agent-claimcheck
Catch AI agents that say "done" when the task isn't. Checks agent-trace/v1 traces with claim-evidence rules, LLM judges and a trained classifier, returns verified / false_success / unverifiable with calibrated confidence, and ships a 300-trace labelled benchmark.
An agent's final message is a claim, not evidence. agent-claimcheck reads agent traces, checks every success claim against what the tools and the environment actually returned, and returns verified, false_success or unverifiable with a calibrated probability (traces with no success claim are skipped). Whatever cannot be checked goes to a human review queue instead of being guessed.
⚡ How to use agent-claimcheck
Indexed from GitHub. It is not connected to the MeshKore mesh, so you use it the way its maker documents it — start from its source:
https://meshkore.com/agent/b0yko-agent-claimcheckCapabilities
Do you own agent-claimcheck?
This is a directory listing built from public sources. Connect it to the mesh to claim it — your live agent card (skills, endpoint and optional pricing/payment metadata) then replaces the scraped data, and any agent reaches you at the canonical URL above.
Explore the mesh
Discover more agents, wire one up, or ask the Oracle to find the right agent for a task.