Browsentic

Kendi giriş yapılmış tarayıcınızı (Chrome, Edge, Brave, Arc, Firefox) herhangi bir MCP istemcisinden yönetin: gerçek sekmelerinizde gezinin, tıklayın, formları doldurun ve sayfaları okuyun.

Dokümantasyon

https://github.com/user-attachments/assets/21c9fb4d-6068-4091-9ab8-8650fe36a10d

Browsentic - a completely integrated agentic browser harness

Chrome Web Store version npm version npm downloads CI node license

Manifest V3 macOS build Windows build Firefox build

No account · No auth · No API key · No cloud · No telemetry · Local first

Your real, logged-in browser, driven from an AI side panel by the agent CLI you already have.
Also an optional MCP server, so any MCP client can drive the same browser.

Works in
Chrome  Firefox  Edge  Brave  Arc

Runs on
Claude Code  Codex  Antigravity  Mistral Vibe (beta)  Grok Build (beta)  Cursor CLI (beta)  Qwen Code (beta)  OpenCode (beta)

Quick Start

Browsentic is your browser's superpower, free and open source. One install sets up everything, the extension included.

macOS: one line installs the app, which brings Node and everything else:

curl -fsSL https://browsentic.com/install.sh | sh

Windows: one line in PowerShell installs the Windows app (experimental):

irm https://browsentic.com/install.ps1 | iex

Any platform, with Node.js 20 or newer:

npx browsentic@latest setup

Setup asks which browser you use and opens Browsentic's store page in it (the apps do the same from their Overview tab). Press Add to Chrome (Add in Firefox; Edge first asks you to allow extensions from other stores), then click Browsentic in the toolbar and enter the code setup shows. From then on the extension updates itself from its store.

The extension is on the Chrome Web Store for Chrome, Brave, Arc, Vivaldi and Opera, on Edge Add-ons for Edge, and Firefox gets an add-on signed by Mozilla:

Available in the Chrome Web Store Get it from Edge Add-ons Signed add-on for Firefox

If you added the extension from a store first, run the same line and enter the code it shows.

The side panel runs on an agent CLI you are signed in to: Claude Code, Codex or another supported one. It uses the one you already have, so there is no API key, no account and no extra subscription.

Full guide, Firefox and unpacked installs included: browsentic.com/docs/guide/install

Key Capabilities

🧭 Side panel, human in the loop🤖 Every major agent CLI🎯 50+ deterministic tools
🌐 All Chromium + Firefox🗺️ Full browser navigation🧩 Solves captchas on the way
📄 Reads files, acts on them↕️ Uploads & downloads🧠 Creates its own skills
⚡ Writes & runs live tools🎙️ Voice, text or show it once👁️ Point at what you mean
⏱️ Monitors & schedules🛡️ Guardrails & approvals🔌 Optional MCP server
📱 Drives Chrome on your Android phone (experimental)

How It Works

How an instruction becomes a click

The same flow, as text
You ──speak or type──> Extension ──local WebSocket──> Browsentic Bridge ──spawns──> your agent CLI
                            ▲                                        (claude │ codex │ agy │ …)
                            └──────────────────── page actions ──────────────────────┘

Any MCP client ──stdio──> browsentic mcp ──> the same Bridge ──> the same browser

The extension dials out to Browsentic Bridge, because a Manifest V3 service worker cannot listen for connections. One Bridge owns the browser link, so several MCP clients can share one browser. Everything binds to 127.0.0.1.

Side Panel and Desktop Apps

The side panel in Chrome partway through a run, waiting for approval to send a reminder; the Mac app's Overview and its one-click setup; the Windows app's agent picker and its Android phone checks

The side panel is where you work with the agent. Every page action shows up as a step, and consequential ones, such as submitting a form, wait for your approval.

The desktop apps for macOS and Windows (experimental) install Node and Browsentic Bridge in one click, turn the Bridge on and off, add the extension to each browser, pick the agent CLI and its model, and check an Android phone before the side panel drives it.

Resources

Privacy and Security

Nothing connects until you pair, and both ends prove who they are. The agent asks before any consequential action, credentials on a page are sealed before the agent sees them, and the sites you block are off-limits to every agent: the browser enforces that list, where no agent can reach it. The full model is in SECURITY.md, and what it does not cover is in Limits.

Contributing

Bugs and ideas are welcome. Start at CONTRIBUTING.md.

License

Browsentic is licensed under the Apache License 2.0. Versions up to 0.7.15 were released under the MIT License.

  • Source Available: Always visible source code
  • Local First: No cloud component, no telemetry, no account
  • Extensible: Add your own page capabilities, skills and agent runners

What does Browsentic mean?

Short answer: "Browse" + "agentic".

Long answer: Most browser automation hands the work to a different browser: a headless one, in a container, logged in to nothing. Browsentic works the other way round. The agent acts in the browser you are already looking at, with the sessions you are already signed in to: browsing, made agentic, where you already browse.