Runbook AI

Your AI agent in the browser -- automate tasks, monitor pages for changes, schedule recurring runs, all in one click.

Your browser, on autopilot. Runbook AI is a local-first AI agent that lives in your browser sidepanel. Tell it what you want in plain language and watch it work — navigating, clicking, filling forms, and reading pages in real time, right in the browser you're already signed into. No scripts, no brittle selectors, no handing over your passwords. What it does: • Automates real workflows — multi-step tasks across tabs and pages: searches, form fills, data extraction, following links, even shadow DOM and iframes. • Turns any web page into an API — pull structured data out of a page and act on it, so sites without an API become one. • Works on a schedule — "check HN's top 5 every morning", "email me a stock-price report twice a day". Set it and forget it. • Watches pages for changes — cheap DOM-diff polling wakes the agent only when something actually changes: a new email, a PR flipping to green, a dashboard, a queue. • Delegates to your CLI — hand off self-contained sub-tasks to Claude Code and other coding agents on your machine without leaving the chat. • Plugs into your tools — drive the agent from external coding agents over the MCP bridge. Private by design: • Runs entirely in your browser — no Runbook-hosted servers in the loop. • Talks only to the LLM provider you choose: OpenAI, Anthropic, Gemini, local Ollama, or any OpenAI-compatible endpoint. • No remote-loaded code — the extension ships everything it runs. • Task results stay on your device and are deleted when you remove the extension. Discover and share runbooks at runbookai.net. Join the Discord community (https://discord.gg/SDtXkAKK2B) to share feedback and follow development. You can also invoke Runbook AI from Claude Code and other coding agents via runbook-ai-mcp (https://github.com/runbook-ai/runbook-ai-mcp), an MCP bridge to the extension.