algorithmicsuperintelligence/openevolve

Health v2 · maintenance only

Adoption not part of the score

7518 stars · 1180 forks observed · 2026-10-11

What it is AI-extracted, prompt v1, taxonomy v1, 2026-08-29, confidence not recorded

OpenEvolve is an open-source Python implementation of DeepMind's AlphaEvolve, an evolutionary coding agent that uses LLM ensembles to autonomously discover and optimize algorithms. It evolves code through iterative refinement with parallel island-based evolution, multi-objective Pareto optimization, and evaluation pipelines.

Use cases

• automatically optimize slow Python functions for speed
• discover new algorithms for math problems like circle packing
• evolve GPU kernels and Metal shaders for better performance
• use LLMs to iteratively refine and improve existing code
• run evolutionary search over code with multiple objectives
• find state-of-the-art solutions to scientific computing problems

When to choose

• you want LLM-driven autonomous code optimization without human guidance
• you need reproducible evolutionary search over program code
• you want to reproduce or extend AlphaEvolve-style algorithm discovery
• you need multi-objective optimization of code with parallel evaluation

When to avoid

• you need simple deterministic code refactoring rather than evolutionary search
• your task lacks a programmable evaluation metric to score candidate programs
• you cannot afford the LLM API costs of large population-based search
• you need guaranteed correctness rather than best-effort discovered solutions

Facets

library · maturity active

llm-inference agent-framework machine-learning developer-tools artificial-intelligence large-language-models python cross-platform cli evolutionary-algorithms genetic-algorithms alphaevolve code-optimization llm-ensemble prompt-evolution map-elites ai-agents algorithms automation

Member repositories

For agents

markdown · JSON · MCP: product_card(name="algorithmicsuperintelligence/openevolve")