Launching today

Agentic Web Check

Launching today

Test whether AI agents can actually use websites

2 followers

Test whether AI agents can actually use websites

2 followers

Visit website

Open-source browser evaluator for AI agents. Agentic Web Check combines 43 deterministic checks with real read-only browser tasks and programmatic PASS/FAIL/BLOCKED/INCONCLUSIVE verdicts, plus a separate safety review. It runs locally with no telemetry.

Free

Launch tags:Open Source•Developer Tools•Artificial Intelligence

Launch Team

Maker

📌

I built Agentic Web Check because I wasn't satisfied with the idea of calling a website “AI-ready” just because it passed a static checklist. I wanted to test the harder question: can an agent actually use it? That led me to combine browser-level checks with real tasks and, importantly, verify the result from the page state instead of trusting the agent to report success. The project is still v0.1.0, so I'm launching it partly to get real technical feedback. I'm especially interested in where the methodology gets things wrong, which checks are actually useful, and what should be measured next. If you try it, I'd be much more interested in what failed or surprised you than in a generic “looks good” comment.

Report

16h ago