# AReno

> AReno is an open-source, self-hosted toolkit for RL post-training of LLMs on a single node with GSPO, GRPO, SFT, DPO, agentic RL, LoRA/QLoRA, and OpenAI serving.

- **Category:** AI
- **Licence:** Apache-2.0
- **Latest version:** v0.10.0
- **Open source:** oss
- **Languages:** Python
- **Platforms:** Docker, Build from Source
- **Tags:** Machine Learning, Agentic Ai, Local Ai, LLM, Cuda, Self Hosted, Agent, Agentic, Lora, Local llm, Npu, Openai compatible, Mlx, Reinforcement Learning, Sft, Grpo, Post Training, Rl, Gsppo, Dpo, Qlora

## Description

AReno is a compact toolkit for training and serving large language models using reinforcement learning on a single machine. Created by engineers at Ant Group's inclusionAI team, it bundles everything needed for post-training — multiple RL algorithms, an agent loop, efficient adapter methods, and a model server — into one package that runs on NVIDIA GPUs, Huawei NPUs, or Apple Silicon. You install it via a script, Docker, or pip, then use a command-line interface or Python SDK to run training jobs. A web dashboard can track experiments locally or on Modal's cloud platform. The code is Apache-2.0 licensed and under active development.

## Links

- [Homepage](https://github.com/inclusionai/areno)
- [Website](https://asystem-ai.io/docs/areno/)
- [Docker](ghcr.io/inclusionai/areno)
- [GitHub Repository](https://github.com/inclusionAI/AReno)
- [FAQ](https://asystem-ai.io/docs/areno/troubleshooting/faq.html)
- [Installation Guide](https://asystem-ai.io/docs/areno/getting-started/installation.html)
- [CLI Reference](https://asystem-ai.io/docs/areno/reference/cli.html)
- [Harbor Integration](https://asystem-ai.io/docs/areno/integrations/harbor.html)

---
Source: https://selfhost.directory/project/areno