Agent Postmortem Skill – Force AI coding agents to prove their work
Generates audit trails for agent work, but Cursor custom instructions already do this.
Make AI work reproducible, debuggable, and contestable — like real software.
Git for AI agent runs—pack, diff, replay, and verify agent work with content addressing.
Engineers building and debugging AI agent workflows and agentic applications
Langsmith (LangChain observability) · Arize (ML observability) · Git (conceptual model)
Generates audit trails for agent work, but Cursor custom instructions already do this.
Passive traffic capture + AI replay beats Selenium fragility for headless automation.
Deterministic capture + replay for LLM agents is a practical, under-served problem and this repo actually ships a 'golden run' zip with cold‑run verification hashes — that’s the kind of evidence chain auditors want. The focus on portable evidence bundles and stress verification suggests useful forensics and load testing of agent logic, but the release page looks early-stage; I'd like to see integrations (tooling for popular agent frameworks), richer docs, and example pipelines before I'd evangelize it.
Trajectory tracking beats diffs for agent memory, but terminal recording isn't new.
Logs AI conversations next to commits, but Cursor, Continue, and GitHub Copilot already do this.
Open-source Rewind alternative with diff-based OCR and a local HTTP API for agents.