Tag: replay

Showing 1-2 of 2

Apr 05, 20267 min readAgent PlaybookIntermediate60 min build

agent_debugger: Local-first debugger for AI agents with replay, failure memory and drift detection

Quickstart to run agent_debugger locally: capture and replay agent sessions, index recurring failures into a searchable memory, and surface smart highlights and drift—see the repo for commands.

agent-debugger local-first observability ai-agents debugging

+3 more

NewsUnited Kingdom

Open

Mar 25, 20265 min readAgent PlaybookIntermediate90 min build

Litmus: Record and deterministically replay full LLM agent executions for debugging and CI validation

Litmus records complete LLM agent executions (prompts, tool calls, outputs) so teams can deterministically replay failures, inject faults, and gate regressions in CI.

litmus llm-agents observability testing ci

+3 more

replay fault-injection reliability