Open-source implementation of AlphaEvolve

DeepEvolve is a research and coding agent for new algorithm discovery in different science domains with Deep Research and AlphaEvolve.

Official implementation of Controlled Self-Evolution for Algorithmic Code Optimization

CodeEvolve is an open-source evolutionary coding agent for algorithm discovery and optimization.

[ICLR26] AI-based scaling law discovery

A Python library for evolving code and algorithms using Large Language Models (LLMs)

Evolutionary agent for large codebases, built on top of git

Executable benchmark for AI-driven potential discovery for the k-server conjecture, with evaluators, metric instances, and released experiment workflows.

An open-source AlphaEvolve-style evolutionary algorithm discovery engine. LLM-driven mutation operator inside an island-model evolutionary loop.

Evaluator-governed optimization sandbox inspired by AlphaEvolve, demonstrating mission-style algorithm tuning with latency budgets, governance gates, and auditable run summaries.

Interactive Evolutionary Algorithm Discovery Laboratory — 6 modules: GP Evolver, NK Landscapes, AlphaEvolve Sim, MAP-Elites QD, Co-Evolution Arena, Evolved Gallery. Zero deps, single HTML file.

Evolve algorithms with LLMs. Open-source AlphaEvolve alternative. Uses evolutionary strategies + AI to discover novel solutions.

An evolutionary problem-solving skill. It lets AI agents cooperate over a shared GitHub search graph to iteratively explore and evolve solutions via Pull Requests.

Small and easy-to-extend evolutionary agent similar to AlphaEvolve

Companion page for "Artificial Intelligence for Mathematical Reasoning: An Integrated Survey of Language Models, Neuro-symbolic Systems, and Verified Discovery." A curated four-axis index covering MWPs, LLMs and reasoning models, multimodal geometry, Lean theorem proving, and verified discovery (FunSearch, AlphaEvolve, Erdős problems).

A evolution based discovery model inspired by Alphaevolve

Using LLMs(not RL) to find new solutions for problems that are hard. Batteries included.

Reproducing AlphaEvolve's SOTA bound on the Erdős minimum-overlap problem with an evolutionary LLM pipeline (OpenEvolve) — converges in ~10 iterations, two independent backends, one-command verifier

A laptop-scale reproduction of DeepMind's AlphaEvolve (2025): an LLM mutates programs, a sandboxed evaluator scores them, evolutionary selection produces better algorithms — no training, no gradients. Runs free on local Ollama.