Metadata-Version: 2.4
Name: docketeer-monty
Version: 0.0.3
Summary: Sandboxed Python execution plugin for Docketeer
Project-URL: Homepage, https://github.com/chrisguidry/docketeer
Project-URL: Repository, https://github.com/chrisguidry/docketeer
Project-URL: Issues, https://github.com/chrisguidry/docketeer/issues
Author-email: Chris Guidry <chris@theguidrys.us>
License-Expression: MIT
Classifier: Development Status :: 3 - Alpha
Classifier: License :: OSI Approved :: MIT License
Classifier: Programming Language :: Python :: 3
Classifier: Topic :: Scientific/Engineering :: Artificial Intelligence
Classifier: Topic :: Software Development :: Interpreters
Requires-Python: >=3.12
Requires-Dist: docketeer
Requires-Dist: pydantic-monty
Description-Content-Type: text/markdown

# docketeer-monty

Sandboxed Python execution plugin for
[Docketeer](https://pypi.org/project/docketeer/). Lets the agent write and run
Python code using [Monty](https://github.com/pydantic/monty), a minimal Python
interpreter written in Rust with microsecond startup and no access to the
filesystem, network, or standard library imports.

All of Docketeer's registered workspace tools are exposed as async functions
inside the sandbox, so the agent can compose multi-step operations in a single
`run_python` call.

Install `docketeer-monty` alongside `docketeer` and the tool is automatically
available. No additional configuration needed.

## Tools

- **`run_python`** — execute Python code in a sandboxed interpreter

## Example

```python
a = await read_file("notes/project.md")
b = await read_file("notes/ideas.md")
f"Project has {len(a)} chars, ideas has {len(b)} chars"
```
