TIGER-AI-Lab/verl-tool
A version of verl to support diverse tool use
This project helps AI developers build, train, and evaluate intelligent agents that can effectively use external tools to complete tasks. It takes your agent's code and definitions of available tools, then provides a robust framework to train the agent to select and interact with these tools. The output is a well-trained agent capable of complex, multi-step problem-solving using its integrated tools. This is for AI researchers and engineers developing sophisticated tool-using AI models.
904 stars.
Use this if you are developing AI agents that need to interact with various external tools to solve problems and require a dedicated framework for training and evaluation.
Not ideal if you are looking for an off-the-shelf AI agent for end-user tasks, rather than a development framework for building agents.
Stars
904
Forks
75
Language
Python
License
MIT
Category
Last pushed
Mar 02, 2026
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/llm-tools/TIGER-AI-Lab/verl-tool"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Compare
Related tools
langfengQ/verl-agent
verl-agent is an extension of veRL, designed for training LLM/VLM agents via RL. verl-agent is...
sotopia-lab/sotopia
Sotopia: an Open-ended Social Learning Environment (ICLR 2024 spotlight)
zhudotexe/redel
ReDel is a toolkit for researchers and developers to build, iterate on, and analyze recursive...
AMAP-ML/Tree-GRPO
[ICLR 2026] Tree Search for LLM Agent Reinforcement Learning
Auromix/ROS-LLM
ROS-LLM is a framework designed for embodied intelligence applications in ROS. It allows natural...