TheHandsomeDev/evolveRL

Empower Truly Autonomous AI Agents through our Experimental Adversarial and Evolutionary Reinforcement Learning Framework. Join our Community: https://t.me/evolveRL_portal

42
/ 100
Emerging

Implements genetic algorithms to autonomously evolve LLM system prompts and agent configurations across generations, using adversarial scenario generation for robustness validation. Supports OpenAI's GPT and Anthropic's Claude backends with multi-agent population-based selection, persisting evolved agent states as JSON configs for reproducibility. The framework enables continuous self-improvement loops without manual prompt engineering through tournament selection and mutation-based exploration.

No commits in the last 6 months. Available on PyPI.

Stale 6m
Maintenance 0 / 25
Adoption 9 / 25
Maturity 18 / 25
Community 15 / 25

How are scores calculated?

Stars

16

Forks

5

Language

Python

License

MIT

Last pushed

Jan 19, 2025

Monthly downloads

17

Commits (30d)

0

Dependencies

3

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/prompt-engineering/TheHandsomeDev/evolveRL"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.