Record Replay Python Packages

cassetter

Rust-powered HTTP cassette recorder for Python tests. Safe by default.

retracesoftware

Turn failed Python tests and CI runs into replayable debug sessions.

jevassert

Record/replay regression tests for Jev (TypeSafe System One) question packs — accuracy, calibration and cost gates in CI

karellen-rr-mcp

MCP server for rr reverse debugging — enables AI assistants to record, replay, and inspect program executions via GDB/MI

agent-chronicle

Record-and-replay for agent decision graphs: reproduce a prod agent failure as a committed regression test, and re-run your fix without live LLM calls.

agent-observability-trace-cli

Deterministic record/replay for LLM agent HTTP traffic. Replay a failed run offline in under 1ms, zero API cost.

agentos-platform

Deterministic record, replay, and git-bisect for AI agent runs. Reproduce a broken run byte-for-byte offline, then binary search to the commit that broke it.

pytest-agentreplay

Regression tests for AI agents. Record once, replay offline, catch behavioural regressions.

orgecc-command-mock

VCR for subprocess calls. Record and replay CLI command outputs (Git, Docker, etc.) for fast, deterministic Python tests

replayx

Record and replay HTTP/S interactions for httpx. Fast, offline, deterministic tests. Install: pip install replayx

mcp-rec

VCR for the Model Context Protocol. Record any MCP server's traffic to JSONL, replay it deterministically — for tests, bug reports, and offline demos.

tracefork

Time-travel debugger for AI agents: record a run to a content-addressed tape, replay it bit-exact for $0 (hash-verified), fork any step, and measure causal blame with confidence intervals.

kopya

Kopya - Record your app's real API calls once. Replay them offline, forever.

promptecho

Record & replay for LLM API calls. Like vcrpy / nock, but built for the way LLM traffic actually behaves.

backspin

The flight recorder for AI agents — record, replay, diff & debug agent runs, 100% local.

vernier-cli

Deterministic diff for agent behaviour. Record an agent run, re-drive it after a change, and get a rule-based verdict on what diverged. No LLM judge.

lockstepd

Deterministic record/replay debugger for LLM agent runs - record once, replay bit-exact offline, fork & bisect failures. No keys needed to test.

flightbox

Record, replay, and diff every LLM call your AI agent makes

agent-observability-trace

Deterministic record/replay for LLM agent HTTP traffic. Replay a failed run offline in under 1ms, zero API cost.