openevolve

openevolve is an agent framework - Open-source implementation of AlphaEvolve.

Overview

LLMs don't just optimize—they discover entirely new algorithms. No human guidance needed.

2-3x speedups on real hardware. State-of-the-art circle packing. Breakthrough optimizations.

Full reproducibility, extensive evaluation pipelines, and scientific rigor built-in.

Note: The example config uses Gemini by default, but you can use any OpenAI-compatible provider by modifying the 'config.yaml'. See the configs for full configuration options.

Prefer Docker? See the Installation & Setup section for Docker options.

Result: Matches published benchmarks for n=26 circle packing problem.

Performance Impact: 2.8x speedup on Apple M1 Pro, maintaining numerical accuracy.

• Python: 3.10+ - LLM Access: Any OpenAI-compatible API - Optional: Docker for containerized runs

Cost-saving tips: - Start with fewer iterations (100-200) - Use o3-mini, Gemini-2.5-Flash or local models for exploration - Use cascade evaluation to filter bad programs early - Configure smaller population sizes initially

Evolve prompts instead of code for better LLM performance. See the LLM Prompt Optimization example for a complete case study with HotpotQA achieving +23% accuracy improvement.

Important: Return raw values from evaluator, OpenEvolve handles binning automatically.

How it works: Place '{greeting}' or '{improvement_suggestion}' placeholders in your templates, and OpenEvolve will randomly choose from the variations for each generation, adding diversity to prompts.

openevolve is open-source, written primarily in Python, with 6,498 GitHub stars under the Apache 2.0 license. The latest release is v0.2.27 (2026-03-18).

Key capabilities

From the project's documentation:

• Quality-Diversity Evolution: Maintains diverse populations across feature dimensions
• Island-Based Architecture: Multiple populations prevent premature convergence
• LLM Ensemble: Multiple models with intelligent fallback strategies
• Artifact Side-Channel: Error feedback improves subsequent generations
• Comprehensive Seeding: Every component (LLM, database, evaluation) is seeded
• Default Seed=42: Immediate reproducible results out of the box

Install

A quick way to get started (always check the official docs for the latest):

pip install openevolve

How it fits a local-AI stack

openevolve runs on your own hardware, so pair it with a model and a GPU sized to your needs. Use the VRAM calculator to pick a model that fits your card, and see what you can run for hardware guidance. Related agent frameworks in the directory:

• Agno
• AutoGPT
• CrewAI
• Genkit

Sources

• Source code & docs: algorithmicsuperintelligence/openevolve

Stats from GitHub, 2026-06-08.