AI open source project

Total 1020 articles posts
Devika:开源的AI软件工程师智能体,能够理解、拆分指令为子任务并编写代码

Devika: open-source AI software engineer intelligence that understands, splits instructions into subtasks and writes code

General Introduction Devika is an advanced AI software engineer that understands high-level human instructions, breaks them down into steps, studies the relevant information, and writes code to achieve a given goal. It intelligently develops software using large-scale language models, planning and reasoning algorithms, and web browsing capabilities.D...
5mos ago
03.3K
EXO:利用闲置家用设备运行分布式AI集群,支持多种推理引擎和自动设备发现。

EXO: Running distributed AI clusters using idle home devices with support for multiple inference engines and automated device discovery.

General Introduction Exo is an open source project designed to run its own AI cluster using everyday devices (e.g. iPhone, iPad, Android, Mac, Linux, etc.). Through dynamic model partitioning and automated device discovery, Exo is able to unify multiple devices into one powerful...
9mos ago
05.6K
Ant Design X:快速构建AI聊天界面的工具包,支持模型集成和数据流管理。

Ant Design X: A toolkit for rapidly building AI chat interfaces with support for model integration and data flow management.

Comprehensive Introduction Ant Design X is a toolkit open-sourced by Ant Group, designed to help developers quickly build AI-driven dialog interfaces. It provides a rich set of components and templates, supports model integration compatible with OpenAI standards, and is suitable for a variety of applications such as intelligent customer service, AI assistants, and other...
9mos ago
03.5K
NVIDIA Garak:检测LLM漏洞的开源工具,确保生成式AI的安全性

NVIDIA Garak: Open-source tool to detect LLM vulnerabilities and secure generative AI

Comprehensive Introduction NVIDIA Garak is an open source tool that specializes in detecting vulnerabilities in Large Language Models (LLMs). It checks the model for multiple weaknesses such as illusions, data leakage, hint injection, error message generation, harmful content generation, etc. through static, dynamic and adaptive probing...
9mos ago
02.7K
Dynamiq:智能体编排框架,支持RAG和LLM代理,简化AI应用开发

Dynamiq: Intelligent Body Orchestration Framework with RAG and LLM Agent Support to Simplify AI Application Development

Comprehensive Introduction Dynamiq is an open source AI orchestration framework designed for agent AI and Large Language Model (LLM) applications. It is designed to simplify the development of AI-driven applications, especially in the area of Retrieval Augmented Generation (RAG) and the orchestration of LLM agents.Dynamiq proposes...
9mos ago
03.7K
Moondream:批量反推图像提示词的开源轻量级视觉语言模型

Moondream: an open source lightweight visual language model for batch backpropagation of image cue words

Comprehensive Introduction Moondream is an open source lightweight visual language model designed to enable image description capabilities through deep learning and computer vision techniques. The model is able to run efficiently on a variety of platforms and is particularly suitable for edge devices.Moondream uses advanced techniques and...
7mos ago
03K
Sana:快速生成高分辨率图像,0.6B超小尺寸模型,低配笔记本GPU运行

Sana: fast generation of high-resolution images, 0.6B ultra-small size model, low-profile laptop GPU operation

General Introduction Sana is an efficient high-resolution image generation framework developed by NVIDIA Labs, capable of generating images up to 4096 × 4096 resolution in a matter of seconds.Sana utilizes a linear diffusion transformer and deep compression self-encoder technology to significantly...
9mos ago
03.2K
SP-MangaEditer:专业四格漫画插图创作工具,生成图像、编辑漫画页面

SP-MangaEditer: Professional four-panel manga illustration creation tool, generating images, editing manga pages

General Introduction SP-MangaEditer is an independent manga editing platform designed for manga creators. The platform supports image generation, layer editing, image adjustment, filter application and many other functions to help users easily create high-quality manga illustrations. Users can simply manipulate...
7mos ago
03.1K
PDFMathTranslate:保留PDF完整排版的AI翻译工具

PDFMathTranslate: AI translation tool that preserves the full typography of PDFs

Comprehensive introduction PDFMathTranslate is an open source tool focusing on the translation of scientific papers , PDF documents can be translated in full and generate a bilingual version . It uses AI technology to retain the full layout of the original document , including formulas , diagrams , tables of contents and notes , support ...
2mos ago
04.8K
Linly-Dubbing:智能视频多语言AI配音/翻译工具

Linly-Dubbing: Intelligent Video Multilingual AI Dubbing/Translation Tool

Comprehensive Introduction Linly-Dubbing is an intelligent multilingual AI dubbing and translation tool designed to provide users with high-quality multilingual video dubbing and subtitle translation services by integrating advanced AI technology. The tool is especially suitable for international education, global content localization and other scenarios, helping...
7mos ago
03.3K
Maxun:开源无代码平台,自动抓取网页数据并转换为API或电子表格

Maxun: open source no-code platform that automatically crawls web data and converts it to APIs or spreadsheets

Comprehensive Introduction Maxun is an open source no-code web data extraction platform that allows users to train robots in minutes to automatically crawl web data and convert it into APIs or spreadsheets. The platform supports paging and scrolling, can adapt to changes in website layout, provides powerful data crawling...
7mos ago
03.7K
Swarm:学习轻量级多智能体系统的实验性教学项目(OpenAI示例)

Swarm: an experimental pedagogical program for learning lightweight multi-intelligent body systems (OpenAI example)

General Introduction Swarm is an experimental educational framework developed by OpenAI to explore lightweight, controlled, and easy-to-test interfaces for multi-agent systems. The framework is primarily used to demonstrate handoffs and routine patterns between agents to help developers understand and implement the coordination and execution of multi-agent systems...
7mos ago
03K
EchoMimic:音频驱动人像照片生成说话视频(EchoMimicV2加速版安装包)

EchoMimic: Audio-driven portrait photos to generate talking videos (EchoMimicV2 accelerated installer)

General Introduction EchoMimic is an open source project designed to generate realistic portrait animations through audio-driven generation. Developed by Ant Group's Terminal Technologies division, the project utilizes editable marker point conditions to generate dynamic portrait videos using a combination of audio and facial marker points.EchoMimic...
7mos ago
03.3K
Danswer: 专注企业知识管理与文档搜索的AI助手,集成多种工作工具

Danswer: AI assistant specializing in enterprise knowledge management and document search, integrating multiple work tools

General Introduction Danswer is an open source enterprise document retrieval AI assistant designed to connect to team documents, applications and people to provide unified search and natural language query answers through an intelligent chat interface and unified search capabilities. Ensuring that user data and chats are fully controlled...
5mos ago
03.5K
DocsGPT:文档聊天助手,从单个文档、网站来源获取可靠的答案,支持本地部署

DocsGPT: Document Chat Assistant, get reliable answers from single documents, web sources, support local deployment

General Introduction DocsGPT is an open source documentation assistant designed to simplify the process of querying project documentation. By integrating a powerful GPT model , developers can easily ask questions about the project and get accurate answers.DocsGPT supports local deployment to ensure data privacy while...
9mos ago
03.3K
InstantIR:受损图像修复与图像高清放大开源项目,最低16G显存

InstantIR: damaged image repair and image high-definition zoom open source project, minimum 16G video memory

General Description InstantIR is an innovative single-image restoration model developed by the InstantX team, designed to resurrect your damaged images with extremely high-quality and realistic details, capable of high-quality restoration of damaged images. The tool not only restores the details of the image...
9mos ago
03.7K
OmniParse:从文档/多媒体中提取任何非结构化数据解析为结构化数据

OmniParse: extract any unstructured data from documents/multimedia and parse it into structured data

Comprehensive Introduction OmniParse is a powerful data parsing and optimization platform designed to convert any unstructured data into structured, actionable data optimized for GenAI (Generative Artificial Intelligence) framework. Whether you are working with documents, tables, images, videos, audio files or...
9mos ago
02.9K
tldraw:开源无限画布白板SDK,AI生成简约线框图和UML图

tldraw: open source unlimited canvas whiteboard SDK, AI to generate minimalist wireframe diagrams and UML diagrams

General Description tldraw is a free and instant collaborative drawing tool that provides an unlimited canvas where users can quickly draw graphics, write text and collaborate instantly. Featuring an intuitive interface and excellent performance, it is suitable for team collaboration and remote work. Supported through the open source community, tldr...
9mos ago
02.9K
RD-Agent:自动化数据驱动研发工具,通过AI技术推动以数据为导向的研发过程

RD-Agent: an automated data-driven R&D tool to drive data-driven R&D processes through AI technology

Comprehensive Introduction RD-Agent is an open source tool from Microsoft designed to automate and optimize the research and development (R&D) process. The tool focuses on data-driven scenarios to improve the efficiency of model and data development through artificial intelligence techniques.RD-Agent integrates research...
5mos ago
04.1K
VideoChat:自定义形象和音色克隆的实时语音交互数字人,支持端到端语音方案和级联方案

VideoChat: real-time voice-interactive digital person with customized image and tone cloning, supporting end-to-end voice solutions and cascading solutions

Comprehensive Introduction VideoChat is a real-time voice interaction digital person project based on open source technology, supporting both end-to-end voice schemes (GLM-4-Voice - THG) and cascade schemes (ASR-LLM-TTS-THG). The project allows users to customize the digital ...
9mos ago
02.9K
Aggregator:一站式代理爬取与聚合平台,免费代理池(请合规使用)

Aggregator: one-stop agent crawling and aggregation platform, free agent pool (please use in compliance)

Comprehensive introduction Aggregator is an open source project aimed at creating a free proxy pool that can crawl a variety of available proxy nodes. The platform has a flexible plug-in system , the user can according to the special needs of the target site , through plug-ins to achieve specific functions . The project is mainly used to learn to crawl ...
9mos ago
02.9K
Perplexica:1比1复刻 Perplexity AI 功能和界面的开源AI搜索引擎

Perplexica: an open source AI search engine that replicates Perplexity AI's features and interface 1 to 1

Comprehensive Introduction Perplexica is an open source AI-driven search engine designed to provide answers that delve deep into the Internet. It uses advanced machine learning algorithms, such as similarity search and embedding techniques, to optimize search results and provide clear answers with cited sources.Perple...
9mos ago
03.3K
AppAgent:利用多模态智能体自动操作智能手机

AppAgent: automated smartphone operation using multimodal intelligences

Comprehensive Introduction AppAgent is a large language model (LLM)-based multimodal agent framework designed to manipulate smartphone applications. The framework mimics human interactions such as taps and swipes through a simplified manipulation space, thus eliminating the need for system back-end access and extending its use across different app...
8mos ago
03.4K
AI Podcast Generator:自动抓取新闻生成音频播客

AI Podcast Generator: Automatically Capturing News to Generate Audio Podcasts

General Introduction AI Podcast Generator is an intelligent podcast generation tool that utilizes advanced AI technology to automatically create engaging audio content from web sources. The system generates natural flowing narratives by capturing news content and converting it into audio podcasts. The project is based on Next...
9mos ago
03.3K
OpenBB:开源金融数据分析平台,集成私有数据集和 AI 来增强投资决策

OpenBB: Open Source Financial Data Analytics Platform Integrates Private Datasets and AI to Enhance Investment Decisions

General Introduction OpenBB is a free and fully open source financial data analytics platform designed to provide easy access to financial data and analytics tools for all. The platform integrates over 100 different data sources covering stocks, options, cryptocurrencies, forex, macroeconomic indicators, fixed...
7mos ago
04.4K
CR-Mentor:知识库+LLM 驱动的GitHub智能代码审查导师

CR-Mentor: Knowledge Base + LLM Driven Intelligent Code Review Mentor for GitHub

Comprehensive Introduction CR-Mentor is an intelligent code review tool that combines a specialized knowledge base with the power of Large Language Modeling (LLM). It not only supports code review for all programming languages, but also customizes exclusive review criteria and focus areas for teams based on best practices accumulated in the knowledge base. Through...
9mos ago
03.1K
muAgent:由 LLM 和 EKG(行业知识)驱动的全新Agent编排框架

muAgent: A New Agent Orchestration Framework Driven by LLM and EKG (Industry Knowledge)

General Introduction muAgent is an innovative multi-intelligentsia framework developed by Ant Group. The framework collaborates with multi-intelligentsia, function calls, code interpreters and other technologies through canvas drag-and-drop and simple text writing to help users execute various complex standard operating procedures (SOPs) under human guidance...
9mos ago
02.8K
99AI:集成多模态AI服务的商业化Web应用(免费开源)

99AI: A commercialized web application integrating multimodal AI services (free and open source)

Comprehensive Introduction 99AI is an open source AI web application project that aims to provide an easy-to-deploy, low-threshold integrated AI service platform. The project supports intelligent dialog, multimodal modeling, application plaza, networked search, and integrates AI painting, music and video...
9mos ago
03.3K
PantoMatrix(EMAGE):全身手势生成框架,从音频生成全身手势的3D动画框架

PantoMatrix (EMAGE): full-body gesture generation framework, 3D animation framework for generating full-body gestures from audio

Comprehensive Introduction PantoMatrix is an advanced full-body gesture generation framework capable of generating complete human movements from audio and partial gestures, including face, partial body, hand and full-body movements. The framework utilizes the latest multimodal datasets and deep learning techniques to provide high-quality 3D...
9mos ago
03.2K
AigoTools:自动收录网站并支持多语言的开源AI工具导航站

AigoTools: automatic inclusion of the site and support for multilingual open source AI tools navigation station

General Introduction AigoTools is an open source AI web site navigation designed to help users quickly create and manage navigation sites. It has built-in site management and AI-based auto-inclusion features , support for multi-language , dark/light theme switching , and SEO optimization.AigoTools proposes ...
10mos ago
02.9K
MindSearch:开源AI搜索引擎框架,部署您自己的 Perplexity 搜索引擎!

MindSearch: open source AI search engine framework to deploy your own Perplexity search engine!

Comprehensive Introduction MindSearch is an open source AI search engine framework launched by Shanghai Artificial Intelligence Laboratory (SAL), aiming to simulate human thought process for complex information gathering and integration. The tool combines the advanced technology of large-scale language modeling (LLM) and search engine through multi-intelligence...
8mos ago
02.9K
CosyVoice:阿里推出的3秒急速语音克隆开源项目,支持情感控制标签

CosyVoice: 3-second rush voice cloning open source project launched by Ali with support for emotionally controlled tags

Comprehensive Introduction CosyVoice is a multilingual large-scale speech generation model that provides full-stack capabilities from inference, training to deployment. Developed by the FunAudioLLM team, it aims to achieve high quality speech through advanced autoregressive transformers and ODE-based diffusion models...
6mos ago
06.3K
Pyramid Flow:快手推出的开源版

Pyramid Flow: an open source version of "Kringle" launched by Racer, based on SD3 and running on GPUs of less than 8GB (one-click deployment version)

Comprehensive Introduction Pyramid Flow is an efficient autoregressive video generation method based on the Flow Matching technique. The method achieves higher computational efficiency in generating and decompressing video content by interpolating between different resolutions and noise levels...
9mos ago
02.9K
Dify:生成式AI应用开发平台,可视化编排, 支持私有化部署

Dify: generative AI application development platform, visual orchestration, private deployment support

Comprehensive Introduction Dify is an open source generative AI application development platform designed to help developers rapidly build and operate native AI applications based on Large Language Models (LLMs). The platform provides everything from Agent building to AI workflow orchestration, RAG retrieval...
7mos ago
04.3K