A browser agent that books appointments, scans listings, sends emails, fills forms. All from a chat in your browser's side panel.
Add to Chrome
Describe what you need in plain English. The agent figures out the rest.
Type @ to point the agent at a specific tab — Gmail, GitHub, anything.
Run tasks every hour, every Friday at 9am, or once in 30 minutes.
The agent remembers context across sessions so it gets sharper over time.
Use Claude, ChatGPT, or Gemini. You pay your provider directly — no markup.
Confirms with you before any irreversible action — submitting forms, deleting, posting.
Pulls clean text from articles, emails, and docs so the agent gets the full content, not a screenshot guess.
Idle-only scheduling defers tasks until you stop using the browser, so it never hijacks your active work.
Recent scheduled runs stick around so you can ask "what did the morning Gmail check find?" and get a real answer.
No. It works inside your existing browser session, so it sees what you'd see when you're logged in — but no credentials ever leave your machine. We don't store passwords, cookies, or browsing data.
Safe Mode is on by default. Before any consequential action — submitting a form, sending a message, posting, deleting — TuClaw pauses and asks you to approve. You're always the one pressing the final button.
Any of the three works: Claude, ChatGPT, or Gemini. You bring your own API key from whichever you already use, and TuClaw talks to that provider directly. Switching is two clicks if you want to try another.
You're already paying your AI provider for usage. Charging a recurring fee on top of that felt wrong. Buy Max once, get the Max features forever.
Your prompts and page content go straight from the extension to your AI provider, using your key. Nothing is routed through our servers. License validation is the only network call we make, and it's just your key.