I've been frustrated with AI assistants that describe what they would do instead of actually doing it. So I built Cerebro.
The core idea is simple: give the AI real tools and let it run.
What it can do
Web browsing — Not a search summary. A real headless browser that navigates to pages, clicks through links, and extracts what it needs. "Go to ProductHunt and find today's top 5 launches" — it opens the site and does it.
Web search — Real-time search. Not limited to training data.
Email — Compose and send emails on your behalf. "Research my top 3 competitors and email me a report" is a single command.
Multi-step tasks — Chain actions together. Research + summarize + email, all in one go.
The uncensored part
Most AI assistants refuse or hedge on anything remotely controversial. Cerebro doesn't. It presents all sides of any topic and lets you decide what to think. It treats you like an adult.
Tech
Built on OpenClaw — an open-source AI agent framework. The AI orchestrates tools in a loop: plan, execute a step, observe the result, continue. The browser is a real Chromium instance with CDP.
Every user session is isolated. Data doesn't cross between users.
Rough edges
Complex multi-step tasks sometimes need a retry. Heavy JavaScript sites occasionally trip up the browser. Still in beta.
Try it
cerebro.vip — free, just Google sign-in. No API keys, no setup.
I'm actively building based on feedback. Curious what the dev community thinks — especially what you'd break first.
Top comments (1)
Really cool build! 🚀 It’s refreshing to see an AI agent that actually does things instead of just talking about them. The practical examples and real‑world use cases make this more than just a concept — it feels like something people can actually adopt. Loved the transparency on how it works under the hood too. Great job!