OpenEvolve
Fewer than 5 people recommend it so far, so there's no written verdict. Here is what commenters said.
2recommend
1warn against
Dec 9, 2025first mention
Jun 9, 2026latest mention
Why people recommend it
“one can use OpenEvolve [0] which is not quite as good but should be a good start”
“https://github.com/algorithmicsuperintelligence/openevolve”
Caveats and dissent
“I found them difficult to customize for specific, multi-step research workflows”
Often compared with
Threads where it came up
- AlphaEvolve: Gemini-powered coding agent scaling impact across fields 2 mentions
- Can LLMs Beat Classical Hyperparameter Optimization Algorithms? 1 mention
- item 47937380 1 mention
- Levi: Outperforming GEPA/OpenEvolve/AlphaEvolve with 7x cost savings 1 mention
- Show HN: AgentCommander - workflow engine for evolutionary code optimization 1 mention
- Reflections on AI at the End of 2025 1 mention
Also written as openevolve. Quotes are verbatim; the verdict and theme labels are written by a model from these comments, and every clause links to its sources.
All comments 8
“I've tried to do "algorithmic discovery" with these systems, e.g. openevolve”
“OpenEvolve is an open source implementation of AlphaEvolve”
“one can use OpenEvolve [0] which is not quite as good but should be a good start”
“Open source implementation of the algorithm”
“Most open-source AlphaEvolve alternatives (OpenEvolve, ShinkaEvolve, GEPA) assume you'll throw a frontier model at every mutation.”
“I found them difficult to customize for specific, multi-step research workflows”
“https://github.com/algorithmicsuperintelligence/openevolve”
“Open-source implementation of AlphaEvolve”