47,133 repositories indexed
1–6 of 6 · Most stars
HarnessRouter Community Edition: the self-hosted, Apache-2.0 edition of the unified interface for agent harnesses. Run Codex, Claude Code, Hermes, PI, DSH, and more through one API, with sessions, streaming, files, cancellation, and failure handling. Implements the Unified Harness Protocol (UHP), an open standard. Your keys, your infrastructure.
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.
Learning to Recover from LLM Agent Failures at Test Time
A unified framework for tabular probabilistic regression, time-to-event prediction, and probability distributions in python
Self-healing Docker CI: BuildKit failure taxonomy, Claude Code fixes, rebuild verification, capped retries.
Open-source simulation harness for testing AI agents. Simulate LLM and tool calls to test edge cases, failure paths, and agent logic without live API calls.