langfengQ/verl-agent

Agent Frameworks

verl-agent is an extension of veRL, designed for training LLM/VLM agents via RL. verl-agent is also the official code for paper "Group-in-Group Policy Optimization for LLM Agent Training"

GitHub →Website →

6.8

GitHub Metrics

Stars

1.8k

Forks

169

Open Issues

Watchers

Contributors

107

Weekly Commits

Language

Python

License

Apache-2.0

Last Commit

Feb 27, 2026

Created

Mar 23, 2025

Latest Release

v0.1.0

Release Date

Dec 11, 2025

Synced: Apr 16, 2026

Quality Scores

Documentation Qualityw: 20%

7.3

Has docs site (https://huggingface.co/papers/2505.10978). Description: 187 chars. Stars signal: 1,802. Contributors: 107. Score: 7.3/10

Community Healthw: 20%

5.9

Stars: 1,802. Contributors: 107. Watchers: 7. Forks: 169. Issue ratio: 3.3%. Score: 5.9/10

Maintenance Velocityw: 15%

6.4

Last commit: 48d ago. Weekly commits: 0. Latest release: v0.1.0. Maturity bonus: 1.1y old. Score: 6.4/10

API Design & DXw: 20%

7.3

Stars/issues ratio: 30. Dynamic language: Python. Has documentation site. Permissive license: Apache-2.0. Popularity signal: 1,802 stars. Score: 7.3/10

Production Readinessw: 15%

6.9

Battle-tested: 1,802 stars. Peer review: 107 contributors. Versioned: v0.1.0. Licensed: Apache-2.0. Age: 1.1 years. Maintenance: last commit 48d ago. Score: 6.9/10

Ecosystem Integrationw: 10%

7.3

Fork interest: 169. Major ecosystem: Python. Integration-friendly: Apache-2.0. Adoption: 1,802 stars. Has web presence. Score: 7.3/10