Trace-native CI/CD for AI agents: grade production traces, cluster failures, freeze them into replayable regression tests, and block PRs that regress. Self-hostable.
Repository Index
47,133 repositories indexed
1–3 of 3 · Most stars
Feather agent harness, training integrations, and evaluation tools for knowledge work
Fault-injected tool environments with side-effect grading for evaluating and post-training LLM agents