MrTsepa/autoevolve

AI agent evolving strategies through automated self-play overnight. Generic framework with GEPA-inspired feedback loop and Elo tracking.

25
/ 100
Experimental

Separates mutation (LLM-driven code iteration), evaluation (head-to-head benchmarking), and rating (Bradley-Terry model for order-independent skill estimation) into pluggable components, enabling domain-specific arenas from game bots to prompt optimization. Integrates with Claude Code as a skill for autonomous overnight experiments, or runs standalone via Python CLI with `matches.json` persistence and Pareto front selection for choosing high-potential parent candidates.

No Package No Dependents
Maintenance 13 / 25
Adoption 3 / 25
Maturity 9 / 25
Community 0 / 25

How are scores calculated?

Stars

3

Forks

Language

Python

License

MIT

Last pushed

Mar 16, 2026

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/agents/MrTsepa/autoevolve"

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