Metadata-Version: 2.4
Name: slowburn
Version: 0.1.0
Summary: Cost-Sustainable Concurrent Execution for Long-Horizon LLM Agents
Project-URL: Homepage, https://github.com/adivekar-utexas/slowburn
Project-URL: Repository, https://github.com/adivekar-utexas/slowburn
Project-URL: Issues, https://github.com/adivekar-utexas/slowburn/issues
Author-email: Abhishek Divekar <adivekar@utexas.edu>
License-File: LICENSE
Keywords: agents,concurrency,cost-optimization,llm,long-horizon
Classifier: Development Status :: 2 - Pre-Alpha
Classifier: Intended Audience :: Developers
Classifier: Intended Audience :: Science/Research
Classifier: License :: OSI Approved :: MIT License
Classifier: Operating System :: OS Independent
Classifier: Programming Language :: Python :: 3
Classifier: Programming Language :: Python :: 3.10
Classifier: Programming Language :: Python :: 3.11
Classifier: Programming Language :: Python :: 3.12
Classifier: Programming Language :: Python :: 3.13
Classifier: Topic :: Scientific/Engineering :: Artificial Intelligence
Classifier: Topic :: Software Development :: Libraries :: Python Modules
Classifier: Typing :: Typed
Requires-Python: >=3.10
Requires-Dist: concurry>=0.13.0
Requires-Dist: litellm>=1.0.0
Requires-Dist: pydantic>=2.0.0
Provides-Extra: all
Requires-Dist: ag2>=0.8.0; extra == 'all'
Requires-Dist: crewai>=0.80.0; extra == 'all'
Requires-Dist: pytest-cov>=4.0; extra == 'all'
Requires-Dist: pytest-timeout>=2.0; extra == 'all'
Requires-Dist: pytest>=7.0; extra == 'all'
Requires-Dist: ray>=2.0.0; extra == 'all'
Requires-Dist: ruff>=0.4; extra == 'all'
Provides-Extra: autogen
Requires-Dist: ag2>=0.8.0; extra == 'autogen'
Provides-Extra: crewai
Requires-Dist: crewai>=0.80.0; extra == 'crewai'
Provides-Extra: dev
Requires-Dist: pytest-cov>=4.0; extra == 'dev'
Requires-Dist: pytest-timeout>=2.0; extra == 'dev'
Requires-Dist: pytest>=7.0; extra == 'dev'
Requires-Dist: ruff>=0.4; extra == 'dev'
Provides-Extra: ray
Requires-Dist: ray>=2.0.0; extra == 'ray'
Description-Content-Type: text/markdown

# SlowBurn

[![PyPI version](https://img.shields.io/pypi/v/slowburn.svg)](https://pypi.org/project/slowburn/)
[![Tests](https://github.com/adivekar-utexas/slowburn/actions/workflows/tests.yml/badge.svg)](https://github.com/adivekar-utexas/slowburn/actions/workflows/tests.yml)
[![Linting](https://github.com/adivekar-utexas/slowburn/actions/workflows/linting.yml/badge.svg)](https://github.com/adivekar-utexas/slowburn/actions/workflows/linting.yml)
[![Python 3.10+](https://img.shields.io/badge/python-3.10%2B-blue.svg)](https://www.python.org/downloads/)
[![License: MIT](https://img.shields.io/badge/License-MIT-yellow.svg)](https://opensource.org/licenses/MIT)

**SlowBurn: Cost-Sustainable Concurrent Execution for Long-Horizon LLM Agents**

SlowBurn is a Python library that lets LLM agent workflows run within a dollar budget by automatically slowing down — not crashing — when the budget is tight. It combines concurrent execution with dollar-denominated rate limiting and per-call cost tracking, so researchers can launch overnight batch experiments on a $5/day budget and wake up to completed results instead of a crashed script.

SlowBurn provides a native asyncio LLM worker for direct use, and drop-in integrations for [AutoGen (AG2)](https://github.com/ag2ai/ag2) and [CrewAI](https://github.com/crewAIInc/crewAI) that add budget control to existing multi-agent workflows without code changes.

## Installation

```bash
pip install slowburn
```

## Development

```bash
git clone https://github.com/adivekar-utexas/slowburn.git
cd slowburn
pip install -e ".[dev]"
pytest
```

## License

MIT
