#2323rd of 41 in Training and fine-tuning
areal
Asynchronous reinforcement learning system for training reasoning and agentic LLMs
- Stars
- 5.9k
- License
- Apache-2.0
- Last commit
- Oct 2026
- Last release
- Aug 2026
- Language
- Python
4,914 on 3 Apr 20265,889 on 30 Oct 2026
From GitHub's daily star counts.
Checked on GitHub.
Overview
AReaL trains LLMs with reinforcement learning using a fully asynchronous rollout and training loop. It ships GRPO, PPO, DAPO, GSPO, DPO, SFT and related algorithms, with SGLang or vLLM for inference and Megatron or PyTorch FSDP for training. Agentic RL works with black-box agents by pointing them at an AReaL endpoint through base_url.
Who it is for: ML researchers and engineers running RL post-training of LLMs on GPU clusters
Strengths
- Asynchronous RL; setting max_head_offpolicyness=0 gives the synchronous variant
- Many algorithms with example configs: GRPO, GSPO, PPO, DAPO, RLOO, M2PO, DPO, SFT
- Agentic RL for existing agents by swapping base_url; examples for SWE, search and tau2
- Backends: SGLang or vLLM inference; Megatron, FSDP or Archon training; Ray and local schedulers
Weaknesses
- Needs CUDA GPUs; install requires a matching flash-attn wheel
- Model support varies by training backend; other Hugging Face LLMs only on FSDP
- 2.0 microservice refactor and v1/v2 options add configuration complexity
- Ascend NPU support lives on a separate branch
What it needs
- GPU required
- Docker
- Needs SGLang or vLLM, Megatron or PyTorch FSDP, flash-attn, Ray (optional)
- Models: Qwen2/3, Qwen3-MoE, Qwen3.5, Qwen2.5-VL, Qwen3-VL
Quick answers
Is areal open source?
Yes. Its code is on GitHub under the Apache-2.0 license.
Can you run areal with Docker?
Yes. Its repository has a Docker setup: a Dockerfile, a Compose file or a published image.
Does areal need a GPU?
Yes, it needs a GPU.
Also in Training and fine-tuning
See all 41| Rank | Project | Score |
|---|---|---|
| 1 | unslothDesktop and web app to run and fine-tune local models | 88 out of 100 |
| 2 | peftPython library for LoRA and other parameter-efficient fine-tuning of Transformers models | 86 out of 100 |
| 3 | deepspeedPyTorch library for distributed training of very large models with ZeRO | 85 out of 100 |
| #4 | verlReinforcement learning training library for LLM post-training with PPO and GRPO | 84 out of 100 |
| #5 | trlPost-training library with SFT, DPO, GRPO and KTO trainers | 83 out of 100 |