Alternatives and similar repositories for MLGym

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

• SWE-Gym / SWE-Gym
  Code for Paper: Training Software Engineering Agents and Verifiers with SWE-Gym [ICML 2025]
  ☆553Updated 2 months ago
• facebookresearch / swe-rl
  [NeurIPS'25] Official codebase for "SWE-RL: Advancing LLM Reasoning via Reinforcement Learning on Open Software Evolution"
  ☆607Updated 7 months ago
• openai / mle-bench
  MLE-bench is a benchmark for measuring how well AI agents perform at machine learning engineering
  ☆1,042Updated last week
• open-thought / reasoning-gym
  [NeurIPS 2025 Spotlight] Reasoning Environments for Reinforcement Learning with Verifiable Rewards
  ☆1,194Updated 3 weeks ago
• LeonGuertler / TextArena
  A Collection of Competitive Text-Based Games for Language Model Evaluation and Reinforcement Learning
  ☆291Updated 3 weeks ago
• sail-sg / oat
  🌾 OAT: A research-friendly framework for LLM online alignment, including reinforcement learning, preference learning, etc.
  ☆539Updated this week
• thinking-machines-lab / tinker-cookbook
  Post-training with Tinker
  ☆1,096Updated this week
• ekinakyurek / marc
  Public repository for "The Surprising Effectiveness of Test-Time Training for Abstract Reasoning"
  ☆330Updated 11 months ago
• NovaSky-AI / SkyRL
  SkyRL: A Modular Full-stack RL Library for LLMs
  ☆1,101Updated this week
• facebookresearch / memory
  Memory layers use a trainable key-value lookup mechanism to add extra parameters to a model without increasing FLOPs. Conceptually, spars…
  ☆342Updated 10 months 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…
  ☆321Updated 2 weeks ago
• ServiceNow / AgentLab
  AgentLab: An open-source framework for developing, testing, and benchmarking web agents on diverse tasks, designed for scalability and re…
  ☆434Updated this week
• PrimeIntellect-ai / prime-rl
  Async RL Training at Scale
  ☆722Updated this week
• SakanaAI / RLT
  Training teachers with reinforcement learning able to make LLMs learn how to reason for test time scaling.
  ☆346Updated 4 months ago
• WooooDyy / AgentGym-RL
  Code and implementations for the paper "AgentGym-RL: Training LLM Agents for Long-Horizon Decision Making through Multi-Turn Reinforcemen…
  ☆453Updated last month
• open-thought / system-2-research
  System 2 Reasoning Link Collection
  ☆857Updated 7 months ago
• huggingface / search-and-learn
  Recipes to scale inference-time compute of open models
  ☆1,111Updated 5 months ago
• groundlight / r1_vlm
  Build your own visual reasoning model
  ☆413Updated 2 weeks ago
• meta-pytorch / OpenEnv
  An interface library for RL post training with environments.
  ☆66Updated this week
• seal-rg / recurrent-pretraining
  Pretraining and inference code for a large-scale depth-recurrent language model
  ☆836Updated last week
• McGill-NLP / nano-aha-moment
  Single File, Single GPU, From Scratch, Efficient, Full Parameter Tuning library for "RL for LLMs"
  ☆538Updated 2 weeks ago
• trotsky1997 / MathBlackBox
  ☆1,035Updated 10 months ago
• mlfoundations / evalchemy
  Automatic evals for LLMs
  ☆550Updated 4 months ago
• NVIDIA-NeMo / Skills
  A project to improve skills of large language models
  ☆587Updated last week
• zorazrw / agent-workflow-memory
  AWM: Agent Workflow Memory
  ☆335Updated 8 months ago
• microsoft / rStar
  ☆1,309Updated last month
• TheAgentCompany / TheAgentCompany
  An agent benchmark with tasks in a simulated software company.
  ☆570Updated 2 weeks ago
• axon-rl / gem
  A Gym for Agentic LLMs
  ☆323Updated 2 weeks ago
• sunblaze-ucb / Intuitor
  Code for the paper: "Learning to Reason without External Rewards"
  ☆366Updated 3 months ago
• SalesforceAIResearch / xLAM
  xLAM: A Family of Large Action Models to Empower AI Agent Systems
  ☆564Updated 2 months ago