gepa
Optimize prompts, code, and more with AI-powered Reflective Optimization
gepa-ai/gepa
View on GitHub ↗Optimize prompts, code, and more with AI-powered Reflective Optimization
gepa ranks 9th of 370 in Training Toolkits, actively maintained, last commit yesterday.
Star trajectory
14 days tracked- in 30d, below the Training Toolkits median of +0.3%.
Last commit yesterday, fresher than the median of 199.5d.
How it compares in Training Toolkits
Ranked 9th of 370 by stars.
Related repos
Ranked by shared tags, then keywords, then starsWhere gepa sits
Hover or focus a node for details. Click to open it.
- This repo
- Related repo
- Tag or category
Reproducing and studying RL algorithms for LLM agents, including GRPO, GSPO, DAPO, OPD, Search-R1, ReTool…
+1k (+205%) in 30d · Committed 2d ago · Python · Apache-2.0
Shares Reinforcement Learning / RLHF, Training Toolkits
[ICML 2026] Meta Context Engineering via Agentic Skill Evolution
+5 (+2.8%) in 30d · Committed 201d ago · Python · MIT
Shares Training Toolkits, Reinforcement Learning / RLHF
[ICML 2026] Let LLMs invent and evolve languages for efficient reasoning.
+48 (+45%) in 30d · Committed 19d ago · Python · MIT
Shares Reinforcement Learning / RLHF, Training Toolkits
- PRIME-RL/PRIME1.9k
Scalable RL solution for advanced reasoning of language models
-2 (-0.1%) in 30d · Committed 614d ago · Python · Apache-2.0
Shares Reinforcement Learning / RLHF, Training Toolkits
A unified framework for building, evaluating, and recursively improving embodied agents. 🚀 Code release…
+630 (+251%) in 30d · Committed yesterday · Python · Apache-2.0
Shares Reinforcement Learning / RLHF, Training Toolkits
Official repository for DR Tulu: Reinforcement Learning with Evolving Rubrics for Deep Research
+7 (+1.0%) in 30d · Committed 43d ago · Python · Apache-2.0
Shares Reinforcement Learning / RLHF, Training Toolkits
[ICML 2026] Let LLMs invent and evolve languages for efficient reasoning.
+27 (+6.4%) in 30d · Committed 4d ago · Python · MIT
Shares Training Toolkits, Reinforcement Learning / RLHF
AdaRubric: Adaptive Dynamic Rubric Evaluator for Agent Trajectories
+2 (+0.5%) in 30d · Committed 90d ago · Python · Apache-2.0
Shares Reinforcement Learning / RLHF, Training Toolkits
The purpose of this repository is to make prototypes as case study in the context of proof of concept(PoC) and…
+0 (+0.0%) in 30d · Committed 1,062d ago · Python · GPL-2.0
Shares Training Toolkits, Reinforcement Learning / RLHF
Compile real-world Claude Code and Codex trajectories into verified, tradable post-training assets.
+2 (+0.7%) in 30d · Committed 21d ago · Python · Apache-2.0
Shares Reinforcement Learning / RLHF, Training Toolkits
- Language
- Jupyter Notebook
- License
- MIT License
- Contributors
- 66
- Forks
- 631
- Watchers
- 25
- Open issues
- 79
- Releases
- 45
- Created
- 2025-08-05
- Stars this week
- +97
You've seen where gepa stands today.
Get the moves before everyone else: the 5 Training Toolkits repos climbing fastest, every Tuesday.
Free weekly digest. Double opt-in, unsubscribe anytime.