Metadata-Version: 2.4
Name: agentcassette
Version: 0.1.0
Summary: Deterministic record and replay tooling for LLM agents.
Author: AgentCassette contributors
License-Expression: MIT
Project-URL: Homepage, https://github.com/darshan-sc/agentcassette
Project-URL: Repository, https://github.com/darshan-sc/agentcassette
Project-URL: Issues, https://github.com/darshan-sc/agentcassette/issues
Requires-Python: >=3.11
Description-Content-Type: text/markdown
Requires-Dist: openai>=1.0.0
Provides-Extra: dev
Requires-Dist: build>=1.2.0; extra == "dev"
Requires-Dist: pytest>=8.0.0; extra == "dev"
Provides-Extra: langgraph
Requires-Dist: langgraph>=0.2.0; extra == "langgraph"
Provides-Extra: all
Requires-Dist: build>=1.2.0; extra == "all"
Requires-Dist: pytest>=8.0.0; extra == "all"
Requires-Dist: langgraph>=0.2.0; extra == "all"

# AgentCassette Python Runtime

Python hooks for recording and replaying non-streaming OpenAI Responses API calls with AgentCassette cassettes.

Install the Python runtime and bundled CLI:

```bash
python3 -m pip install agentcassette
```

This single installation provides both `import agentcassette` and the
`agentcassette` command. See the root `readme.md` for CLI usage, examples,
cassette format, and privacy behavior.
