verl-project
verl-project Joined May 2025 View on GitHub
- Stars
- 27,280
- across 14 public repos
- Rank
- #1,327
- of 94,827 organizations, top 2%
Repositories with 50+ stars
| Rank | Repository | Language | Stars |
|---|---|---|---|
| 1,808 | verl/HybridFlow: A Flexible and Efficient RL Post-Training Framework | Python | 24,187 |
| 46,044 | Multimodal RL training framework for diffusion & omni models | Python | 1,487 |
| 90,131 | Uni-Agent is a framework for training long-horizon agents. | Python | 719 |
| 173,546 | A set of examples based on verl for end-to-end RL training recipes. | Python | 346 |
| 344,664 | A unified VLA post-training framework for human-in-the-loop data collection, fine-tuning, and reinforcement learning. | Python | 153 |
| 480,756 | Provide performance insight capabilities for RL frameworks. | Python | 101 |
| 540,157 | Python | 87 | |
| 594,799 | verl Zero-Mismatch Dense/MoE HuggingFace Rollout | Python | 77 |
| 648,236 | Open MinT training runtime on veRL | Python | 69 |
Among 94,827 organizations
25k–40k stars: 673 organizations, including verl-project
top 50%top 10%top 1%top 0.1% 
Stars along the bottom, and organizations in each band on a log scale
Where the stars are
verl 24.2k, 89%verl-omni 1.5k, 5%uni-agent 719, 3%verl-recipe 346, 1%
4 more repos 334, 1%
verl-vla 153, 1%Smaller repos 54, <1%
Languages
- Python 27.2k stars, 100% · 9 repos
When they were made
9 repos with 50+ stars, made between 2024 and 2026
101001k10k100k uni-agentverl-omniverl
Quick stats
- Next rank
- +6 stars to reach #1,326
- Next milestone
- +7,714 stars to reach the top 1%
- Public repos
- 14, 9 with 50+ stars
- Popular repos
- 2 over 1k stars, 1 over 10k stars
- Top repo
- verl, #1,808 of all repos, 89% of stars
- Smaller repos
- 54 stars from repos under 50