AI open source rankings.

The prime repository for state-of-the-art Multilingual Question Answering research and development.

Zero-dependency browser video editor that AI agents can drive — JSON timeline, MCP + REST, live-reloading UI

A top-down, practical guide to learn AI, Deep learning and Machine Learning.

AI Werewolf game. You take one seat, LLM players fill the rest. AI 狼人杀。

DeepSeek 系列工作解读、扩展和复现。

Enhance your application with the ability to see and interact with humans using any RGB camera.

🔥 SpatialVLA: a spatial-enhanced vision-language-action model that is trained on 1.1 Million real robot episodes. Accepted at RSS 2025.

A unified framework for easy fine-tuning in Flow-Matching models

Interactive LLM Powered NPCs, is an open-source project that completely transforms your interaction with non-player characters (NPCs) in any game! 🎮🤖🚀

Code for Xiaomi-Robotics-1

[ICLR'26] The official code implementation for "Cache-to-Cache: Direct Semantic Communication Between Large Language Models"

AI System Design - Learn how to design AI systems built on LLMs, RAG, and AI Agents step by step.

One dashboard to manage all your AI subscriptions — track quotas, costs, accounts, Claude Code proxy, and Codex proxy in one place.

A reading list of video generation

Animation oriented nodes pack for ComfyUI

DeepSeek Harness 轻量桌面启动器：启动项与多实例，版本、插件、整合包、MCP 和技能管理。A lightweight desktop launcher for DeepSeek Harness: launch entries, multiple instances, versions, plugins, modpacks, MCP and skills.

Curated list of ChatGPT related resource, tools, prompts, apps / ChatGPT 相關優質資源、工具、應用的精選清單。

Efficient Universal Perception Encoder: a single on-device vision encoder with versatile representations that match or exceed specialized experts across multiple task domains.

Fast, stateless CLI for web search and scrape. Built for AI agents.

Hashbrown is a framework for building agents that run the browser. Built for Angular and React.

本项目旨在为致力于进入VLA(Vision-Language-Action)领域的算法工程师提供一份全中文、实战导向的学习/面试手册。 不同于通用的 CV/NLP 面试指南，本项目聚焦于 Robotics 特有的挑战

HoloMotion: A Foundation Model for Whole-Body Humanoid Control

R1-searcher: Incentivizing the Search Capability in LLMs via Reinforcement Learning

"Unit tests" for your agent skills

A curated list of awesome exploration RL resources (continually updated)

The local-first LLM Wiki: open-source knowledge graph builder, RAG knowledge base, and agent memory store. Built on Andrej Karpathy's pattern. An Obsidian alternative for personal knowledge management, AI second brain, and durable Claude Code / Codex / OpenClaw memory.

RDNA-native LLM inference engine in Rust.

Multi-agent communication extension for pi coding agent

Dynamic SLAM, Life-long SLAM Research(Lidar, Visual, Sensor Fusion etc.)