Open-source repositories gaining traction right now.
316 repositories

《深入理解 AI Agent:设计原理与工程实践》(李博杰 著)开源主仓库:全书正文、编译版 PDF 与按章配套代码

利用AI大模型,一键生成高清短视频 Generate short videos with one click using AI LLM.

Official inference framework for 1-bit LLMs

A vector index built on TurboQuant, written in Rust with Python bindings

Turn any technical book PDF into a Claude Code skill — ready to study, reference, and use while you work.

Agent harness built with LangChain and LangGraph. Equipped with a planning tool, a filesystem backend, and the ability to spawn subagents - well-equipped to handle complex agentic tasks.

Academic Research Skills for Claude Code: research → write → review → revise → finalize

🤗 ml-intern: an open-source ML engineer that reads papers, trains models, and ships ML models

🌐 Make websites accessible for AI agents. Automate tasks online with ease.

Open Source AI Platform - AI Chat with advanced features that works with every LLM

A curated list of awesome skills, hooks, slash-commands, agent orchestrators, applications, and plugins for Claude Code by Anthropic

Give Claude the ability to watch any video. /watch downloads, extracts frames, transcribes, hands it all to Claude.

⭐AI-driven public opinion & trend monitor with multi-platform aggregation, RSS, and smart alerts.🎯 告别信息过载,你的 AI 舆情监控助手与热点筛选工具!聚合多平台热点 + RSS 订阅,支持关键词精准筛选。AI 智能筛选新闻 + AI 翻译 + AI 分析简报直推手机,也支持接入 MCP 架构,赋能 AI 自然语言对话分析、情感洞察与趋势预测等。支持 Docker ,数据本地/云端自持。集成微信/飞书/钉钉/Telegram/邮件/ntfy/bark/slack 等渠道智能推送。

AI 时代的伯克希尔:基于 Claude Code / Codex 的价值投资研究框架。巴菲特·芒格·段永平·李录四大师方法论 + 多Agent并行研究。| AI-era Berkshire: a value investing research framework built for Claude Code / Codex. 4 masters' methodologies + multi-agent adversarial analysis.

A set of ready to use Agent Skills for research, science, engineering, analysis, finance and writing.

100+ AI Agent & RAG apps you can actually run — clone, customize, ship.

The most powerful and modular diffusion model GUI, api and backend with a graph/nodes interface.

A lightweight, powerful framework for multi-agent workflows

Self-evolving agent: grows skill tree from 3.3K-line seed, achieving full system control with 6x less token consumption

A feed-forward 3D foundation model for reconstructing scenes from streaming data

A comprehensive collection of Agent Skills for context engineering, multi-agent architectures, and production agent systems. Use when building, optimizing, or debugging agent systems that require effective context management.

Machine Learning Systems

OpenSandbox is a general-purpose sandbox platform for AI applications, offering multi-language SDKs, unified sandbox APIs, and Docker/Kubernetes runtimes for scenarios like Coding Agents, GUI Agents, Agent Evaluation, AI Code Execution, and RL Training.

Learn it. Build it. Ship it for others.

A specialized Claude Code workspace for creating long-form, SEO-optimized blog content for any business. This system helps you research, write, analyze, and optimize content that ranks well and serves your target audience.


The best ChatGPT that $100 can buy.

Public repository for Agent Skills

OCR model that handles complex tables, forms, handwriting with full layout.

World's first open-source, agentic video production system. 12 pipelines, 52 tools, 500+ agent skills. Turn your AI coding assistant into a full video production studio.

VoxCPM2: Tokenizer-Free TTS for Multilingual Speech Generation, Creative Voice Design, and True-to-Life Cloning

Skills Catalog for Codex

Hindsight: Agent Memory That Learns

"RAG-Anything: All-in-One RAG Framework"

Agent framework and applications built upon Qwen>=3.0, featuring Function Calling, MCP, Code Interpreter, RAG, Chrome extension, etc.

PersonaPlex code.

OpenRAG is a comprehensive, single package Retrieval-Augmented Generation platform built on Langflow, Docling, and Opensearch.

14MB foundation model for tiny devices; phones, wearables, smart home, and robots.

Edit videos with coding agents

Use claude-code for free in the terminal, VSCode extension or discord like OpenClaw (voice supported)


DeepTutor: Lifelong Personalized Tutoring. https://deeptutor.info/.

微舆:人人可用的多Agent舆情分析助手,打破信息茧房,还原舆情原貌,预测未来走向,辅助决策!从0实现,不依赖任何框架。

The AI Scientist-v2: Workshop-Level Automated Scientific Discovery via Agentic Tree Search

"ViMax: Agentic Video Generation (Director, Screenwriter, Producer, and Video Generator All-in-One)"

Free Motion Capture for Everyone 💀✨

🚀🚀 「大模型」2小时完全从0训练26M的小参数GPT!🌏 Train a 26M-parameter GPT from scratch in just 2h!

AI turns documents or topics into real, native PowerPoint decks—with native shapes, transitions and animations, data-backed charts and tables on demand, audio narration from speaker notes, and support for your own .pptx templates. · by Hugo He

openpilot is an operating system for robotics. Currently, it upgrades the driver assistance system on 300+ supported cars.

基于多智能体LLM的中文金融交易框架 - TradingAgents中文增强版

A Flexible Framework for Experiencing Heterogeneous LLM Inference/Fine-tune Optimizations

The CLI and skills that turn any coding assistant into an expert at creating, evaluating, and deploying AI agents on Google Cloud.

An open-source long-horizon SuperAgent harness that researches, codes, and creates. With the help of sandboxes, memories, tools, skill, subagents and message gateway, it handles different levels of tasks that could take minutes to hours.

Claude Skill: Multi-source content processor for NotebookLM. Supports WeChat articles, web pages, YouTube, PDF, Markdown, search queries → Podcast/PPT/MindMap/Quiz etc.

Local UI to run and train LLMs and diffusion models, including Qwen3.8, Kimi K3, MiniMax-H3, Gemma 4, DeepSeek-V4, FLUX and more.

TimesFM (Time Series Foundation Model) is a pretrained time-series foundation model developed by Google Research for time-series forecasting.

MLX-VLM is a package for inference and fine-tuning of Vision Language Models (VLMs) on your Mac using MLX.

Specification and documentation for Agent Skills

Build and run agents you can see, understand and trust.

Build local voice agents with open-source models
Paste a github.com URL. Submissions are reviewed before they are tracked.