Agent-One-Lab/AgentFly

Scalable and extensible reinforcement learning for LM agents.

122Stars on the repository
4Mods indexed here, across every type
6d agoLast push, which is what freshness is scored on
Apache-2.0Licence, which decides whether bodies are shown

agent

01

Agent-One-Lab/AgentFly

Agent

The foundation class for all agents in AgentFly.

122 6d ago A 0 tokens original Apache-2.0

index

02

Agent-One-Lab/AgentFly

Agent

AgentFly provides a comprehensive agent system with a base class and specialized implementations for different use cases. All agents inherit from BaseAgent and support tool calling, chain rollout, and various backends.

122 6d ago A 0 tokens original Apache-2.0

llm_backends

03

Agent-One-Lab/AgentFly

Agent

AgentFly supports multiple LLM backends for text generation, each with their own configuration options. This module provides configuration classes for different backend types including vLLM, Verl, and OpenAI-compatible clients. Among them, Verl backend is designed for internal training usage. The Verl backend is the…

122 6d ago A 0 tokens original Apache-2.0

rollout

04

Agent-One-Lab/AgentFly

Agent

Agent "rollout" from Agent-One-Lab/AgentFly, covering rollout and chain generation.

122 6d ago A 0 tokens original Apache-2.0