rllm

About this project

Agentic RL on any harness, with any backend, on any benchmark. rLLM is an open-source framework for training language agents with reinforcement learning. Bring any harness, run it in any sandbox, and switch training backends with one flag — the same agent code drives both eval and training. Core features — Any harness. 10+ CLI harnesses (Claude Code, Codex, Terminus-2, mini-swe-agent, opencode, ...) plus Harbor-compatible task dirs. Or wrap your own agent — LangGraph, OpenAI Agents SDK, openai.OpenAI — with @rllm.rollout. — Any sandbox. Docker, Daytona, Modal, or local — with snapshot + warm-pool acceleration to keep rollouts cheap at training-scale. — Multiple training…

GitHub

Reviews

Built by

rllm-org

Imported from GitHub · not yet claimed on GitPalace

View developer pageSign in with GitHub to claim

Maintain rllm-org/rllm? Claiming verifies admin access through your GitHub account and gives you control of this listing.

You might also like

tensorflow

Machine Learning

An Open Source Machine Learning Framework for Everyone

★ New198.9K stars

by tensorflow

prompts.chat

Machine Learning

f.k.a. Awesome ChatGPT Prompts. Share, discover, and collect prompts from the community. Free and open source — self-hos

★ New169.5K stars

by f

transformers

Machine Learning

🤗 Transformers: the model-definition framework for state-of-the-art machine learning models in text, vision, audio, and

★ New164.9K stars

by huggingface

ComfyUI

Machine Learning

The most powerful and modular diffusion model GUI, api and backend with a graph/nodes interface.

★ New131.8K stars

by Comfy-Org