Alternatives and similar repositories for SkyRL

Users that are interested in SkyRL are comparing it to the libraries listed below

• sail-sg / oat
  🌾 OAT: A research-friendly framework for LLM online alignment, including reinforcement learning, preference learning, etc.
  ☆623Updated last week
• NVIDIA-NeMo / RL
  Scalable toolkit for efficient model reinforcement
  ☆1,293Updated this week
• facebookresearch / swe-rl
  [NeurIPS'25] Official codebase for "SWE-RL: Advancing LLM Reasoning via Reinforcement Learning on Open Software Evolution"
  ☆673Updated 10 months ago
• huggingface / Math-Verify
  ☆1,084Updated 3 weeks ago
• sail-sg / understand-r1-zero
  Understanding R1-Zero-Like Training: A Critical Perspective
  ☆1,203Updated 5 months ago
• open-thought / reasoning-gym
  [NeurIPS 2025 Spotlight] Reasoning Environments for Reinforcement Learning with Verifiable Rewards
  ☆1,326Updated 2 weeks ago
• microsoft / rStar
  ☆1,385Updated 4 months ago
• PrimeIntellect-ai / prime-rl
  Async RL Training at Scale
  ☆1,034Updated this week
• NVIDIA-NeMo / Skills
  A project to improve skills of large language models
  ☆804Updated this week
• srush / awesome-o1
  A bibliography and survey of the papers surrounding o1
  ☆1,213Updated last year
• BytedTsinghua-SIA / DAPO
  An Open-source RL System from ByteDance Seed and Tsinghua AIR
  ☆1,715Updated 8 months ago
• THUDM / slime
  slime is an LLM post-training framework for RL Scaling.
  ☆3,571Updated last week
• TIGER-AI-Lab / verl-tool
  A version of verl to support diverse tool use
  ☆852Updated 3 weeks ago
• SWE-Gym / SWE-Gym
  Code for Paper: Training Software Engineering Agents and Verifiers with SWE-Gym [ICML 2025]
  ☆625Updated 6 months ago
• huggingface / search-and-learn
  Recipes to scale inference-time compute of open models
  ☆1,124Updated 8 months ago
• thinking-machines-lab / batch_invariant_ops
  ☆957Updated 3 months ago
• radixark / miles
  Miles is an enterprise-facing reinforcement learning framework for LLM and VLM post-training, forked from and co-evolving with slime.
  ☆830Updated this week
• mlfoundations / evalchemy
  Automatic evals for LLMs
  ☆578Updated last month
• GAIR-NLP / LIMO
  [COLM 2025] LIMO: Less is More for Reasoning
  ☆1,061Updated 6 months ago
• mll-lab-nu / RAGEN
  RAGEN leverages reinforcement learning to train LLM reasoning agents in interactive, stochastic environments.
  ☆2,503Updated last week
• axon-rl / gem
  A Gym for Agentic LLMs
  ☆439Updated 2 weeks ago
• facebookresearch / meta-agents-research-environments
  Meta Agents Research Environments is a comprehensive platform designed to evaluate AI agents in dynamic, realistic scenarios. Unlike stat…
  ☆418Updated last week
• PRIME-RL / TTRL
  [NeurIPS 2025] TTRL: Test-Time Reinforcement Learning
  ☆972Updated 4 months ago
• SimpleBerry / LLaMA-O1
  Large Reasoning Models
  ☆807Updated last year
• MoonshotAI / checkpoint-engine
  Checkpoint-engine is a simple middleware to update model weights in LLM inference engines
  ☆902Updated this week
• allenai / OLMo-core
  PyTorch building blocks for the OLMo ecosystem
  ☆763Updated this week
• zhentingqi / rStar
  ☆971Updated last year
• facebookresearch / coconut
  Training Large Language Model to Reason in a Continuous Latent Space
  ☆1,491Updated 5 months ago
• NVIDIA / NeMo-Aligner
  Scalable toolkit for efficient model alignment
  ☆848Updated 3 months ago
• sierra-research / tau2-bench
  τ²-Bench: Evaluating Conversational Agents in a Dual-Control Environment
  ☆690Updated last week