Alternatives and similar repositories for Gym

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

• meta-pytorch / torchforge
  PyTorch-native post-training at scale
  ☆600Updated last week
• safety-research / bloom
  bloom - evaluate any behavior immediately  🌸🌱
  ☆1,136Updated last week
• facebookresearch / cwm
  Research code artifacts for Code World Model (CWM) including inference tools, reproducibility, and documentation.
  ☆806Updated last month
• NVIDIA-NeMo / Nemotron
  Developer Asset Hub for NVIDIA Nemotron — A one-stop resource for training recipes, usage cookbooks, datasets, and full end-to-end refere…
  ☆374Updated this week
• open-tinker / OpenTinker
  OpenTinker is an RL-as-a-Service infrastructure for foundation models
  ☆599Updated last week
• MoonshotAI / checkpoint-engine
  Checkpoint-engine is a simple middleware to update model weights in LLM inference engines
  ☆891Updated last week
• thinking-machines-lab / tinker-cookbook
  Post-training with Tinker
  ☆2,770Updated this week
• ByteDance-Seed / seed-oss
  ☆862Updated 4 months ago
• Tencent / WeDLM
  WeDLM: The fastest diffusion language model with standard causal attention and native KV cache compatibility, delivering real speedups ov…
  ☆588Updated 2 weeks ago
• laude-institute / terminal-bench
  A benchmark for LLMs on complicated tasks in the terminal
  ☆1,442Updated last week
• google / tunix
  A Lightweight LLM Post-Training Library
  ☆2,128Updated this week
• WeiboAI / VibeThinker
  Tiny Model, Big Logic: Diversity-Driven Optimization Elicits Large-Model Reasoning Ability in VibeThinker-1.5B
  ☆565Updated 2 months ago
• NVIDIA-NeMo / RL
  Scalable toolkit for efficient model reinforcement
  ☆1,267Updated this week
• google / lmeval
  ☆237Updated 2 months ago
• MoonshotAI / Kimi-Linear
  ☆1,278Updated 2 months ago
• openai / circuit_sparsity
  Open-source release accompanying Gao et al. 2025
  ☆498Updated last month
• MoonshotAI / kosong
  The LLM abstraction layer for modern AI agent applications.
  ☆499Updated this week
• McGill-NLP / the-markovian-thinker
  Code for paper "The Markovian Thinker: Architecture-Agnostic Linear Scaling of Reasoning"
  ☆339Updated 2 months ago
• NVlabs / ToolOrchestra
  ToolOrchestra is an end-to-end RL training framework for orchestrating tools and agentic workflows.
  ☆604Updated last month
• PrimeIntellect-ai / prime-rl
  Async RL Training at Scale
  ☆1,034Updated this week
• facebookresearch / matrix
  Matrix (Multi-Agent daTa geneRation Infra and eXperimentation framework) is a versatile engine for multi-agent conversational data genera…
  ☆260Updated last week
• Chengsong-Huang / R-Zero
  codes for R-Zero: Self-Evolving Reasoning LLM from Zero Data (https://www.arxiv.org/pdf/2508.05004)
  ☆736Updated last month
• SalesforceAIResearch / MCP-Universe
  MCP-Universe is a comprehensive framework designed for developing, testing, and benchmarking AI agents
  ☆548Updated 2 weeks ago
• lupantech / AgentFlow
  AgentFlow: In-the-Flow Agentic System Optimization
  ☆1,519Updated this week
• SWE-bench / SWE-smith
  [NeurIPS 2025 D&B Spotlight] Scaling Data for SWE-agents
  ☆532Updated this week
• laude-institute / harbor
  Harbor is a framework for running agent evaluations and creating and using RL environments.
  ☆488Updated this week
• ByteDance-Seed / Seed-Coder
  Seed-Coder is a family of lightweight open-source code LLMs comprising base, instruct and reasoning models, developed by ByteDance Seed.
  ☆732Updated 7 months ago
• inclusionAI / ASearcher
  An Open-Source Large-Scale Reinforcement Learning Project for Search Agents
  ☆543Updated 2 months ago
• xlang-ai / OpenCUA
  OpenCUA: Open Foundations for Computer-Use Agents
  ☆646Updated 2 weeks ago
• agentica-project / rllm
  ☆321Updated 4 months ago