Evaluate and improve models and agents using environments
☆912May 22, 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☆1,635Updated this week
- Open-source library for scalable, reproducible evaluation of AI models and benchmarks.☆283Updated this week
- Weird autoencoder experiments☆24May 11, 2026Updated last week
- Official Repo for SvS: A Self-play with Variational Problem Synthesis strategy for RLVR training☆54Dec 13, 2025Updated 5 months ago
- ☆14Apr 16, 2025Updated last year
- 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.
- An interface library for RL post training with environments.☆1,870May 13, 2026Updated last week
- Scalable data pre processing and curation toolkit for LLMs☆1,576Updated this week
- Post-training with Tinker☆3,293Updated this week
- Training library for Megatron-based models with bidirectional Hugging Face conversion capability☆642Updated this week
- Official implementation of paper "Think-at-Hard: Selective Latent Iterations to Improve Reasoning Language Models"☆69Apr 4, 2026Updated last month
- Hand-Rolled GPU communications library☆93Nov 25, 2025Updated 5 months ago
- Implementation of the model: "Reka Core, Flash, and Edge: A Series of Powerful Multimodal Language Models" in PyTorch☆29May 12, 2026Updated last week
- ☆33Jan 26, 2026Updated 3 months ago
- 🎨 NeMo Data Designer: Generate high-quality synthetic data from scratch or from seed data.☆1,880Updated this week
- Deploy on Railway without the complexity - Free Credits Offer • AdConnect your repo and Railway handles the rest with instant previews. Quickly provision container image services, databases, and storage volumes.
- Supercharge Your LLM with the Fastest KV Cache Layer☆8,282Updated this week
- ☆26Mar 7, 2026Updated 2 months ago
- verl/HybridFlow: A Flexible and Efficient RL Post-Training Framework☆21,337May 16, 2026Updated last week
- Async pipelined version of Verl☆125Apr 8, 2025Updated last year
- ☆23Jan 15, 2026Updated 4 months ago
- BigCodeBench: Benchmarking Code Generation with Diverse Function Calls and Complex Instructions☆25Aug 8, 2024Updated last year
- 🚀 SuperMCP - Create multiple isolated MCP servers using a single connector. Build powerful Model Context Protocol integrations for datab…☆57Jan 26, 2026Updated 3 months ago
- PyTorch-native post-training at scale☆684Updated this week
- SkyRL: A Modular Full-stack RL Library for LLMs☆1,867Updated this week
- Wordpress hosting with auto-scaling - Free Trial Offer • AdFully Managed hosting for WordPress and WooCommerce businesses that need reliable, auto-scalable performance. Cloudways SafeUpdates now available.
- Checkpoint-engine is a simple middleware to update model weights in LLM inference engines☆955Feb 28, 2026Updated 2 months ago
- Trinity-RFT is a general-purpose, flexible and scalable framework designed for reinforcement fine-tuning (RFT) of large language models (…☆633Updated this week
- Agent Reinforcement Trainer: train multi-step agents for real-world tasks using GRPO. Give your agents on-the-job training. Reinforcement…☆9,459May 16, 2026Updated last week
- A Lightweight LLM Post-Training Library☆2,276May 15, 2026Updated last week
- An open source MCP proxy.☆18Jan 3, 2025Updated last year
- Scaling Agentic Reinforcement Learning with a Multi-Turn, Multi-Task Framework☆289Jan 17, 2026Updated 4 months ago
- Breaking the Curse of Space Explosion: Towards Efficient NAS with Curriculum Search☆17Jul 25, 2024Updated last year
- The RL Bridge for LLM-based Agent Applications. Made Simple & Flexible.☆5,203Updated this week
- Submodule for Grounded-SAM☆12Apr 17, 2023Updated 3 years ago
- GPUs on demand by Runpod - Special Offer Available • AdRun AI, ML, and HPC workloads on powerful cloud GPUs—without limits or wasted spend. Deploy GPUs in under a minute and pay by the second.
- Build, enrich, and transform datasets using AI models with no code☆1,635Apr 9, 2026Updated last month
- Online Preference Alignment for Language Models via Count-based Exploration☆18Jan 14, 2025Updated last year
- Standardized environment infrastructure for Agentic AI development.☆300May 15, 2026Updated last week
- Open-source toolkit for training, Priming, and serving next generation Hybrid architectures☆69May 9, 2026Updated 2 weeks ago
- General-purpose planning and execution harness for LLMs — structured phases, critique, gating, and review☆66May 16, 2026Updated last week
- Code for our paper "Mask-Align: Self-Supervised Neural Word Alignment" in ACL 2021☆61May 10, 2021Updated 5 years ago
- ☆14Apr 7, 2025Updated last year