A comprehensive toolkit for evolving and tracking AI agents
Project description
Agent Evolve
A comprehensive toolkit for evolving and tracking AI agents through evolutionary programming and automated optimization.
Features
- 🧬 Evolutionary Optimization: Automatically improve your AI agents using OpenEvolve
- 📊 Interactive Dashboard: Real-time tracking and visualization of evolution progress
- 🎯 Smart Extraction: Automatically find and extract functions marked for evolution
- 🔧 Auto-Generation: Generate evaluators, training data, and configurations automatically
- 📈 Metrics Tracking: Comprehensive metrics collection and analysis
- 🚀 CLI Interface: Easy-to-use command-line tools for all operations
Quick Start
Installation
pip install agent-evolve
Basic Usage
- Mark functions for evolution by adding the
@evolvedecorator:
from agent_evolve import evolve
@evolve()
def my_function(x: int) -> str:
return f"Hello {x}"
- Extract evolution targets:
agent-evolve extract /path/to/your/code
- Run the evolution pipeline:
agent-evolve pipeline my_function
- View results in the dashboard:
agent-evolve dashboard
CLI Commands
extract- Extract functions marked with @evolve decoratorgenerate-training-data- Generate training data for extracted functionsgenerate-evaluators- Generate evaluation functionsgenerate-configs- Generate OpenEvolve configuration filesevolve- Run evolution optimization on a specific toolpipeline- Run the complete pipeline (training data → evaluator → config → evolution)dashboard- Launch the interactive Streamlit dashboardanalyze- Analyze tracking data
Dashboard Features
- Evolution Pipeline: Step-by-step progress tracking
- Code Comparison: Side-by-side diffs of original vs evolved code
- Metrics & Timeline: Performance improvements over time
- Interactive Tools: Generate evaluators, run evolution, and more
Requirements
- Python 3.8+
- OpenAI API key (for evaluator generation)
- OpenEvolve package
License
MIT License - see LICENSE file for details.
Contributing
Contributions welcome! Please read our contributing guidelines and submit pull requests.
Project details
Release history Release notifications | RSS feed
Download files
Download the file for your platform. If you're not sure which to choose, learn more about installing packages.
Source Distribution
Built Distribution
Filter files by name, interpreter, ABI, and platform.
If you're not sure about the file name format, learn more about wheel file names.
Copy a direct link to the current filters
File details
Details for the file agent_evolve-1.0.0.tar.gz.
File metadata
- Download URL: agent_evolve-1.0.0.tar.gz
- Upload date:
- Size: 92.1 kB
- Tags: Source
- Uploaded using Trusted Publishing? No
- Uploaded via: twine/6.1.0 CPython/3.13.4
File hashes
| Algorithm | Hash digest | |
|---|---|---|
| SHA256 |
079744561e9c3fe2afea9fcf1385771c056dddbcbb4a27422a95118fd27888b8
|
|
| MD5 |
7979b5da0ee836d00b22f0fd596709bc
|
|
| BLAKE2b-256 |
a8fbdb35ebcfc8ac136d6ed73bba732f6355f3e104a94193c62d84b3f63459e5
|
File details
Details for the file agent_evolve-1.0.0-py3-none-any.whl.
File metadata
- Download URL: agent_evolve-1.0.0-py3-none-any.whl
- Upload date:
- Size: 103.0 kB
- Tags: Python 3
- Uploaded using Trusted Publishing? No
- Uploaded via: twine/6.1.0 CPython/3.13.4
File hashes
| Algorithm | Hash digest | |
|---|---|---|
| SHA256 |
84f2981f5f248fdd8504145d116973bba573b2eee663f3d46f119a7ec520b998
|
|
| MD5 |
3b097f1de7be8dd13a92223dfd224b38
|
|
| BLAKE2b-256 |
4a74d05bed1aa3f41f806c5c229d6de85038ba900b094dff0483b292458e5e72
|