SkyRL: A Modular Full-stack RL Library for LLMs
☆2,138Aug 6, 2026Updated this week
Alternatives and similar repositories for SkyRL
Users that are interested in SkyRL are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- slime is an LLM post-training framework for RL Scaling.☆7,820Updated this week
- Miles is an enterprise-facing reinforcement learning framework for LLM and VLM post-training, forked from and co-evolving with slime.☆1,939Updated this week
- Democratizing Reinforcement Learning for LLMs☆5,772Updated this week
- verl/HybridFlow: A Flexible and Efficient RL Post-Training Framework☆22,877Updated this week
- Agentic RL Training at Scale☆1,867Updated this week
- Virtual machines for every use case on DigitalOcean • AdGet dependable uptime with 99.99% SLA, simple security tools, and predictable monthly pricing with DigitalOcean's virtual machines, called Droplets.
- Scalable toolkit for efficient model reinforcement☆1,891Updated this week
- A Gym for Agentic LLMs☆504Jan 21, 2026Updated 6 months ago
- RAGEN leverages reinforcement learning to train LLM reasoning agents in interactive, stochastic environments.☆2,765Jul 24, 2026Updated 2 weeks ago
- [COLM 2025] Official repository for R2E-Gym: Procedural Environment Generation and Hybrid Verifiers for Scaling Open-Weights SWE Agents☆316Jul 13, 2025Updated last year
- Our library for RL environments + evals☆4,479Updated this week
- The RL Bridge for LLM-based Agent Applications. Made Simple & Flexible.☆5,651Updated this week
- An Efficient and User-Friendly Scaling Library for Reinforcement Learning with Large Language Models☆3,356Updated this week
- A version of verl to support diverse tool use [TMLR 2026]☆1,029Jul 15, 2026Updated 3 weeks ago
- Code for Paper: Training Software Engineering Agents and Verifiers with SWE-Gym [ICML 2025]☆720Jul 29, 2025Updated last year
- GPUs on demand by Runpod - Special Offer Available • AdRun AI, ML, and HPC workloads on powerful cloud GPUs—without limits or wasted spend. Deploy GPUs in under a minute and pay by the second.
- An Easy-to-use, Scalable and High-performance Agentic RL Framework based on Ray (PPO & DAPO & REINFORCE++ & VLM & TIS & vLLM & Ray & Asy…☆9,898Jul 14, 2026Updated 3 weeks ago
- A scalable asynchronous reinforcement learning implementation with in-flight weight updates.☆432Updated this week
- Search-R1: An Efficient, Scalable RL Training Framework for Reasoning & Search Engine Calling interleaved LLM based on veRL☆5,278Nov 13, 2025Updated 8 months ago
- Framework for evaluating and improving agents☆4,037Updated this week
- Post-training with Tinker☆4,000Updated this week
- verl-agent is an extension of veRL, designed for training LLM/VLM agents via RL. verl-agent is also the official code for paper "Group-in…☆2,193Jun 9, 2026Updated 2 months ago
- PyTorch-native post-training at scale☆700Updated this week
- [NeurIPS 2025 D&B Spotlight] Scaling Data for SWE-agents☆732Updated this week
- OpenTinker is an RL-as-a-Service infrastructure for foundation models☆677Mar 21, 2026Updated 4 months ago
- GPUs on demand by Runpod - Special Offer Available • AdRun AI, ML, and HPC workloads on powerful cloud GPUs—without limits or wasted spend. Deploy GPUs in under a minute and pay by the second.
- [NeurIPS 2025 Spotlight] Reasoning Environments for Reinforcement Learning with Verifiable Rewards☆1,477Apr 17, 2026Updated 3 months ago
- [ICLR 2026] End-to-End Reinforcement Learning for Multi-Turn Tool-Integrated Reasoning☆403Mar 30, 2026Updated 4 months ago
- Checkpoint-engine is a simple middleware to update model weights in LLM inference engines☆993Updated this week
- My learning notes for ML SYS.☆6,842Updated this week
- Official Repo for Open-Reasoner-Zero☆2,098Jun 2, 2025Updated last year
- ☆1,174Jan 10, 2026Updated 7 months ago
- An LLM post-training framework with vLLM for RL Scaling☆407Updated this week
- 🌾 OAT: A research-friendly framework for LLM online alignment, including reinforcement learning, preference learning, etc.☆666Jan 29, 2026Updated 6 months ago
- [NeurIPS'25] Official codebase for "SWE-RL: Advancing LLM Reasoning via Reinforcement Learning on Open Software Evolution"☆715Mar 16, 2025Updated last year
- Virtual machines for every use case on DigitalOcean • AdGet dependable uptime with 99.99% SLA, simple security tools, and predictable monthly pricing with DigitalOcean's virtual machines, called Droplets.
- An interface library for RL post training with environments.☆2,489Updated this week
- SGLang is a high-performance serving framework for large language models and multimodal models.☆31,578Updated this week
- AllenAI's post-training codebase☆3,821Updated this week
- ☆1,302May 20, 2026Updated 2 months ago
- Agentic RL on Any Harness at Scale☆759Updated this week
- ☆353May 24, 2025Updated last year
- Simple RL training for reasoning☆3,872Dec 23, 2025Updated 7 months ago