RAGEN
Reinforcement learning framework for training reasoning LLM agents over multi-turn episodes with the StarPO algorithm.
Harness by mll-lab-nu
Get started
Setup steps are in the repository. Website · Repository
About
Use cases: model-inference
Reviews
Write a reviewNo reviews yet. Installed it? Reviews come from verified installers only. How reviews work
Fact sheet
- Languages
- Python
Facts extracted by Claude Haiku 5.5 from the linked sources on Oct 24, 2026. Wrong fact? Tell us.
Alternatives
Frameworks for the same language with a similar way of orchestrating agents.
- 0.853score
LlamaIndex
LlamaIndex
Open-source Python toolkit for RAG and agents over your own data, with event-driven workflows and 300+ integration packages.
HarnessAFreshness: A★ 52.6K↓ 1.4M/wk - 0.753score
LangChain
LangChain
Python framework of interoperable components and integrations for building agents and LLM apps, with LangGraph and Deep Agents layered above it.
HarnessAFreshness: A★ 148.4K↓ 37.3M/wk - 0.748score
LangGraph
LangChain
Low-level Python orchestration framework for long-running stateful agents, with durable execution, human review points and short- and long-term memory.
HarnessAFreshness: A★ 43.8K↓ 13.1M/wk - 0.732score
CrewAI
CrewAI
Open-source Python framework for multi-agent workflows, with role-based Crews and event-driven Flows.
HarnessAFreshness: A★ 60.1K↓ 644.6K/wk - 0.627score
AutoGen
Microsoft
Archived Microsoft Python framework for multi-agent apps; Microsoft directs new users to Microsoft Agent Framework.
HarnessAFreshness: A★ 61.5K↓ 89K/wk
Signals
- Stars
- 2,825
- Forks
- 229
- Open issues
- 28
- Last commit
- Aug 23, 2026 (2 months ago)
From GitHub (fetched Oct 24, 2026).
Details
- License
- MIT
- Repository
- github.com/mll-lab-nu/RAGEN
- Website
- ragen-ai.github.io/
- First seen
- Oct 24, 2026
- Last checked
- Oct 24, 2026
- Source
- READMEgithub-graphql
Cite this page
RAGEN. Agent Mart. https://agentmart.dev/harnesses/ragen (last updated 2026-10-24)