NVIDIA-NeMo / GymLinks
Build RL environments for LLM training
☆625Updated last week
Alternatives and similar repositories for Gym
Users that are interested in Gym are comparing it to the libraries listed below
Sorting:
- PyTorch-native post-training at scale☆613Updated this week
- OpenTinker is an RL-as-a-Service infrastructure for foundation models☆625Updated last week
- Checkpoint-engine is a simple middleware to update model weights in LLM inference engines☆902Updated this week
- bloom - evaluate any behavior immediately 🌸🌱☆1,152Updated 3 weeks ago
- Developer Asset Hub for NVIDIA Nemotron — A one-stop resource for training recipes, usage cookbooks, datasets, and full end-to-end refere…☆392Updated this week
- WeDLM: The fastest diffusion language model with standard causal attention and native KV cache compatibility, delivering real speedups ov…☆597Updated 3 weeks ago
- ☆1,283Updated 2 months ago
- ☆867Updated 4 months ago
- Research code artifacts for Code World Model (CWM) including inference tools, reproducibility, and documentation.☆833Updated last month
- OpenCUA: Open Foundations for Computer-Use Agents☆672Updated this week
- ☆237Updated 2 months ago
- Seed-Coder is a family of lightweight open-source code LLMs comprising base, instruct and reasoning models, developed by ByteDance Seed.☆738Updated 8 months ago
- ToolOrchestra is an end-to-end RL training framework for orchestrating tools and agentic workflows.☆642Updated last week
- MCP-Universe is a comprehensive framework designed for developing, testing, and benchmarking AI agents☆550Updated 3 weeks ago
- Code for paper "The Markovian Thinker: Architecture-Agnostic Linear Scaling of Reasoning"☆339Updated 2 months ago
- Open-source release accompanying Gao et al. 2025☆501Updated last month
- A benchmark for LLMs on complicated tasks in the terminal☆1,494Updated 2 weeks ago
- Matrix (Multi-Agent daTa geneRation Infra and eXperimentation framework) is a versatile engine for multi-agent conversational data genera…☆261Updated this week
- [ICLR2026] Test-Time Scaling with Reflective Generative Model☆302Updated last week
- Scalable toolkit for efficient model reinforcement☆1,293Updated this week
- Post-training with Tinker☆2,805Updated this week
- The offical repo for "Parallel-R1: Towards Parallel Thinking via Reinforcement Learning"☆255Updated 2 months ago
- Evolve your language agent with Agentic Context Engineering (ACE)☆576Updated 2 weeks ago
- An interface library for RL post training with environments.☆1,112Updated this week
- Code and implementations for the paper "AgentGym-RL: Training LLM Agents for Long-Horizon Decision Making through Multi-Turn Reinforcemen…☆577Updated 4 months ago
- codes for R-Zero: Self-Evolving Reasoning LLM from Zero Data (https://www.arxiv.org/pdf/2508.05004)☆755Updated this week
- A clean, modular SDK for building AI agents with OpenHands V1.☆476Updated last week
- 🐉 Loong: Synthesize Long CoTs at Scale through Verifiers.☆483Updated this week
- Code to accompany the Universal Deep Research paper (https://arxiv.org/abs/2509.00244)☆459Updated 5 months ago
- A Lightweight LLM Post-Training Library☆2,140Updated this week