Project directory

Projects

Open-source AI projects tracked by the leaderboard, ordered by GitHub stars.

Python 42,781 stars

agno-agi/agno

Build, run, and manage agent platforms.

### Overview: Agno is a comprehensive framework and runtime for agent platforms, allowing developers to build, run, and manage their agent stacks with ease. ### Key Features: - **Build Agent Platform**: Use the Agno SDK to create and deploy agent platforms. - **Run Agent Platform**: Utilize the AgentOS runtime to execute agent applications. - **Manage Platform**: Access the AgentOS UI for comprehensive management and monitoring. ### Tech Stack: Python ### Why It Matters: Agno empowers developers to build, run, and manage agent platforms with ease, ensuring control over data, memory, and security. It integrates seamlessly with various tools and platforms, making it a versatile solution for agent development. ### Repository: agno-agi/agno ### GitHub Stars: 42,781 ### Primary Language: Python ### GitHub Description: Build, run, and manage agent platforms.

Python 42,593 stars

apachecn/ailearning

AiLearning：数据分析+机器学习实战+线性代数+PyTorch+NLTK+TF2

### Overview: AI Learning: 数据分析+机器学习实战+线性代数+PyTorch+NLTK+TF2 ### Key features: - 实战项目 - 线性代数 - PyTorch - NLTK - TensorFlow 2.x - 数据分析 - 机器学习实战 ### Tech stack: Python ### Why it matters: 通过本项目，你可以系统地学习数据分析、机器学习、线性代数、PyTorch、NLTK和TensorFlow 2.x等技术，掌握实战项目开发技能，提升编程能力。

Python 42,443 stars

666ghj/BettaFish

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。

Overview: 微舆：一个从0实现的多智能体舆情分析系统，旨在打破信息茧房，还原舆情原貌，预测未来走向，辅助决策。用户只需像聊天一样提出分析需求，智能体开始全自动分析国内外30+主流社媒与数百万条大众评论。 Key features: - 实时监控国内外关键社媒 - 融合微调模型、统计模型等多模型协同工作，确保深度、准度与多维视角 - 多模态解析短视频内容，提取结构化多模态信息 - 强大多模态能力，全面掌握舆情动态 - 强化Agent协作机制，避免同质化思维，催生高质量集体智能与决策支持 - 公私域数据无缝融合，提供外部趋势+内部洞察的分析能力 - 轻量化与高扩展性框架，基于纯Python模块化设计，实现一键式部署 Tech stack: Python Why it matters: 微舆通过融合多种智能体和多模态分析能力，提供了一个简洁通用的数据分析引擎，能够有效辅助决策和预测未来走向。相比同类产品，微舆拥有六大优势：AI驱动的全域监控、超越LLM的复合分析引擎、强大的多模态能力、Agent“论坛”协作机制、公私域数据无缝融合以及轻量化与高扩展性框架。这使得微舆成为驱动一切业务场景的简洁通用的数据分析引擎。

Python 42,276 stars

anthropics/claude-plugins-official

Official, Anthropic-managed directory of high quality Claude Code Plugins.

Overview: The anthropics/claude-plugins-official repository is a curated directory of high-quality plugins for Claude Code, managed by Anthropic. It includes both internal and external plugins, each following a standardized structure. Key features: - Curated collection of high-quality plugins - Support for both internal and external plugins - Standardized plugin structure for consistency Tech stack: Python (primary language, though plugins can be in various languages) Why it matters: It provides a trusted source for plugins that enhance the functionality of Claude Code, ensuring quality and security for users.

Rust 42,135 stars

tinyhumansai/openhuman

The fastest, cheapest, most efficient open-source agent harness. Run more than 500 agents on a $10 VPS.

Overview: OpenHuman is an open-source agent harness designed for running multiple agents on a low-cost server, making it highly efficient and cost-effective. Key features: - Runs up to 500 agents on a $10 VPS - Desktop app for users - Rust library for developers Tech stack: Rust Why it matters: OpenHuman is a powerful tool for developers and users alike, offering a cost-effective and efficient way to run multiple agents, making it ideal for those looking to scale their projects without breaking the bank.

Python 42,067 stars

AstrBotDevs/AstrBot

AI Agent Assistant & development framework that integrates lots of IM platforms, LLMs, plugins and AI feature, and can be your openclaw alternative. ✨

### Overview: AstrBot is an AI Agent Assistant and development framework that integrates various IM platforms, LLMs, plugins, and AI features, offering a versatile solution for developers seeking an alternative to openclaw. Built with Python, it's designed to be highly customizable and efficient, making it a valuable tool for anyone looking to enhance their AI development capabilities. ### Key Features: - **Integration with Multiple Platforms**: AstrBot seamlessly integrates with a wide range of IM platforms, ensuring compatibility with various communication tools. - **Support for LLMs and Plugins**: The framework supports advanced language models and plugins, providing a robust ecosystem for AI development. - **Open-Source and Customizable**: AstrBot is open-source, allowing developers to modify and extend its functionality to meet specific needs. ### Tech Stack: Python ### Why It Matters: AstrBot stands out as a powerful and flexible AI development framework that simplifies the process of integrating AI features into existing projects. Its ability to work with multiple platforms and support for advanced AI models makes it an invaluable tool for developers looking to enhance their applications with cutting-edge AI capabilities.

Python 41,575 stars

HKUDS/DeepTutor

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

### Overview: DeepTutor is a comprehensive platform designed to provide lifelong personalized tutoring for students of all ages. With its advanced AI-driven learning algorithms, DeepTutor adapts to each student's needs, offering tailored solutions for academic success. ### Key Features: - **Personalized Learning Paths**: Tailored study plans based on individual student performance and progress. - **Interactive Quizzes and Assessments**: Engaging quizzes and tests to reinforce knowledge and track understanding. - **Real-Time Feedback**: Immediate feedback on assignments and practice questions, helping students improve quickly. - **Progress Tracking**: Detailed analytics and reports to monitor and improve student performance over time. ### Tech Stack: - Python 3.11+ - Next.js 16 - AI and Machine Learning Algorithms ### Why It Matters: DeepTutor is revolutionizing the way education is delivered, making learning accessible and effective for students worldwide. Its personalized approach ensures that every student receives the support they need to achieve their goals, making it a valuable tool for educators and learners alike.

Python 41,431 stars

hpcaitech/ColossalAI

Making large AI models cheaper, faster and more accessible

### Overview: Colossal-AI is a framework designed to make large AI models more accessible, cheaper, and faster. ### Key Features: - **Instant GPU Access**: Quickly set up a Colossal-AI environment on HPC-AI Cloud, enabling high-performance AI workloads. - **Cost-Effective H200 Cluster**: Rent a high-performance GPU cluster for just $1.99 per hour, making AI more affordable. - **Access to Top Models**: Seamless integration with HPC-AI Model APIs, allowing you to access state-of-the-art language models without additional costs. ### Tech Stack: Python ### Why it Matters: Colossal-AI simplifies the process of deploying large AI models, making them more accessible and affordable for developers and researchers. By leveraging pre-configured environments and cost-effective GPU clusters, it significantly reduces the barrier to entry for AI development, enabling faster innovation and deployment of AI solutions.

Python 40,977 stars

wshobson/agents

Multi-harness agentic plugin marketplace for Claude Code, Codex, Cursor, OpenCode, GitHub Copilot, Google Antigravity, and Pi

### Overview: Explore a comprehensive collection of plugins, agents, and skills for AI coding tools, including Claude Code, OpenAI Codex CLI, Cursor, OpenCode, Antigravity CLI, GitHub Copilot, and Pi. This marketplace provides a unified interface for developers across multiple tools, ensuring a consistent coding experience. ### Key Features: - **Multi-harness support**: Choose the appropriate harness for your project and follow its specific setup instructions. - **Plugins**: Cover Python and JavaScript development, code review, testing, infrastructure, security, and more. - **Agents**: 92 local agents, 185 skills, and 105 commands, all sourced from a single Markdown repository. - **Commands**: Commands can be directly invoked as skills, enhancing the developer workflow. - **Quick Start**: Register the marketplace and install plugins with specific commands for different tools. - **Claude Code**: Register the marketplace and install the Python development plugin. - **Codex CLI**: Add the marketplace and install the Python development plugin. - **Cursor**: Use the committed plugin marketplace registry and follow the setup instructions. ### Tech Stack: Python ### Why It Matters: This marketplace simplifies the integration of AI tools into developer workflows, providing a unified interface for various AI coding tools, enhancing productivity and consistency across projects.

TypeScript 40,488 stars

Crosstalk-Solutions/project-nomad

Project NOMAD is an offline-first knowledge and education server. Wikipedia, thousands of books, courses, maps, and optional local AI, all running on hardware you own with no internet required.

### Overview: Project NOMAD is an offline-first knowledge and education server, providing critical tools, knowledge, and AI to keep users informed and empowered without internet connectivity. ### Key Features: - **Knowledge Base**: Access to offline Wikipedia, medical references, eBooks, and more. - **AI Chat**: Local AI chat powered by Ollama or compatible software. - **Information Library**: Offline Wikipedia, medical references, eBooks, and more via Kiwix. - **Education Platform**: Khan Academy courses with progress tracking via Kolibri. - **Offline Maps**: Downloadable regional maps via ProtoMaps. - **Data Tools**: Encryption, encoding, and analysis via CyberChef. - **Notes**: Local note-taking via FlatNotes. ### Tech Stack: Project NOMAD is built on TypeScript, using a terminal-based installation process and a management UI (Command Center) and API. ### Why It Matters: Project NOMAD provides essential tools and resources for education and knowledge acquisition, ensuring users are always informed and empowered, regardless of network availability.

Go 40,316 stars

photoprism/photoprism

AI-Powered Photos App 🌈💎✨

### Overview: PhotoPrism is an AI-powered, privacy-first app designed to organize, browse, and share your photos and videos. It offers a seamless user experience, ensuring your pictures remain organized and accessible without compromising on freedom or functionality. ### Key Features: - **Browse All Your Pictures**: No worries about RAW images or video formats. - **Intuitive PWA**: Native app-like experience that can be easily installed on your home screen. - **Powerful Search Filters**: Combines and supports multiple properties for precise searches. - **Automatically Label Pictures**: Based on content and location, recognizing faces. - **Live Photos**: Start playing automatically when hovered over or viewed in slideshow. - **World Maps and Privacy-Preserving Geocoding**: Enhances trip memories and global exploration. - **Metadata Extraction and Merging**: Excludes Exif, XMP, and Google Photos metadata. - **Compatible Apps**: Supports PhotoSync for seamless iOS and Android phone backups. - **WebDAV Clients**: Connects to Microsoft Windows Explorer and Apple Finder for seamless integration. ### Tech Stack: Go ### Why It Matters: PhotoPrism is built with the mission of providing the most user-friendly and privacy-focused solution for organizing and accessing your photos. It ensures your pictures remain organized and accessible without compromising on freedom or functionality, making it a valuable tool for anyone looking to enhance their photo management experience.

Python 40,230 stars

anthropics/financial-services

Overview: Claude for Financial Services provides a suite of agents and vertical plugins tailored for financial services workflows such as investment banking, equity research, and wealth management. It can be installed as a Claude Cowork plugin or deployed through the Claude Managed Agents API. Key features: - Agents and vertical plugins for various financial services workflows - Self-contained agent plugins that bundle necessary skills and connectors - Deployment options through Claude Cowork and Managed Agents API Tech stack: Python Why it matters: It streamlines complex financial services workflows by automating tasks and providing comprehensive tools for analysts and professionals.

Python 40,196 stars

volcengine/OpenViking

Self-evolving Context Database for AI Agents. Unify Agent Memory, Knowledge RAG and Skills.

### Overview: OpenViking is a self-evolving context database designed for AI agents. It unifies agent memory, knowledge retrieval, and skills, providing a unified filesystem for storing, accessing, and modifying context. ### Key features: - **Unified Context Storage**: Agents can store, retrieve, and modify context data under a virtual filesystem named `viking://`. - **Agent Memory Management**: The database organizes context as a filesystem, allowing agents to navigate and manipulate it like files. - **Context Summary**: Each directory carries a summary, enabling agents to scan and decide what to read first. - **Integration with AI Agents**: Seamlessly integrates with various AI agent frameworks and systems. ### Tech stack: - Python ### Why it matters: OpenViking simplifies context management for AI agents, making it easier to manage and access context data, leading to more efficient and effective AI applications.

Python 40,190 stars

HKUDS/LightRAG

[EMNLP2025] LightRAG: Simple and Fast Retrieval-Augmented Generation

### Overview: LightRAG is a simple and fast retrieval-augmented generation model designed for efficient text completion tasks. It leverages existing knowledge to improve the quality of generated text, making it suitable for various applications such as language modeling and text completion. ### Key Features: - **Retrieval-Augmented Generation (RAG)**: LightRAG integrates a pre-trained language model with a knowledge graph to enhance the quality of generated text. - **Efficient Training**: Utilizes a lightweight architecture that requires minimal computational resources, making it suitable for real-time applications. - **Scalability**: Designed to scale well with large datasets, enabling efficient processing of large volumes of text data. ### Tech Stack: - **Python**: The primary programming language used for implementing the model. ### Why It Matters: LightRAG offers a balance between simplicity and effectiveness, making it an ideal choice for applications that require high-quality text generation while maintaining efficiency. Its ability to leverage existing knowledge through a knowledge graph ensures that the generated text is contextually relevant and coherent, enhancing user experience and application performance.

JavaScript 40,145 stars

github/awesome-copilot

Community-contributed instructions, agents, skills, and configurations to help you make the most of GitHub Copilot.

Overview: Awesome GitHub Copilot is a community-driven repository that provides a variety of custom agents, instructions, skills, and plugins to enhance the GitHub Copilot experience. It includes a website with full-text search and filtering capabilities, as well as a Learning Hub for guides and tutorials. Key features: - Community-contributed resources for GitHub Copilot - Comprehensive Learning Hub with guides and tutorials - Curated plugins and workflows for specific use cases Tech stack: JavaScript Why it matters: It significantly extends the functionality of GitHub Copilot by offering a wide range of custom integrations and configurations.

Python 40,039 stars

google-research/bert

TensorFlow code and pre-trained models for BERT

Overview: BERT is a pre-trained language model designed for various natural language processing tasks. It has been widely used in research and development. Key features: - 24 smaller BERT models available for download - Fine-tuned for knowledge distillation - GLUE scores: 64.2 for BERT-Tiny, 65.8 for BERT-Mini, 71.2 for BERT-Small, and 73.5 for BERT-Medium Tech stack: Python Why it matters: BERT models are essential for researchers and developers looking to improve their models with pre-training, especially in environments with limited computational resources.

TypeScript 40,010 stars

Yeachan-Heo/oh-my-claudecode

Teams-first Multi-agent orchestration for Claude Code

### Overview: Claude Code is a powerful AI platform designed for developers, offering a zero-learning curve approach to multi-agent orchestration. This project, `oh-my-claudecode`, simplifies the process of integrating Claude Code into your projects, allowing teams to easily collaborate and automate workflows without needing to understand the underlying code. ### Key Features: - **Zero Learning Curve**: Intuitive setup and seamless integration. - **Team Collaboration**: Facilitates efficient team communication and project management. - **Orchestration**: Streamlines the process of deploying and managing multiple Claude Code agents. - **Customization**: Allows for easy configuration and extension of the platform. ### Tech Stack: The project is built using TypeScript, ensuring robust and maintainable code. ### Why It Matters: Claude Code is a game-changer for developers, providing a simple yet powerful way to integrate AI into their projects. This project simplifies the process, making it accessible to a wider audience. With its focus on team collaboration and orchestration, it is ideal for any developer looking to enhance their workflow with AI tools. ### Repository: The repository is maintained by Yeachan Heo, with a high number of stars and a dedicated community of ambassadors and contributors. It is available on GitHub, where you can find the latest updates, documentation, and community support. ### Quick Start: To get started with `oh-my-claudecode`, follow these steps: 1. **Install via Marketplace**: ```bash /plugin marketplace add https://github.com/Yeachan-Heo/oh-my-cla

Python 39,914 stars

2noise/ChatTTS

A generative speech model for daily dialogue.

### Overview: ChatTTS is a generative speech model designed specifically for dialogue scenarios, optimized for natural and expressive speech synthesis. It supports multiple speakers and fine-grained control over prosodic features, surpassing most open-source TTS models in terms of prosody. ### Key features: - **Conversational TTS**: Optimized for dialogue-based tasks, enabling natural and expressive speech synthesis with multiple speakers. - **Fine-grained Control**: Predicts and controls fine-grained prosodic features such as laughter, pauses, and interjections. - **Better Prosody**: Slightly surpasses most open-source TTS models in terms of prosody. ### Tech stack: Python ### Why it matters: ChatTTS is designed specifically for dialogue scenarios, making it ideal for applications like language models as assistants. It supports multiple speakers and fine-grained control over prosodic features, enhancing the quality of speech synthesis.

Java 39,873 stars

YunaiV/ruoyi-vue-pro

🔥 官方推荐 🔥 RuoYi-Vue 全新 Pro 版本，优化重构所有功能。基于 Spring Boot + MyBatis Plus + Vue & Element 实现的后台管理系统 + 微信小程序，支持 RBAC 动态权限、数据权限、SaaS 多租户、Flowable 工作流、三方登录、支付、短信、商城、CRM、ERP、MES、IM、AI 大模型、IoT 物联网等功能。你的 ⭐️ Star ⭐️，是作者生发的动力！

Overview: RuoYi-Vue Pro is an open-source backend management system and mobile app framework based on Spring Boot, MyBatis Plus, and Vue.js. It supports various features such as RBAC dynamic permissions, SaaS multi-tenancy, and third-party integrations. Key features: - Supports RBAC dynamic permissions, data permissions, and SaaS multi-tenancy - Includes work flow management with Flowable - Provides third-party integrations like WeChat mini-programs, payment systems, and SMS services - Offers high-efficiency development with code generators for Java, Vue, and SQL Tech stack: Java, Spring Boot, MyBatis Plus, Vue.js Why it matters: The project's comprehensive feature set and open-source nature make it a valuable resource for developers building enterprise-level applications.

Go 39,598 stars

The-Vibe-Company/quivr

An open-source engine that turns continuous content streams into search and monitoring. Durable ingestion, hybrid search, alerts, and plugins for formats, models and business rules.

Overview: Quivr V2 is an open-source engine that converts continuous content streams into search and monitoring capabilities. It provides durable ingestion, hybrid search, alerts, and flexible plugin integration. Key features: - Durable ingestion - Hybrid search - Alerts - Flexible plugin integration Tech stack: Go Why it matters: Quivr V2 offers a robust and scalable solution for content monitoring and search, making it suitable for various domains and use cases. Repository: The-Vibe-Company/quivr GitHub stars: 39,598 GitHub description: An open-source engine that turns continuous content streams into search and monitoring. Durable ingestion, hybrid search, alerts, and plugins for formats, models, and business rules. The API is `v0` and may change without notice. Do not run it in production yet.