mistral-vibe) (beta), [Grok Build](https://docs.x.ai/build/overview) (beta), [Cursor CLI](https://cursor.com/docs/cli/overview) (beta) or [Qwen Code](https://qwenlm.github.io/qwen-code-docs/en/) (beta) on your `PATH`, logged in | `claude --version`, `codex --version`, `agy --version`, `vibe --version`, `grok --version`, `cursor-agent --version`, `qwen --version` |Two things worth knowing before you start:diff --git a/docs/guide/limits.md b/docs/guide/limits.mdindex 30040f2..bfce836 100644--- a/docs/guide/limits.md+++ b/docs/guide/limits.md@@ -68,21 +68,26 @@ contains it with whatever levers that CLI offers, and they are not equal:| Antigravity | No tool list and no sandbox flag; its built-in tools are governed by your own CLI settings || Mistral Vibe (beta) | A per-run tool allowlist; its shell and file tools are never loaded, and every browser tool is granted by name || Grok Build (beta) | A per-run tool list, approvals that refuse anything not granted up front, and a sandbox that keeps its writes in its own folder; MCP servers you set up in Grok itself still load |+| Cursor CLI (beta) | Per-run deny rules, where a deny beats every allow including your own; a kernel sandbox is asked for too, but it has no Windows backend and is not depended on |+| Qwen Code (beta) | `--safe-mode` drops every setting of your own — hooks, extensions, bundled skills, MCP servers, permission rules — and deny rules close the shell, the disk and the tools that reach either; because that mode also disables Qwen's own fail-closed tool allowlist, the run's startup line is read back and anything unexpected stops it |The environment is sealed for all of them — cloud keys, registry tokens and database URLs inheritedfrom your shell are removed before the spawn, keeping only what that agent needs to authenticate.Details in [internals/guardrails.md](../internals/guardrails.md#spawn-containment).-## Two of the agents are beta+## Four of the agents are beta-Mistral Vibe and Grok Build were built by reading each CLI and checking every flag, the containment-and the error texts against the real binary — but neither has carried a whole conversation end to-end yet, so the popup, the docs and the release notes say *beta*. What that means in practice:+Mistral Vibe, Grok Build, Cursor CLI and Qwen Code were built by reading each CLI and checking its+flags, its containment and its error texts — but none has carried a whole conversation end to end+yet, so the popup, the docs and the release notes say *beta*. What that means in practice:- a run that fails says why, with the command that fixes it, rather than hanging;- Vibe's replies arrive a message at a time rather than typed out, and it reports no token counts;- a free Grok account is rate-limited, and Grok retries quietly for minutes before it gives up;-- the other three agents are untouched: the hooks the two share are covered by the spawn and+- Cursor is less fenced off on Windows, where its kernel sandbox has no backend;+- Qwen was written against its source rather than a running binary — no provider was configured on+ the machine it was built on — and it needs one configured before it will answer at all;+- the other three agents are untouched: the hooks the four share are covered by the spawn anddrive tests.[Choosing an agent](agents.md) has the per-agent detail. Please report what you find.diff --git a/docs/guide/mac-app.md b/docs/guide/mac-app.mdindex 5b0a94c..2692309 100644--- a/docs/guide/mac-app.md+++ b/docs/guide/mac-app.md@@ -46,7 +46,7 @@ The app opens on six checks and runs them on its own:| **Browsentic command** | `~/.browsentic/cli` holds the version this app carries | **Install** copies it there and writes the `browsentic` launcher to `~/.browsentic/bin` || **Browser extension** | the same version is unpacked at `~/browsentic/extension/chrome-mv3` | **Install** unpacks it || **A Chromium browser** | Chrome, Brave, Edge, Arc, Vivaldi, Opera or Chromium is installed | **Get Chrome** opens the download page. Advisory — it does not block you |-| **An AI agent** | `claude`, `codex` or `agy` is on your `PATH` | **Install Claude Code** runs `npm i -g @anthropic-ai/claude-code`. Advisory |+| **An AI agent** | One of `claude`, `codex`, `agy`, `vibe`, `grok`, `cursor-agent` or `qwen` is on your `PATH` | **Install Claude Code** runs `npm i -g @anthropic-ai/claude-code`. Advisory |**Set up everything** installs the first three in one click. A browser and an agent are yours tochoose, so each has a button of its own. When everything required is in place the app moves on by@@ -65,7 +65,7 @@ The tabs float at the top; ⌘1–⌘7 switch between them.| --- | --- || **Overview** | Turn the daemon on and off with the power button, restart it, see its address, version and whether the extension is connected and in sync. Copy the extension’s path, or open `chrome://extensions` in your browser with the path already on the clipboard || **Browsers** | Get a [pairing code](pair.md) with a live countdown, see every paired browser, unpair one or all |-| **Agents** | See which of Claude Code, Codex, Antigravity and Grok Build are ready, [switch](agents.md) between them, pick a model, install a missing one, or let Browsentic fix what one still needs |+| **Agents** | See which of the seven agent CLIs are ready, [switch](agents.md) between them, pick a model, install a missing one, or let Browsentic fix what one still needs || **Skills** | Every [skill](features/skills.md) the router can see and which folder it came from || **Activity** | Your standing [approvals](approvals.md), forgettable per site, and the downloads agents captured || **Logs** | `~/.browsentic/daemon.log`, followed live |diff --git a/docs/guide/troubleshooting.md b/docs/guide/troubleshooting.mdindex 2784ca5..6bc3c88 100644--- a/docs/guide/troubleshooting.md+++ b/docs/guide/troubleshooting.md@@ -65,6 +65,9 @@ Those three answer most questions. The daemon log also lives at `~/.browsentic/d| Cursor CLI reaches an MCP server you did not expect | A project `.cursor/mcp.json` does not replace your global one, so every server you gave Cursor loads too | Browsentic denies each by name for the run; if one still answers, update Browsentic and report it || Cursor CLI is less fenced off on Windows | Cursor's kernel sandbox has no Windows backend | Nothing to do — the deny rules still apply; treat a Windows run as `host`-class || `AGENT_UNSAFE`: *Grok Build offered this run …* | Grok offered tools Browsentic never asks for, so the run was stopped before the model saw them | Update Grok Build and Browsentic; report it if it persists |+| Qwen Code fails with *No auth type is selected* | Qwen has no provider configured, and its OAuth free tier ended on 2026-04-15 | Run `qwen` and use `/auth`, or export `OPENAI_API_KEY` with `OPENAI_BASE_URL` |+| Qwen Code cannot see an API key you exported | Only `QWEN_*`, `DASHSCOPE_*`, `BAILIAN_*` and `OPENAI_*` reach a run; the rest are sealed away | Point Qwen at one of those four providers |+| `AGENT_UNSAFE`: *Qwen Code registered …* / *loaded the MCP server …* | Qwen's own startup line named a tool or a server Browsentic denied, so the run was stopped before the model saw it | Update Qwen Code and Browsentic; report it if it persists |## Pages and tabsdiff --git a/docs/internals/agent-runs.md b/docs/internals/agent-runs.mdindex 9c70f15..365e801 100644--- a/docs/internals/agent-runs.md+++ b/docs/internals/agent-runs.md@@ -83,15 +83,15 @@ read the answer back*.**Adding an agent is one file plus one line in `runners/index.ts`.**-Every runner is given the same four things, by whichever mechanism its CLI supports:--| | Claude Code | Codex | Antigravity | Grok Build |-| --- | --- | --- | --- | --- |-| Run | `claude -p --output-format stream-json` | `codex exec --json` | `agy -p --output-format stream-json` | `grok -p --output-format streaming-json` |-| MCP server | `--mcp-config` + `--strict-mcp-config` | `-c mcp_servers.browsentic.*`, with `default_tools_approval_mode="approve"` — headless Codex refuses any MCP call it would have prompted for | `.agents/mcp_config.json` in its cwd | `.grok/config.toml` in its cwd, loaded with `GROK_FOLDER_TRUST=0`, and approved with `--allow MCPTool(browsentic__*)` |-| System prompt | `--append-system-prompt` | `-c developer_instructions` | `AGENTS.md` in its cwd | `--rules` |-| Follow-up turns | `--resume <session>` | `exec resume <thread>` | `--conversation <id>` | `--session-id <uuid>` names it, `--resume <uuid>` continues it, in a folder named after it |-| Kept off the machine by | `--allowedTools` + `--disallowedTools` | `-c sandbox_mode="read-only"`, `-c approval_policy="never"`, `-c features.multi_agent=false` | its own permission rules | `--tools`, `--permission-mode dontAsk`, `--deny`, `--sandbox workspace` |+Every runner is given the same five things, by whichever mechanism its CLI supports:++| | Claude Code | Codex | Antigravity | Mistral Vibe | Grok Build | Cursor CLI | Qwen Code |+| --- | --- | --- | --- | --- | --- | --- | --- |+| Run | `claude -p --output-format stream-json` | `codex exec --json` | `agy -p --output-format stream-json` | `vibe --prompt … --output streaming --trust --agent ask` | `grok -p --output-format streaming-json` | `cursor-agent -p --output-format stream-json --stream-partial-output` | `qwen -p --output-format stream-json --include-partial-messages` |+| MCP server | `--mcp-config` + `--strict-mcp-config` | `-c mcp_servers.browsentic.*`, with `default_tools_approval_mode="approve"` — headless Codex refuses any MCP call it would have prompted for | `.agents/mcp_config.json` in its cwd | `.vibe/config.toml` in a folder per conversation, every tool granted by name | `.grok/config.toml` in its cwd, loaded with `GROK_FOLDER_TRUST=0`, and approved with `--allow MCPTool(browsentic__*)` | `.cursor/mcp.json` in a folder per conversation, allowed as `Mcp(browsentic:*)` with every other server denied by name | `--mcp-config` + `--allowed-mcp-server-names`, under `--safe-mode`, which drops the ones on disk |+| System prompt | `--append-system-prompt` | `-c developer_instructions` | `AGENTS.md` in its cwd | `AGENTS.md` beside its config | `--rules` | `AGENTS.md` in its cwd | `--append-system-prompt` |+| Follow-up turns | `--resume <session>` | `exec resume <thread>` | `--conversation <id>` | `--resume <session>`, re-read from the folder the session began in | `--session-id <uuid>` names it, `--resume <uuid>` continues it, in a folder named after it | `--resume <session>` | `--session-id <uuid>` names it, `--resume <uuid>` continues it |+| Kept off the machine by | `--allowedTools` + `--disallowedTools` | `-c sandbox_mode="read-only"`, `-c approval_policy="never"`, `-c features.multi_agent=false` | its own permission rules | `--enabled-tools`, which is an allowlist | `--tools`, `--permission-mode dontAsk`, `--deny`, `--sandbox workspace` | deny rules in `.cursor/cli.json`, plus `--sandbox enabled` | `--safe-mode`, `--exclude-tools`, `--approval-mode default` |**Two CLIs do not put the browser tools in the model's list, and both are told so in the prompt.**Grok reaches MCP tools only through two meta-tools, `search_tool` and `use_tool`, under adiff --git a/docs/internals/guardrails.md b/docs/internals/guardrails.mdindex ccfe1bc..264f499 100644--- a/docs/internals/guardrails.md+++ b/docs/internals/guardrails.md@@ -345,6 +345,7 @@ type LocalTools = 'allowlist' | 'sandbox' | 'host'| **Antigravity** | `host` | No tool list and no sandbox flag; its built-in tools are governed by the user's own CLI settings, so a sealed environment is the only containment Browsentic applies || **Mistral Vibe** | `allowlist` | `--enabled-tools` is the whole of what loads: Browsentic's MCP tools, plus web search and fetch on a research run. The shell and file tools never exist in the run, and `--auto-approve` is a forbidden flag || **Grok Build** | `allowlist` | A per-run built-in tool list, `--permission-mode dontAsk`, deny rules, and a kernel sandbox for writes. Reads are closed by the tool list and a `Read` deny rather than the sandbox, and MCP servers the user set up in Grok itself still load |+| **Qwen Code** | `allowlist` | `--allowed-tools mcp__browsentic` is what a run may call without being asked, and a headless turn refuses everything it would otherwise have prompted for. `--safe-mode` is what makes the rest hold: it drops the user's hooks, extensions, bundled skills, `settings.json` MCP servers, `.mcp.json` and permission rules, while keeping `--mcp-config` — an explicit per-invocation argument rather than ambient state. Its cost is that it also **silently ignores `--core-tools`**, the fail-closed allowlist over Qwen's twenty-one core tools, so the built-ins are closed with `--exclude-tools` deny rules instead. A deny list cannot be fail-closed, so the `init` line is read back: it names every tool and MCP server that actually registered, and the reader ends the run with `AGENT_UNSAFE` on anything Browsentic did not ask for, before the model has spoken || **Cursor CLI** | `allowlist` | Deny rules in a project `.cursor/cli.json`, where **a deny beats every allow** — including the user's own. Measured against 2026.09.18: a headless run asked to `echo` a marker got `permissionDenied`, twice, and gave up. `--sandbox enabled` is asked for as well but not depended on, and it has no Windows backend. This is the first runner whose containment lives in a file rather than in argv, which is why `vetPlan` checks file *content* and not only that the file was written. `--trust` is **required**, not forbidden: headless Cursor refuses to start in a folder nobody trusted, and the folder is one Browsentic created and wrote every file in — it grants no tool permission of its own |#### Grok Build, and why not always-approve@@ -420,6 +421,20 @@ Each agent keeps only the prefixes it needs to authenticate:| Mistral Vibe | `MISTRAL_`, `VIBE_` || Grok Build | `XAI_`, `GROK_` || Cursor CLI | `CURSOR_` |+| Qwen Code | `QWEN_`, `DASHSCOPE_`, `BAILIAN_`, `OPENAI_` |++Qwen Code is the awkward one: it authenticates through whichever provider it is pointed at, and the+documented mainstream setup is `OPENAI_API_KEY` with `OPENAI_BASE_URL` at a DashScope endpoint, so+sealing that prefix would seal most installs out of their own model — and Codex already keeps it.+The `anthropic` and `gemini` auth types Qwen also accepts are **not** widened for: handing one+vendor's agent another vendor's key is what this exists to prevent, so `check()` reports a Qwen with+only `ANTHROPIC_API_KEY` set as *needs setup* rather than promising a login that cannot happen.++Sealing is also not absolute for Qwen, and it is worth saying so plainly: Qwen loads the first+`.env` it finds walking up from its working directory, then `~/.qwen/.env` and `~/.env`, for+variables not already present — so a key `sealEnv` stripped can come back from disk. It reaches the+model provider rather than the model, because the shell and file tools are denied, but the guarantee+is weaker there than for the other six.Plus **federated** cases, where a flag turns another prefix into the agent's own credentials: ClaudeCode on Bedrock authenticates with `AWS_*`, so sealing it would be sealing the agent out of its owndiff --git a/docs/reference/cli.md b/docs/reference/cli.mdindex f440b6a..a879996 100644--- a/docs/reference/cli.md+++ b/docs/reference/cli.md@@ -72,7 +72,7 @@ See [guide/pair.md](../guide/pair.md).| Command | Does || --- | --- || `browsentic agent` | Show which agent runs the side panel, and which are installed |-| `browsentic agent <name>` | Switch to `claude`, `codex`, `antigravity`, `vibe` or `grok` |+| `browsentic agent <name>` | Switch to `claude`, `codex`, `antigravity`, `vibe`, `grok`, `cursor` or `qwen` || `browsentic agent fix <name>` | Let Browsentic fix what that agent still needs || `browsentic agent model <name> [model]` | Pin that agent’s model in `config.json`; omit the model to go back to the CLI’s own default |diff --git a/docs/reference/errors.md b/docs/reference/errors.mdindex d86f326..26d0032 100644--- a/docs/reference/errors.md+++ b/docs/reference/errors.md@@ -66,9 +66,9 @@ repeatedly: failures carry the *fix* in the message, and a failed tool call neve| Code | Origin | Meaning and next move || --- | --- | --- || `AGENT_MISSING` | Runner | The chosen agent's binary is not on the *daemon's* `PATH`. Set `agents.<name>.bin` to an absolute path |-| `AGENT_NEEDS_PERMISSION` | Runner | Antigravity has no rule allowing Browsentic's MCP tools (`browsentic agent fix antigravity`), or Grok Build is not signed in (`grok login`) |+| `AGENT_NEEDS_PERMISSION` | Runner | Antigravity has no rule allowing Browsentic's MCP tools (`browsentic agent fix antigravity`), Grok Build or Cursor CLI is not signed in (`grok login`, `cursor-agent login`), or Qwen Code has no model provider configured (`qwen`, then `/auth`) || `AGENT_UNUSABLE` | Runner | The CLI is present but cannot run — usually too old for the flags Browsentic passes |-| `AGENT_UNSAFE` | Runner | The run was stopped before the agent could act on the machine: its plan had lost its containment, which is a bug in Browsentic, or Grok Build offered tools Browsentic never asks for. Update both, and report it |+| `AGENT_UNSAFE` | Runner | The run was stopped before the agent could act on the machine: its plan had lost its containment, which is a bug in Browsentic, or the CLI itself said it had not applied it — Grok Build offering tools Browsentic never asks for, or Qwen Code reporting a denied tool or a second MCP server as registered. Update both, and report it |## Guardrails