LLM-mock – Record real LLM API responses once, replay them in tests
Intercepts HTTP transport layer so production code needs zero changes.
Record real LLM API responses once, replay them in tests forever — no API key, no cost, no non-determinism.
HTTP-layer interception for deterministic LLM tests without touching production code.
Python developers testing LLM-integrated applications
betamax · vcrpy · pytest-recording
Intercepts HTTP transport layer so production code needs zero changes.
Hub-and-spoke IR translates LLM APIs without N^2 adapter hell.
VCR for LLM calls—eliminates API costs and non-determinism in agent testing.
Fork from failed agent runs and prove fixes before shipping—LangSmith doesn't do this.
Independent billing receipts when OpenAI and Anthropic grade their own invoices.
Zero-code instrumentation via monkey-patching, but Langsmith, Helicone, and Arize already do this.