{"data":{"node":{"slug":"verl-project-verl","name":"verl","tagline":"A Flexible and Efficient RL Post-Training Framework","github_url":"https://github.com/verl-project/verl","owner":"verl-project","repo":"verl","owner_avatar_url":"https://avatars.githubusercontent.com/u/212961691?v=4","primary_language":"Python","stars":23318,"forks":4500,"topics":[],"archived":false,"github_pushed_at":"2026-09-04T22:00:53+00:00","maintenance_label":"Very active","stars_delta_30d":464,"url":"https://www.graphcanon.com/tools/verl-project-verl","markdown_url":"https://www.graphcanon.com/tools/verl-project-verl.md","api_url":"https://www.graphcanon.com/api/graphcanon/tools/verl-project-verl","graph_url":"https://www.graphcanon.com/api/graphcanon/graph?tool=verl-project-verl"},"categories":[{"slug":"model-training","name":"Model Training","url":"https://www.graphcanon.com/categories/model-training","markdown_url":"https://www.graphcanon.com/categories/model-training.md","api_url":"https://www.graphcanon.com/api/graphcanon/categories/model-training"}],"tags":[{"slug":"grpo","name":"grpo"},{"slug":"post-training","name":"post-training"},{"slug":"ppo","name":"ppo"},{"slug":"python","name":"python"},{"slug":"reinforcement-learning","name":"reinforcement learning"},{"slug":"rl","name":"rl"}],"edges":[],"neighbours":[{"slug":"openrlhf-openrlhf","name":"OpenRLHF","tagline":"Scalable and High-performance Agentic RL Framework based on Ray","github_url":"https://github.com/OpenRLHF/OpenRLHF","owner":"OpenRLHF","repo":"OpenRLHF","owner_avatar_url":"https://avatars.githubusercontent.com/u/175771028?v=4","primary_language":"Python","stars":10014,"forks":1019,"topics":["large-language-models","proximal-policy-optimization","raylib","reinforcement-learning","reinforcement-learning-from-human-feedback","transformers","visual-language-models","vllm"],"archived":false,"github_pushed_at":"2026-09-17T05:49:37+00:00","maintenance_label":"Active","url":"https://www.graphcanon.com/tools/openrlhf-openrlhf","markdown_url":"https://www.graphcanon.com/tools/openrlhf-openrlhf.md","api_url":"https://www.graphcanon.com/api/graphcanon/tools/openrlhf-openrlhf","graph_url":"https://www.graphcanon.com/api/graphcanon/graph?tool=openrlhf-openrlhf","shared_categories":["model-training"]},{"slug":"reinflow-reinflow","name":"ReinFlow","tagline":"ReinFlow combines Flow Policy with online reinforcement learning for fine-tuning across various robotic tasks.","github_url":"https://github.com/ReinFlow/ReinFlow","owner":"ReinFlow","repo":"ReinFlow","owner_avatar_url":"https://avatars.githubusercontent.com/u/212894921?v=4","primary_language":"Python","stars":364,"forks":35,"topics":["actorcritic","fine-tuning","finetuning-rl","finetuning-vision-models","flow","flowmatching","locomotion","manipulation","onlinerl","pi0","policygradient","post-training","rl","robot-learning","robotics","visuomotor","vla"],"archived":false,"github_pushed_at":"2026-04-24T22:34:21+00:00","maintenance_label":"Slowing","url":"https://www.graphcanon.com/tools/reinflow-reinflow","markdown_url":"https://www.graphcanon.com/tools/reinflow-reinflow.md","api_url":"https://www.graphcanon.com/api/graphcanon/tools/reinflow-reinflow","graph_url":"https://www.graphcanon.com/api/graphcanon/graph?tool=reinflow-reinflow","shared_categories":["model-training"]}]}}