Lists (19)
Stars
Local UI to run and train LLMs and diffusion models, including Qwen3.8, Kimi K3, MiniMax-H3, Gemma 4, DeepSeek-V4, FLUX and more.
HY-World 2.0: A Multi-Modal World Model for Reconstructing, Generating, and Simulating 3D Worlds
Use PEFT or Full-parameter to CPT/SFT/DPO/GRPO 600+ LLMs (Qwen3.6, DeepSeek-V4, GLM-5.1, InternLM3, Llama4, ...) and 300+ MLLMs (Qwen3-VL, Qwen3-Omni, InternVL3.5, Ovis2.5, GLM4.5v, Gemma4, Llava, …
Unified Codebase for Advanced World Models.
verl/HybridFlow: A Flexible and Efficient RL Post-Training Framework
An interface library for RL post training with environments.
Train transformer language models with reinforcement learning.
Research into how agentic AI coding assistants work. Reconstructed prompt patterns, agent coordination, and security classification
Fast, accurate & comprehensive text measurement & layout
Self-evolving Context Database for AI Agents. Unify Agent Memory, Knowledge RAG and Skills.
HY-World 1.5: A Systematic Framework for Interactive World Modeling with Real-Time Latency and Geometric Consistency
The ultimate training toolkit for finetuning diffusion models
AI Elements is a component library and custom registry built on top of shadcn/ui to help you build AI-native applications faster.
Official inference repo for FLUX.2 models
Community-contributed instructions, agents, skills, and configurations to help you make the most of GitHub Copilot.
[ICCV 2025 Best Paper] Official repository for BrickGPT, the first approach for generating physically stable toy brick models from text prompts.
TripoSG: High-Fidelity 3D Shape Synthesis using Large-Scale Rectified Flow Models
OrioleDB – building a modern cloud-native storage engine (... and solving some PostgreSQL wicked problems)
Community plugin to control Blender 3D with any LLM of your choice
Fully open reproduction of DeepSeek-R1