Verl Agent
verl-agent is an extension of veRL, designed for training LLM/VLM agents via RL
Coding Agents
7.5 /10
Open Source Last Updated
2026-06-09
GitHub Stars
2,011
About Verl Agent
Features
Multi-Turn Agent-Environment Interaction
Fully Customizable Memory Module & Per-Step Input Structure
Scalable for Very Long-Horizon Optimization
Parallelized Gym-Style Environments and Group Environments
Support for Various Models
LoRA Fine-Tuning Support
Detailed Ratings
Ease of Use 7.2
Value for Money 7.7
Features 7.5
Support 6.9
Performance 7.6
Overall Rating
7.5 /10
Who Is It For?
#agent-framework#deepseek-r1#gigpo#grpo#large-language-models#news
Related Agents
CORAL
An organization for autonomous AI agents β spawn agents, run experiments, share knowledge, and loop forever
Open Source
7.0 /10
Aeon
Give it a direction β AEON leverages 197 skills to get it done
Open Source
7.0 /10
Agent Governance Toolkit
AI Agent Governance Toolkit β Policy enforcement, zero-trust identity, execution sandboxing, and reliability engineering
Open Source
8.0 /10
AgentGuide
https://adongwanai
Freemium
8.0 /10