GEPA
Fewer than 5 people recommend it so far, so there's no written verdict. Here is what commenters said.
Why people recommend it
“I use GEPA to optimize the prompt for each model/tool/harness combination I’m evaluating.”
Show 2 more
“using GEPA where you optimize the skill content instead of the prompt works really well”
“GEPA prompts help, if you have good evals.”
Caveats and dissent
No one in these comments warned against it.
Often compared with
Who recommends it in their own words
From the makers not counted in the ranking
Thank you so much for the kind words! Didn't realize it got truncated: https://gepa-ai.github.io/gepa/blog/2026/02/18/introducing-optimize-anything/
“It extends GEPA (our prompt optimizer, discussed here previously: https://arxiv.org/abs/2507.19457)”
Threads where it came up
- Optimize_anything: A Universal API for Optimizing Any Text Parameter 2 mentions
- Levi: Outperforming GEPA/OpenEvolve/AlphaEvolve with 7x cost savings 1 mention
- If Dspy is so great, why isn't anyone using it? 1 mention
- How are people do AI evals these days? 1 mention
- Agent Skills 1 mention
- Training a trillion parameter model to be funny 1 mention
Data: gepa.json. 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 6
“Most open-source AlphaEvolve alternatives (OpenEvolve, ShinkaEvolve, GEPA) assume you'll throw a frontier model at every mutation.”
“Til about GEPA”
“I use GEPA to optimize the prompt for each model/tool/harness combination I’m evaluating.”
“using GEPA where you optimize the skill content instead of the prompt works really well”
“GEPA prompts help, if you have good evals.”
“an optimization algo GEPA”