Evaluate and improve models and agents using environments
☆1,314Nov 2, 2026Updated this week
Alternatives and similar repositories for Gym
Users that are interested in Gym are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- Scalable toolkit for efficient model reinforcement☆2,102Updated this week
- Open-source library for scalable, reproducible evaluation of AI models and benchmarks.☆355Oct 19, 2026Updated 2 weeks ago
- A project to improve skills of large language models☆1,056Updated this week
- An interface library for RL post training with environments.☆2,827Updated this week
- SkyRL: A Modular Full-stack RL Library for LLMs☆2,490Updated this week
- GPU virtual machines on DigitalOcean Gradient AI • AdGet to production fast with high-performance AMD and NVIDIA GPUs you can spin up in seconds. The definition of operational simplicity.
- 🚀 Pytorch Distributed native training library for LLMs/VLMs with OOTB Hugging Face support☆1,068Updated this week
- Miles is an enterprise-facing reinforcement learning framework for LLM and VLM post-training, forked from and co-evolving with slime.☆3,253Updated this week
- slime is an LLM training framework for RL Scaling.☆8,774Oct 27, 2026Updated last week
- Our library for RL environments + evals☆4,763Updated this week
- Training library for Megatron-based models with bidirectional Hugging Face conversion capability☆977Updated this week
- Agentic RL Training at Scale☆2,213Updated this week
- Scalable data pre processing and curation toolkit for LLMs☆1,847Updated this week
- PyTorch-native post-training at scale☆707Sep 9, 2026Updated last month
- 🎨 NeMo Data Designer: Generate high-quality synthetic data from scratch or from seed data.☆2,387Updated this week
- Deploy to Railway using AI coding agents - Free Credits Offer • AdUse Claude Code, Codex, OpenCode, and more. Autonomous software development now has the infrastructure to match with Railway.
- Developer Asset Hub for NVIDIA Nemotron — A one-stop resource for training recipes, usage cookbooks, datasets, and full end-to-end refere…☆2,270Updated this week
- Framework for evaluating and improving agents☆6,719Updated this week
- Agentic RL on Any Harness at Scale☆867Updated this week
- Post-training with Tinker☆4,232Updated this week
- The RL Bridge for LLM-based Agent Applications. Made Simple & Flexible.☆5,889Updated this week
- verl/HybridFlow: A Flexible and Efficient RL Post-Training Framework☆24,091Updated this week
- A scalable, agentic-first, and HuggingFace-native RL framework for research (9k lines).☆1,210Updated this week
- A compact implementation of SGLang, designed to demystify the complexities of modern LLM serving systems.☆5,498May 17, 2026Updated 5 months ago
- Democratizing Reinforcement Learning for LLMs☆5,905Oct 16, 2026Updated 2 weeks ago
- 1-Click AI Models by DigitalOcean Gradient • AdDeploy popular AI models on DigitalOcean Gradient GPU virtual machines with just a single click. Zero configuration with optimized deployments.
- A tool to configure, launch and manage your machine learning experiments.☆263Updated this week
- AllenAI's post-training codebase☆3,915Updated this week
- Ongoing research training transformer models at scale☆18,316Updated this week
- ☆291Updated this week
- AgentENV (AENV) is a distributed platform for running agent environments at scale.☆3,710Updated this week
- A unified library of SOTA model optimization techniques like quantization, distillation, pruning, neural architecture search, speculative…☆5,488Updated this week
- Agent Reinforcement Trainer: train multi-step agents for real-world tasks using GRPO. Give your agents on-the-job training. Reinforcement…☆10,837Oct 26, 2026Updated last week
- A scalable generative AI framework built for researchers and developers working on Large Language Models, Multimodal, and Speech AI (Auto…☆18,672Updated this week
- SGLang is a high-performance serving framework for large language models and multimodal models.☆38,342Updated this week
- Deploy to Railway using AI coding agents - Free Credits Offer • AdUse Claude Code, Codex, OpenCode, and more. Autonomous software development now has the infrastructure to match with Railway.
- A Gym for Agentic LLMs☆511Jan 21, 2026Updated 9 months ago
- Checkpoint-engine is a simple middleware to update model weights in LLM inference engines☆1,018Oct 22, 2026Updated last week
- OpenTinker is an RL-as-a-Service infrastructure for foundation models☆678Mar 21, 2026Updated 7 months ago
- A library for exporting models including NeMo and Hugging Face to optimized inference backends, and deploying them for efficient querying☆43Updated this week
- Train transformer language models with reinforcement learning.☆19,649Updated this week
- [NeurIPS 2025 Spotlight] Reasoning Environments for Reinforcement Learning with Verifiable Rewards☆1,542Apr 17, 2026Updated 6 months ago
- A benchmark for LLMs on complicated tasks in the terminal☆2,613Jul 11, 2026Updated 3 months ago