by webbrain-one
Open-source AI browser agent for Chrome and Firefox (monorepo) 🧠
# Add to your Claude Code skills
git clone https://github.com/webbrain-one/webbrainwebbrain is an open-source ai agents skill for AI coding assistants such as Claude Code, Codex CLI, and ChatGPT, built by webbrain-one. Open-source AI browser agent for Chrome and Firefox (monorepo) 🧠. It has 141 GitHub stars.
webbrain's catalog security scan is still queued. You can run an instant dependency and prompt-injection check now with the "Scan for vulnerabilities" button above.
Clone the repository with "git clone https://github.com/webbrain-one/webbrain" and add it to your Claude Code skills directory (see the Installation section above).
webbrain is primarily written in JavaScript. It is open-source under webbrain-one on GitHub, so you can review or fork the full source.
Yes. SkillsLLM lists many other AI Agents skills you can browse and compare side by side. Open the AI Agents category from the badge at the top of this page, or use the Related Skills and comparison links further down to weigh webbrain against similar tools.
No comments yet. Be the first to share your thoughts!
Unlocks once the catalog security scan passes (runs nightly).
The deep catalog scan for this skill is still queued. Run an instant dependency check now instead.

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.
stepfun/step-3.7-flash; access 100+ models)go_back / go_forward history tools instead of CSP-sensitive page JavaScriptfetch_url suggestion while preserving the UI-first and /allow-api mutation policywebbrain-tools manifest. FreeSkillz.xyz is enabled by default for YouTube transcripts and public media downloads, and can be removed.0.15 for browser-control decisions; Ask mode uses 0.3, and dedicated vision screenshot descriptions use 0git clone https://github.com/webbrain-one/webbrain.git
chrome://extensions/webbrain/src/chrome foldergit clone https://github.com/webbrain-one/webbrain.git
about:debugging#/runtime/this-firefoxsrc/firefox/ and select manifest.jsonNote: 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
# Or run: ollama launch webbrain --model <model>
# Or using Jan (OpenAI-compatible)
# Start Jan's local API server and use http://localhost:1337/v1
# Or using vLLM / SGLang (OpenAI-compatible)
vllm serve your-model --port 8000
python -m sglang.launch_server --model-path your-model --port 30000
WebBrain supports Ollama today through the local OpenAI-compatible provider. A new ollama launch webbrain --model <model> handoff can also configure WebBrain automatically, but it is not integrated into upstream Ollama yet. For now, try it from the codex/ollama-webbrain-launch-handoff branch of esokullu/ollama; we hope Ollama will integrate it upstream.
git clone https://github.com/esokullu/ollama.git
cd ollama
git switch codex/ollama-webbrain-launch-handoff
cmake -S . -B build -G Ninja -DOLLAMA_MLX_BACKENDS=
cmake --build build --parallel 8
OLLAMA_ORIGINS="chrome-extension://*,moz-extension://*" ./ollama serve
./ollama launch webbrain --model <model>
Context window: For reliable agent runs, load a local model with at least a 16k-token context window (the usable minimum). 8k can work with Compact mode enabled (Settings → per-provider checkbox); 4k is too small to hold the system prompt + tool schemas. WebBrain auto-compacts the conversation as it nears the window — it assumes 16k for local models unless you set an explicit context size, so give the model server (e.g.
llama-server -c 16384) enough room.
Click the WebBrain icon → the side panel opens. Type a message like:
Click the gear icon or go to the extension's Options page to configure:
Display Settings:
Skills:
read_youtube_transcript, resolve_public_media, and download_public_media through its skill manifest; remove it from Settings → Skills if you do not want those tools available.webbrain-tools JSON manifest. Importing a skill is the trust boundary for its declared HTTPS endpoint; download-job skill tools still run in Act mode and use the normal Downloads permission gate before saving files.resultPolicy: "untrusted" so they are wrapped as data, not instructions.Providers:
| Provider | Base URL | API Key | Default Model |
|---|---|---|---|
| llama.cpp | http://localhost:8080 |
Not needed | (your loaded model) |
| Ollama | http://localhost:11434/v1 |
Not needed | (your loaded model) |
| LM Studio | http://localhost:1234/v1 |
Not needed | (your loaded model) |
| Jan | http://localhost:1337/v1 |
Not needed | (your loaded model) |
| vLLM | http://localhost:8000/v1 |
Optional | (your served model) |
| SGLang | http://localhost:30000/v1 |
Optional | (your served model) |
| OpenAI | https://api.openai.com/v1 |
Required | gpt-5.5 |
| Anthropic Claude | https://api.anthropic.com |
Required | claude-sonnet-4-6 |
| Google Gemini | https://generativelanguage.googleapis.com/v1beta/openai |
Required | gemini-3.1-flash |
| Cloudflare Workers AI | https://api.cloudflare.com/client/v4/accounts/{account_id}/ai/v1 |
Required (plus Account ID) | @cf/zai-org/glm-5.2 |
| Mistral AI | https://api.mistral.ai/v1 |
Required | mistral-large-latest |
| DeepSeek | https://api.deepseek.com/v1 |
Required | deepseek-v4-flash |
| xAI Grok | https://api.x.ai/v1 |
Required | grok-4.3 |
| Nvidia NIM | https://integrate.api.nvidia.com/v1 |
Required | meta/llama-3.1-8b-instruct |
| Groq | https://api.groq.com/openai/v1 |
Required | llama-3.3-70b-versatile |
| MiniMax | https://api.minimax.chat/v1 |
Required | minimax-m2.7 |
| Alibaba Cloud (Qwen) | https://dashscope.aliyuncs.com/compatible-mode/v1 |
Required | qwen-max |
| OpenRouter | https://openrouter.ai/api/v1 |
Required | stepfun/step-3.7-flash |
src/chrome/ src/firefox/
├── manifest.json (MV3) ├── manifest.json (MV2)
├── src/ ├── src/
│ ├── background.js │ ├── background.js (+ background.html)
│ ├── agent/ │ ├── agent/
│ ├── content/ │ ├── content/
│ ├── providers/ │ ├── providers/
│ ├── network/ │ ├── network/
│ ├── trace/ │ ├── trace/
│ ├── ui/ │ └── ui/
│ └── offscreen/ ├── styles/
├── styles/ ├── icons/
└── icons/ └── LICENSE
web/
├── index.html
├── privacy.html
└── vercel.json
Key difference: Chrome uses Manifest V3 (service worker, chrome.scripting, sidePanel API), Firefox uses Manifest V2 (background page, browser.tabs.executeScript, sidebar_action).
Deeper docs live in docs/: