AgentReplay
Trace, Eval, compare, and improve AI agents locally
2 followers
Trace, Eval, compare, and improve AI agents locally
2 followers
The open-source, 100% local observability and evals platform for AI agents. Trace every LLM call, evaluate with 20+ evaluators — all without sending data to the cloud.
Free
Launch Team / Built With
Render Sandboxes: a computer for every agentRun untrusted code safely. Idle sandboxes cost nothing
Promoted
