Your LLM tests, fast, free, and deterministic.

Cassette records your app's LLM & agent API calls, then replays them in CI — so tests stop being slow, expensive, and flaky. The team tier catches agent behavior regressions on every PR.

Start free Get Team

Start in one line

Free & open source. Records to local files; no gateway, no infra.

pip install cassette-sdk        # Python
npm install cassette-sdk        # Node / TypeScript
from cassette.recorder import http_client
from openai import OpenAI
client = OpenAI(http_client=http_client(project="demo"))  # records → replays

How it works

1. Record

First test run saves each LLM response to a portable cassette file.

2. Replay

Every run after replays it — instant, $0 tokens, no flakiness.

3. Gate

On each PR, the Team gate flags when your agent's behavior actually changed.

Pricing

Free / OSS
£0

The recorder + replay, local cassettes, unlimited. For individuals & open source.

Install
Team
£18/dev/mo

Shared registry + the GitHub PR behavior-gate on semantic drift. Storage included.