Evaluate and improve models and agents using environments
☆1,204Sep 23, 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☆2,029Updated this week
- A project to improve skills of large language models☆1,042Updated this week
- Open-source library for scalable, reproducible evaluation of AI models and benchmarks.☆342Updated this week
- Miles is an enterprise-facing reinforcement learning framework for LLM and VLM post-training, forked from and co-evolving with slime.☆2,979Updated this week
- An interface library for RL post training with environments.☆2,606Updated 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.
- 🚀 Pytorch Distributed native training library for LLMs/VLMs with OOTB Hugging Face support☆968Updated this week
- slime is an LLM post-training framework for RL Scaling.☆8,524Updated this week
- Our library for RL environments + evals☆4,648Updated this week
- PyTorch-native post-training at scale☆703Sep 9, 2026Updated 2 weeks ago
- Training library for Megatron-based models with bidirectional Hugging Face conversion capability☆928Updated this week
- SkyRL: A Modular Full-stack RL Library for LLMs☆2,345Updated this week
- Scalable data pre processing and curation toolkit for LLMs☆1,779Updated this week
- Developer Asset Hub for NVIDIA Nemotron — A one-stop resource for training recipes, usage cookbooks, datasets, and full end-to-end refere…☆2,085Updated this week
- Agentic RL Training at Scale☆2,072Updated this week
- Managed Kubernetes at scale on DigitalOcean • AdDigitalOcean Kubernetes includes the control plane, bandwidth allowance, container registry, automatic updates, and more for free.
- The RL Bridge for LLM-based Agent Applications. Made Simple & Flexible.☆5,791Updated this week
- 🎨 NeMo Data Designer: Generate high-quality synthetic data from scratch or from seed data.☆2,272Updated this week
- Agentic RL on Any Harness at Scale☆843Aug 13, 2026Updated last month
- Post-training with Tinker☆4,145Updated this week
- verl/HybridFlow: A Flexible and Efficient RL Post-Training Framework☆23,583Updated this week
- Framework for evaluating and improving agents☆5,538Updated this week
- A compact implementation of SGLang, designed to demystify the complexities of modern LLM serving systems.☆5,147May 17, 2026Updated 4 months ago
- A tool to configure, launch and manage your machine learning experiments.☆259Updated this week
- ☆276Updated this week
- Proton VPN Special Offer - Get 70% off • AdSpecial partner offer. Trusted by over 100 million users worldwide. Tested, Approved and Recommended by Experts.
- Checkpoint-engine is a simple middleware to update model weights in LLM inference engines☆1,005Sep 15, 2026Updated last week
- Democratizing Reinforcement Learning for LLMs☆5,836Sep 12, 2026Updated last week
- [NeurIPS 2025 Spotlight] Reasoning Environments for Reinforcement Learning with Verifiable Rewards☆1,512Apr 17, 2026Updated 5 months ago
- Agent Reinforcement Trainer: train multi-step agents for real-world tasks using GRPO. Give your agents on-the-job training. Reinforcement…☆10,770Updated this week
- A Gym for Agentic LLMs☆510Jan 21, 2026Updated 8 months ago
- A scalable asynchronous reinforcement learning implementation with in-flight weight updates.☆434Aug 5, 2026Updated last month
- A library for exporting models including NeMo and Hugging Face to optimized inference backends, and deploying them for efficient querying☆42Updated this week
- A benchmark for LLMs on complicated tasks in the terminal☆2,593Jul 11, 2026Updated 2 months ago
- SGLang is a high-performance serving framework for large language models and multimodal models.☆36,377Updated this week
- AI Agents on DigitalOcean Gradient AI Platform • AdBuild production-ready AI agents using customizable tools or access multiple LLMs through a single endpoint. Create custom knowledge bases or connect external data.
- A lightweight, AI-native training framework for large language models. Designed for fast iteration, reproducible experiments, and modular…☆587Sep 4, 2026Updated 2 weeks ago
- OpenTinker is an RL-as-a-Service infrastructure for foundation models☆679Mar 21, 2026Updated 6 months ago
- Atropos is a Language Model Reinforcement Learning Environments framework for collecting and evaluating LLM trajectories through diverse …☆1,351Jul 4, 2026Updated 2 months ago
- [ICML 2026] RLVE: Scaling Up Reinforcement Learning for Language Models with Adaptive Verifiable Environments☆235Apr 30, 2026Updated 4 months ago
- bloom - evaluate any behavior immediately 🌸🌱☆1,407May 7, 2026Updated 4 months ago
- LMCache: Supercharge Your LLM with the Fastest KV Cache Layer☆11,895Updated this week
- cuTile is a programming model for writing parallel kernels for NVIDIA GPUs☆2,150Updated this week