Current collected state Current
Observed since 20 Oct, 23:35 UTC
No superseded metadata states collected. Unchanged observations do not create new revisions.
Replay and diff AI agent event trajectories for debugging regressions. Python port of @mukundakatta/agent-trajectory-replay.
Replay and diff AI agent event trajectories. Pure Python, zero deps. Python port of @mukundakatta/agent-trajectory-replay.
pip install agent-trajectory-replay-py
from agent_trajectory_replay import summarize_trajectory, diff_trajectories, replay_trajectory
events = [{"type": "tool_call", "tool": "search"}, {"type": "final", "content": "ok"}]
summarize_trajectory(events) # TrajectorySummary(steps=2, tool_calls=1, errors=0, final_output='ok')
diff_trajectories(events, events) # [] (no diff)
replay_trajectory(events, {"final": lambda e, s: s.update({"a": e["content"]})})
# {"a": "ok"}
MIT
Download counts and popularity will appear here as the collector receives them.
| Version | Published | Direct dependencies | Open version |
|---|---|---|---|
| 0.1.0 | 27 Apr 2026 | 1 |
This describes our collected data; it is not a security assessment.
Shared repository data · GitHub
Observed since 20 Oct, 23:35 UTC
No superseded metadata states collected. Unchanged observations do not create new revisions.
package:221a7cefc5f06b7b39b6b19367f76f73487d8ce2f3009995502fa78c25ddf428