WebBrain is a free, open-source browser extension that brings AI agent capabilities to your browser. Read pages, extract data, and automate web tasks — powered by your choice of LLM. The self-hostable alternative to proprietary browser AI plugins.
See how WebBrain reads pages, extracts data, and automates browser tasks.
A full-featured AI agent that lives in your browser sidebar and understands any web page.
Reads and comprehends any web page — articles, docs, dashboards, forms. Ask questions and get instant answers from the current page content.
Click, type, scroll, navigate, and interact with pages on your behalf. Automate repetitive tasks with natural language instructions.
Asks before consequential actions; read-only Ask Mode is the default.
Extract structured data from any page — tables, lists, links, forms. Export product catalogs, search results, or any page content. Works with PDFs.
Works with local llama.cpp, OpenAI, Claude, and OpenRouter. Use your preferred model — or run completely offline with local AI.
Your data stays yours. Run with a local LLM for zero data leakage. No telemetry, no tracking, no accounts required. Fully open-source.
Automatic context management prevents token overflow. Intelligently trims conversation history and limits tool output for smooth, uninterrupted sessions.
Pair a fast text-only model for planning with a separate vision-capable model for reading screenshots. Cheaper and faster than using a single big multimodal model for everything.
Optional plaintext bio — name, work email, company, a throwaway password — lets the agent breeze through low-stakes signup forms without asking every time. Off by default, all stored locally.
Off by default. Stored locally in your browser, never sent to WebBrain.
Dismisses consent banners (OneTrust, Cookiebot, Didomi, Quantcast) before reasoning about the page. Detects paywalls and tells you honestly instead of fabricating article content or trying to bypass them.
Plug in a CapSolver API key and the agent will auto-solve reCAPTCHA v2/v3, hCaptcha, and Cloudflare Turnstile when they block a step — instead of stopping to ask. Off by default, BYO key, no captcha service is shipped or contacted unless you turn it on.
Off by default. BYO key — no CAPTCHA service is contacted unless you enable it.
The plugin ships in English, Español, Français, Türkçe and 中文. Auto-detects your browser language on first use; switch anytime from the globe icon in the side panel. The marketing site is localized to match.
Screenshots are resized and iteratively JPEG-compressed before they leave your machine, keeping image tokens small. Smart context trimming and tool-output caps keep cloud bills predictable — no surprise spend on long sessions.
Connect to any OpenAI-compatible API or run a local model. Switch providers anytime from the extension settings. For local models, give them at least a 16k-token context window (8k works with Compact mode) — WebBrain auto-compacts the conversation as it nears the limit.
Offline knowledge, under your controlSet up the three essentials for private local chat: a Text Model, a Vision Model, and one offline Wikipedia edition.
Install WebBrainConnect Claude Code, Codex, Cursor, OpenCode, or any stdio MCP client to your signed-in Chromium tabs. WebBrain keeps the task-level permission gate in the browser — and now returns structured JSON too.
No cookie export, headless login, or credential replay. The local server hands the task to WebBrain in Chrome, Edge, Brave, Opera, or Vivaldi. Firefox is not supported by the MCP bridge.
WebBrain sits at the intersection of browser-native AI plugins and full agent frameworks. Here's how it stacks up.
| Feature | WebBrain | Claude in Chrome |
|---|---|---|
| Open Source | MIT License | Proprietary |
| Price | Free forever | Requires Claude Pro ($20/mo) |
| Local LLM support | llama.cpp, Ollama | No — Claude only |
| Multi-provider | All OpenAI-compatible endpoints | Claude only |
| Chrome | Yes (MV3) | Yes |
| Firefox | Yes (MV2) | No |
| Side panel UI | Yes | Yes |
| Fully offline | Yes (with local LLM) | No — cloud required |
| Self-hostable | Yes | No |
| Aspect | WebBrain | OpenClaw / Browser-Use / etc. |
|---|---|---|
| What is it? | Browser extension (end-user tool) | Agent framework / SDK (developer tool) |
| Target user | Anyone — no coding needed | Developers building automations |
| Installation | One-click browser install | Python/Docker setup required |
| UI | Built-in side panel chat | No UI — code or API only |
| Browser control | Content script (lightweight) | CDP / Playwright (full control) |
| Multi-tab workflows | Per-tab conversations | Programmable multi-tab orchestration |
| Headless mode | No — runs in your browser | Yes — headless automation |
| Extensibility | Add custom LLM providers | Full Python SDK, custom tools |
| Best for | Daily browsing AI assistant | Automated scraping / testing pipelines |
WebBrain is a browser extension for end users who want an AI assistant while they browse. Agent frameworks like OpenClaw are developer tools for building automated browser pipelines. Different tools for different jobs — and you can use both.
Available for Chrome, Edge, and Firefox. Free, open-source, no account required.
Manifest V3 · Chrome 116+ · Also works with Brave, Opera, Vivaldi, and other Chromium-compatible browsers.
Manifest V3 · Windows 10/11 · Requires Microsoft Edge on Windows.
WebBrain
