WebBrain

Open-source AI browser agent for Chrome and Firefox. Chat with any web page, automate browser tasks, and run multi-step agent workflows — powered by your choice of LLM.

• Page Reading — Extracts text, links, forms, tables, and interactive elements from any page
• Browser Actions — Click, type, scroll, navigate, and interact with page elements
• Ask / Act Modes — Read-only mode by default, full agent mode with confirmation
• Multi-Step Agent — Autonomous task execution with tool-use loops (configurable, default 25 steps)
• Continue from Limit — When the agent hits the step limit, click Continue to keep going
• Multi-Provider LLM — Supports local and cloud models:
  • llama.cpp (local, default) — No API key needed
  • OpenAI (GPT-4o, etc.)
  • OpenRouter (access 100+ models)
  • Anthropic Claude (native API)
• Side Panel UI — Clean chat interface that lives alongside your browsing
• Per-Tab Conversations — Each tab has its own chat history
• Streaming — Real-time token streaming from all providers
• Smart Context — Automatic context trimming, tool result limits, and emergency overflow recovery
• Copy Support — Copy buttons on code blocks and full messages
• Page Inspection Banner — Visual indicator when the agent is interacting with the page
• Stop Button — Abort the agent mid-execution at any time

git clone https://github.com/esokullu/webbrain.git

1. Open Chrome → chrome://extensions/
2. Enable Developer mode (top right)
3. Click Load unpacked → select the webbrain folder

git clone https://github.com/esokullu/webbrain.git

1. Open Firefox → about:debugging#/runtime/this-firefox
2. Click Load Temporary Add-on
3. Navigate to the webbrain-firefox folder and select manifest.json

Note: Temporary add-ons are removed when Firefox restarts. For permanent installation, the extension needs to be signed via addons.mozilla.org.

# Using llama.cpp
llama-server -m your-model.gguf --port 8080

# Or using Ollama (OpenAI-compatible)
ollama serve
# Then set base URL to http://localhost:11434/v1 in settings

Click the WebBrain icon → the side panel opens. Type a message like:

• "Summarize this page"
• "Find all links about pricing"
• "Fill in the search box with 'AI agents' and click Search"
• "Navigate to github.com and find trending repositories"

Click the gear icon or go to the extension's Options page to configure:

Display Settings:

• Verbose Mode — Show full tool call JSON (off by default)
• Screenshot Fallback — Use screenshots when DOM reading fails
• Max Agent Steps — Configurable step limit (5-50, default 25)

Providers:

webbrain/                          webbrain-firefox/
├── manifest.json (MV3)            ├── manifest.json (MV2)
├── src/                           ├── src/
│   ├── background.js              │   ├── background.js (+ background.html)
│   ├── agent/                     │   ├── agent/
│   │   ├── agent.js               │   │   ├── agent.js
│   │   └── tools.js               │   │   └── tools.js
│   ├── content/                   │   ├── content/
│   │   └── content.js             │   │   └── content.js
│   ├── providers/                 │   ├── providers/
│   │   ├── base.js                │   │   ├── base.js
│   │   ├── llamacpp.js            │   │   ├── llamacpp.js
│   │   ├── openai.js              │   │   ├── openai.js
│   │   ├── anthropic.js           │   │   ├── anthropic.js
│   │   └── manager.js             │   │   └── manager.js
│   └── ui/                        │   └── ui/
│       ├── sidepanel.html         │       ├── sidepanel.html
│       ├── sidepanel.js           │       ├── sidepanel.js
│       ├── settings.html          │       ├── settings.html
│       └── settings.js            │       └── settings.js
├── styles/                        ├── styles/
│   └── sidepanel.css              │   └── sidepanel.css
├── web/                           └── icons/
│   ├── index.html
│   └── vercel.json
└── icons/

Key difference: Chrome uses Manifest V3 (service worker, chrome.scripting, sidePanel API), Firefox uses Manifest V2 (background page, browser.tabs.executeScript, sidebar_action).

WebBrain accepts a small set of slash commands as the first thing on a line in the input box:

The default UI-first rule exists because API actions are invisible (you don't see what's being sent), often require separate auth tokens you may not have configured, and can have a much larger blast radius than a visible mis-click. Only use /allow-api when you've decided you want that tradeoff for a specific job.

• Firefox is meaningfully weaker than Chrome. Firefox has no equivalent to Chrome DevTools Protocol via chrome.debugger, so several Chrome-only features are missing in the Firefox build:
  • Click/type goes through the content-script path (document.querySelector + el.click()) instead of CDP Input.dispatchMouseEvent. This means no shadow-DOM piercing, no real trusted mouse events (some React/Vue handlers won't fire), no closed-shadow-root traversal, and no resolveSelector retry budget.
  • No SPA-navigation-aware retry extension.
  • No conversation persistence across background restarts.
  • No CDP screenshots. Auto-screenshot uses tabs.captureVisibleTab instead, which works for active tabs only and at slightly lower quality.
  • No closed shadow root support for read/extract tools.
  • Site adapters, vision detection, loop detection, and the auto-screenshot loop are mirrored to Firefox.
• SPA navigation detection in Firefox. Some single-page applications may not trigger content-script re-injection after client-side navigation.
• Firefox temporary add-on — Firefox requires the extension to be loaded as a temporary add-on during development, which is removed on restart.

• Conversation export/import — Save and load chat histories
• Custom tool definitions — User-defined tools via settings
• Keyboard shortcuts — Hotkeys for opening panel, sending messages, switching modes
• Context menu integration — Right-click → "Ask WebBrain about this"
• Screenshot/vision tool — Send screenshots to multimodal models for visual understanding
• Chrome Web Store / Firefox AMO — Official store listings

1. Create a new class extending BaseLLMProvider in src/providers/
2. Implement chat() and optionally chatStream()
3. Register it in src/providers/manager.js

All providers normalize to a common response format:

{ content: string, toolCalls: Array|null, usage: Object|null }

MIT — built by Emre Sokullu