WebBrain

WebBrain is a web browser extension that puts an AI agent in a side panel next to your tabs. Ask it about the page you're on, or hand it a task and let it click, type, and navigate its way through. It runs on the model you choose — a local llama.cpp or Ollama server, a frontier cloud API, or the managed default that needs no setup at all.

Install

Install from the Chrome Web Store, Firefox Add-ons, or Edge Add-ons.

git clone --filter=blob:none https://github.com/webbrain-one/webbrain.git

Chrome — open chrome://extensions/, enable Developer mode (top right), click Load unpacked, and select the webbrain/src/chrome folder. For an isolated copy that won't pick up stray working-tree files, run npm run build:chrome first and load webbrain/build/chrome instead.

Firefox — open about:debugging#/runtime/this-firefox, click Load Temporary Add-on, and select src/firefox/manifest.json (or build/firefox/manifest.json after npm run build:firefox). Temporary add-ons are removed when Firefox restarts; permanent installation requires signing via addons.mozilla.org.

Use it

Click the WebBrain icon to open the side panel, then type something 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"

Three modes control what the agent is allowed to do:

Mode	What it can do
Ask	Read-only. Reads the page, answers questions, fetches URLs.
Act	Clicks, types, navigates, uploads, downloads, fills forms.
Dev	Adds page source, styles, console, network, and reversible page edits.

WebBrain picks the mode for each message: it stays in Ask unless your message asks it to do something in the browser. Start a message with /ask, /act or /dev to choose the mode yourself.

Pick a model

WebBrain Compass 1.0 is the default and needs no API key or local setup.

Local models need no API key either. Point WebBrain at any OpenAI-compatible server:

llama-server -m your-model.gguf --port 8080          # llama.cpp
ollama serve                                          # Ollama  → :11434/v1
vllm serve your-model --port 8000                     # vLLM    → :8000/v1
python -m sglang.launch_server --model-path your-model --port 30000

LM Studio (:1234/v1), Osaurus (:1337/v1), Jan (:1337/v1), LocalAI (:8080/v1), and GPT4All (:4891/v1) work the same way. WebBrain Companion is our separate desktop app for local models and supported account subscriptions. Download it for Windows, macOS, or Linux, then choose the WebBrain Companion provider card, click Load Models, select a model, and test the connection. The local endpoint defaults to http://127.0.0.1:8327/v1 and needs no API key on this computer. See the Companion setup. A generic Local OpenAI-compatible Proxy card remains available for other OpenAI-compatible gateways. Unsloth Studio (Local) uses the same OpenAI-compatible path with the Studio port and sk-unsloth- API key configured by the user; see the Unsloth Studio setup. Osaurus (Local) connects to the Mac's Osaurus server with model discovery, streaming, and tool calls; see the Osaurus setup. Size the loaded context window for the selected tier's system prompt and tool schemas, the page/history, and the requested output. 16k is a configuration fallback, not a guaranteed minimum; Compact is not guaranteed to fit 8k. Mid and Full can exceed 16k before history accumulates, and compaction cannot shrink fixed instructions or schemas. The sizing estimate is not the model's exact tokenizer; see the context guidance. WebBrain auto-detects the real window for llama.cpp, Ollama, and LM Studio, and auto-compacts the conversation as it fills up. For Ollama, llama.cpp, LM Studio, and LocalAI, it also reads native server metadata before adding screenshots; Settings → Models → LLM provides Auto, Force on, and Off overrides. When the optional Model field is blank, the loaded-model capability is rechecked on every user turn so a server-side hot swap takes effect. There is also a preview ollama launch webbrain --model <model> handoff. Details: providers and models.

Cloud APIs — OpenAI, Anthropic Claude, Google Gemini, Azure OpenAI, AWS Bedrock, Mistral, DeepSeek, xAI Grok, MiniMax, Kimi, Qwen, z.ai GLM, Groq, Together, Cloudflare, Nvidia NIM, Hugging Face, Fireworks, OpenRouter, and more. Settings → Models → LLM ships 121 built-in provider cards on Chromium (120 on Firefox), including an endpoint-free local WebGPU option with the tested LFM2.5 2.6B preset and an experimental custom Hugging Face ONNX repository option — see the full catalog.

This is the beginning of the README. Read the rest at the original. Read the full README ↗