Metadata-Version: 2.4
Name: donna
Version: 0.2.0
Summary: A deterministic workflow and state orchestration engine for LLM agents.
License-Expression: BSD-3-Clause
License-File: LICENSE
Keywords: ai,agent,cli,llm,workflow
Author: Aliaksei Yaletski
Author-email: a.eletsky@gmail.com
Requires-Python: >=3.12,<4.0
Classifier: Development Status :: 3 - Alpha
Classifier: Environment :: Console
Classifier: Intended Audience :: Developers
Classifier: Programming Language :: Python :: 3
Classifier: Programming Language :: Python :: 3.12
Classifier: Programming Language :: Python :: 3 :: Only
Classifier: Topic :: Software Development :: Build Tools
Classifier: Topic :: Utilities
Requires-Dist: jinja2 (>=3.1,<3.2)
Requires-Dist: markdown-it-py (>=4.0,<4.1)
Requires-Dist: mdformat (>=1.0.0,<1.1.0)
Requires-Dist: pydantic (>=2.12,<2.13)
Requires-Dist: typer (>=0.20,<0.21)
Project-URL: Homepage, https://github.com/Tiendil/donna
Project-URL: Issues, https://github.com/Tiendil/donna/issues
Project-URL: Repository, https://github.com/Tiendil/donna
Description-Content-Type: text/markdown

# State Machines for your AI Agents

`Donna` is a CLI tool that helps manage the work of AI agents like Codex.

It is designed to to invert control flow: instead of agents deciding what to do next, the `donna` tells agents what to do next by following predefined workflows.

The core idea is that most of high-level workflows are more algorithmic than it may seem at first glance. For example, it may be difficult to fix a particular type issue in the codebase, but the overall process of polishing the codebase is quite linear:

1. Ensure all tests pass.
2. Ensure the code is formatted correctly.
3. Ensure there are no linting errors.
4. Go to the step 1 if you changed something in the process.
5. Finish.

We may need coding agents on the each step of the process, but there no reason for agents to manage the whole grooming loop by themselves — it take longer time, spends tokens and may lead to confusion of agents.

