Scalable toolkit for efficient model reinforcement

Lightning-Fast RL for LLM Reasoning and Agents. Made Simple & Flexible.

Async RL Training at Scale

health care management system frontend: react backend: flask

Democratizing Reinforcement Learning for LLMs

NVIDIA Isaac GR00T N1.6 - A Foundation Model for Generalist Robots.

verl-agent is an extension of veRL, designed for training LLM/VLM agents via RL. verl-agent is also the official code for paper "Group-in-Group Policy Optimization for LLM Agent Training"

verl: Volcano Engine Reinforcement Learning for LLMs

Vision infrastructure to turn complex documents into RAG/LLM-ready data

Train transformer language models with reinforcement learning.

The TypeScript AI agent framework. ⚡ Assistants, RAG, observability. Supports any LLM: GPT-4, Claude, Gemini, Llama.

Every AI Agent deserves a wallet.

Build, enrich, and transform datasets using AI models with no code

⚡A CLI tool for code structural search, lint and rewriting. Written in Rust

Fine-tuning & Reinforcement Learning for LLMs. 🦥 Train OpenAI gpt-oss, DeepSeek-R1, Qwen3, Gemma 3, TTS 2x faster with 70% less VRAM.

ClickHouse® is a real-time analytics database management system

Framework for orchestrating role-playing, autonomous AI agents. By fostering collaborative intelligence, CrewAI empowers agents to work together seamlessly, tackling complex tasks.

Universal memory layer for AI Agents

Agent Reinforcement Trainer: train multi-step agents for real-world tasks using GRPO. Give your agents on-the-job training. Reinforcement learning for Qwen2.5, Qwen3, Llama, and more!

Save, load, host, and share AI model checkpoints without slowing down training. Host on Lightning AI or your own cloud with enterprise-grade access controls.

Machine Learning Engineering Open Book

A curated list of Large Language Model (LLM) Interpretability resources.

OpenR: An Open Source Framework for Advanced Reasoning with Large Language Models

The simplest, fastest repository for training/finetuning medium-sized GPTs.

Fully open reproduction of DeepSeek-R1

An LLM-powered knowledge curation system that researches a topic and generates a full-length report with citations.

A minimal Python framework for building custom AI inference servers with full control over logic, batching, and scaling.

Curated list of datasets and tools for post-training.