# algorithmicsuperintelligence/openevolve

Open-source implementation of AlphaEvolve

Repository: https://github.com/algorithmicsuperintelligence/openevolve
Canonical: https://ross.abutalabs.com/products/openevolve
Language: Python
License: Apache-2.0
License Family: permissive
Topics: alphacode, coding-agent, deepmind, deepmind-lab, discovery, distributed-evolutionary-algorithms, evolutionary-algorithms, evolutionary-computation, genetic-algorithm, genetic-algorithms, iterative-methods, iterative-refinement, llm-engineering, llm-ensemble, llm-inference, optimize, alpha-evolve, alphaevolve, openevolve
Last push: 2026-07-18T13:16:12+00:00

## Health v2 (maintenance only)
Score: 81/100 (v2, computed 2026-09-02T17:46:02.011165+00:00)
- activity 93, release rhythm 93, longevity 33
- inputs: {"age_days": 475, "days_push": 46, "days_rel": 46, "gap_med": 1.5, "n_releases_24m": 55}
- flags: none
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 7271, forks 1142 (observed 2026-08-28T04:09:57.953412+00:00)

## What it is
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
- artifact type: library
- maturity: active
- function: llm-inference, agent-framework, machine-learning, developer-tools
- domain: artificial-intelligence, large-language-models
- platform: python, cross-platform, cli
- tags: evolutionary-algorithms, genetic-algorithms, alphaevolve, code-optimization, llm-ensemble, prompt-evolution, map-elites, ai-agents, algorithms, automation

## Member repositories
- algorithmicsuperintelligence/openevolve (main) score 81

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:09:57.953412+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-29T17:38:55.104604+00:00, confidence not recorded.
  - readme: https://github.com/algorithmicsuperintelligence/openevolve (fetched 2026-08-28T04:09:57.953412+00:00, sha 649bf007b865)
- Data as of 2026-08-30T08:39:29.467469+00:00.