chrome-devtools-mcp vs karpathy/autoresearch
Both in the agentic & browser category. Side-by-side — pick the one that fits your stack tonight.
Give your agent the same debug tools you use in Chrome's inspector.
- rating
- 4★
- tested
- ✓ loya-tested
- cost
- free
- install
- drop-in
- stars
- 36,664
- updated
- 4d ago
You never hit 'Inspect' in Chrome and don't care what's happening under the hood.
Karpathy's proof-of-concept for letting AI agents do research on their own.
- rating
- 4★
- tested
- —
- cost
- free
- install
- needs-wiring
- stars
- 75,483
- updated
- 4w ago
You want a ready-to-use tool. This is research — better studied than installed.
why it matters · chrome-devtools-mcp
The Chrome DevTools panel — the thing you see when you right-click and hit Inspect — has network tabs, console logs, performance profilers, and memory tools. This plug exposes all of that to Claude. Your agent can watch network requests, read console errors, run Lighthouse audits, and take performance traces — then fix the bug directly. Built by the Google Chrome team. Pair it with Playwright for actions + DevTools for observation.
why it matters · karpathy/autoresearch
Andrej Karpathy built this to show what it looks like when you point AI agents at a scientific problem and let them iterate — they propose experiments, run them, read the results, propose new ones. Minimal babysitting. Not a drop-in tool you install. It's a pattern to learn from: how to scope a goal, what a feedback loop looks like, where to add guardrails. If you're trying to build an autonomous agent for your own topic, study this one as a case study.