rllm-org/rllm

Democratizing Reinforcement Learning for LLMs

68
/ 100
Established

This tool helps AI engineers enhance their language model agents using reinforcement learning, making them more effective at tasks like complex problem-solving. You provide your existing agent code and a way to measure its success (a reward function), and it outputs a more capable, finely-tuned agent ready for deployment. This is for AI engineers and researchers working on building and optimizing sophisticated AI agents.

5,219 stars. Actively maintained with 64 commits in the last 30 days.

Use this if you are developing AI agents with existing frameworks (like LangGraph or OpenAI's SDK) and want to apply reinforcement learning to improve their performance with minimal code changes.

Not ideal if you are new to developing AI agents or do not have a clear way to define a reward signal for your agent's performance.

AI agent development reinforcement learning large language models agent optimization AI research
No Package No Dependents
Maintenance 22 / 25
Adoption 10 / 25
Maturity 16 / 25
Community 20 / 25

How are scores calculated?

Stars

5,219

Forks

515

Language

Python

License

Apache-2.0

Last pushed

Mar 13, 2026

Commits (30d)

64

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/rag/rllm-org/rllm"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.