Record-replay debugger for AI agent runs.
An agent only touches the outside world through a narrow boundary: model calls in, tool calls out. rewind captures everything crossing that boundary, then replays it exactly — or branches from any step to explore alternate trajectories.
pip install rewind-llm# Record a session
rewind record -- claude "fix the bug"
# Replay it
rewind replay traces/anthropic_20260101_120000.jsonl -- claude "fix the bug"rewind ls # List traces
rewind show <trace.jsonl> # Pretty-print
rewind diff <a.jsonl> <b.jsonl> [--html out.html] # Diff traces
rewind branch <trace> --at N --edit|--inject|--live # Branch
rewind record -- <cmd> # Record via proxy
rewind replay <trace> -- <cmd> # Replay via proxypip install -e ".[dev]"
python -m pytest tests/ -vMIT
