replay

Yohei Nakajima's open-source ActiveGraph Python runtime uses an append-only event log as the source of truth for long-running agents, enabling replay, forking, and lineage. A paper and v1.2.0 have been released.

Replay QA is a tool that helps developers find bugs before users do, by capturing and replaying sessions.

Retrace is a tool that allows developers to debug AI agents by replaying and forking runs.

PreAct compiles successful agent runs into small state-machine programs, enabling 8.5-13x faster replay on repeated tasks without per-step language model calls, with runtime screen checks to ensure correctness.

PreAct compiles successful task runs of computer-using agents into small state-machine programs, allowing fast replay (8.5–13× faster) on repeated tasks by skipping per-step language model calls, while verifying screen states at each step and falling back to the agent when mismatches occur.

Fact0 is a tool for tamper-evident audit trails and execution replay for AI agents, integrating with LangChain, CrewAI, and LlamaIndex. It provides cryptographic verification, execution DAG visualization, and searchable logs.

A developer tool that records AI agent runs inside a sandboxed GitHub repository, capturing terminal/browser sessions and turning them into replayable narrated videos for improved observability.