A scalable, agentic-first, and HuggingFace-native RL framework for research (9k lines).
☆1,360Nov 17, 2026Updated this week
Alternatives and similar repositories for labs-molt
Users that are interested in labs-molt are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- Miles is an enterprise-facing reinforcement learning framework for LLM and VLM post-training, forked from and co-evolving with slime.☆3,331Updated this week
- slime is an LLM training framework for RL Scaling.☆8,842Nov 5, 2026Updated last week
- Agentic RL on Any Harness at Scale☆878Updated this week
- Scalable toolkit for efficient model reinforcement☆2,140Updated this week
- 🚀 Pytorch Distributed native training library for LLMs/VLMs with OOTB Hugging Face support☆1,087Updated 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.
- An LLM post-training framework with vLLM for RL Scaling☆504Updated this week
- SkyRL: A Modular Full-stack RL Library for LLMs☆2,539Updated this week
- AgentENV (AENV) is a distributed platform for running agent environments at scale.☆3,754Updated this week
- Uni-Agent is a framework for training long-horizon agents.☆733Updated this week
- Compact and Agent-Native MoE Training System☆360Updated this week
- The RL Bridge for LLM-based Agent Applications. Made Simple & Flexible.☆5,918Updated this week
- UniRL is a Framework for Unified Multimodal Model Reinforcement Learning☆1,051Updated this week
- Agentic RL Training at Scale☆2,257Updated this week
- verl/HybridFlow: A Flexible and Efficient RL Post-Training Framework☆24,266Updated 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.
- An Efficient and User-Friendly Scaling Library for Reinforcement Learning with Large Language Models☆3,455Updated this week
- An Asynchronous Reinforcement Learning Engine for Omni-Modal Post-Training at Scale☆677Updated this week
- Democratizing Reinforcement Learning for LLMs☆5,925Oct 16, 2026Updated last month
- Training library for Megatron-based models with bidirectional Hugging Face conversion capability☆1,005Updated this week
- Checkpoint-engine is a simple middleware to update model weights in LLM inference engines☆1,025Oct 22, 2026Updated 3 weeks ago
- A scalable asynchronous reinforcement learning implementation with in-flight weight updates.☆440Aug 5, 2026Updated 3 months ago
- TokenSpeed is a speed-of-light LLM inference engine.☆2,934Updated this week
- Mixture-of-experts (MoE) training megakernel for NVL72s☆647Oct 1, 2026Updated last month
- MoonEP: A Perfectly Balanced Expert Parallelism Library via Dynamic Redundant Experts☆1,214Oct 12, 2026Updated last month
- 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.
- 🚀 Efficient implementations for emerging model architectures☆6,059Updated this week
- VeOmni: Scaling Any Modality Model Training with Model-Centric Distributed Recipe Zoo☆2,296Updated this week
- My learning notes for ML SYS.☆7,684Oct 21, 2026Updated 3 weeks ago
- An Easy-to-use, Scalable and High-performance Agentic RL Framework based on Ray (PPO & DAPO & REINFORCE++ & VLM & TIS & vLLM & Ray & Asy…☆10,167Nov 3, 2026Updated 2 weeks ago
- A compact implementation of SGLang, designed to demystify the complexities of modern LLM serving systems.☆5,609May 17, 2026Updated 6 months ago
- FlashKDA: high-performance Kimi Delta Attention kernels☆1,297Updated this week
- Ongoing research training transformer models at scale☆18,433Updated this week
- ☆37Updated this week
- FlashREINFORCE: Critic-Free, Single-Rollout, Asynchronous RL for Agentic Language Models☆106Sep 14, 2026Updated 2 months ago
- 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.
- Bitwise-identical token probabilities between RL rollout (vLLM) and training☆45Nov 8, 2026Updated last week
- Accelerating MoE with IO and Tile-aware Optimizations☆791Aug 29, 2026Updated 2 months ago
- Training terminal-agents☆345Nov 2, 2026Updated 2 weeks ago
- verl/HybridFlow: A Flexible and Efficient RL Post-Training Framework☆761Oct 19, 2026Updated last month
- A Gym for Agentic LLMs☆518Jan 21, 2026Updated 9 months ago
- DeepSpec: a full-stack codebase for training and evaluating speculative decoding algorithms☆7,317Jul 9, 2026Updated 4 months ago
- A PyTorch native platform for training generative AI models☆5,916Updated this week
Are these results useful?