B0yko/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.
GitHub repository with 31 stars and 0 forks.
Language: Python
Topics: agent-evaluation, agent-reliability, ai-agents, benchmark, calibration, evals, human-in-the-loop, llm-as-a-judge, llm-evaluation, openai-compatible