AI open source project

KTransformers: A high-performance Python framework designed to break through the bottleneck of large model inference. It is not just a simple model running tool, but also a set of extreme performance optimization engine and flexible interface empowerment platform. KTransf...

Comprehensive Introduction CFG-Zero-star is an open source project developed by Weichen Fan and the S-Lab team at Nanyang Technological University. It focuses on improving the Classifier Free Guidance (CFG) technique in stream matching models by optimizing the guidance strategy and zero-initial ...

Comprehensive Introduction DeOldify is an open source project based on deep learning technology, specifically designed for intelligent colorization and restoration of black and white photos and videos. The project uses an innovative NoGAN training method to successfully solve the common defects of traditional GAN networks in the image coloring process...

Comprehensive Introduction FinGPT is an open source financial big language modeling platform developed by the AI4Finance Foundation, designed for the financial sector to solve complex financial tasks and drive innovation in fintech.FinGPT utilizes lightweight adaptation techniques and reinforcement learning approaches...

General Introduction SadTalker is an open source tool that combines a single still portrait photo with an audio file to create realistic talking avatar videos for a variety of scenarios such as personalized messages, educational content, and more. The revolutionary use of 3D modeling technologies such as ExpNet and PoseVA...

General Introduction n8n-mcp-server is an open source project hosted on GitHub and developed by Leonard Sellem. It is an MCP (Model Context Protocol) service tool specialized...

General Introduction OmniSQL is an open source project developed by the RUCKBReasoning team and hosted on GitHub. Its core function is to transform user-input natural language questions into high-quality SQL query statements to help users easily with the number of ...

Comprehensive Introduction AsrTools is an intelligent speech-to-text tool with built-in interfaces from big players such as Cutscene, Racer, Must Cut, etc. It does not require GPU or cumbersome configuration, and supports efficient multi-threaded batch processing. It is based on PyQt5 development, beautiful and user-friendly interface, able to output SRT and TXT format words...

General Introduction YTSage is a modern YouTube downloader with a clean PyQt6 interface. Users can use YTSage to download videos of any quality, extract audio, get subtitles (including auto-generated subtitles), and view the video's meta...

General Introduction Moffee is an open source tool that turns Markdown files into professional slideshows quickly, simply and efficiently. Users only need to write Markdown content, Moffee can automatically handle the layout, pagination and style, eliminating the need to manually typeset...

General Description Deep Chat is an open source AI chat component designed for web developers. It was developed by Ovidijus Parsiunas, is hosted on GitHub, and currently has over 2k stars. Users can simply configure...

General Introduction OrionChat is a web-based AI chat interface that provides users with a unified platform to interact with multiple mainstream AI models. The project supports a wide range of AI models including Ollama (running locally), OpenAI GPT, Google Gemi...

General Description AutoGen Studio 2.0 is a user interface powered by AutoGen designed to simplify the process of creating and managing multi-agent solutions. The platform enables users to declaratively define and modify agents and their workflows through an intuitive interface...

Comprehensive Introduction ConsisID is an open source project developed by Yuan Rong's group at Peking University, aiming to realize identity-consistent text-to-video generation (IPT2V) through frequency decomposition techniques. The core of the project is a DiT (Diffusion Transfor...

General Introduction Gemini Teacher is an English speaking practice assistant based on Google Gemini AI. It recognizes the user's English pronunciation in real time and provides instant feedback and correction suggestions. The tool is designed to help users improve their English speaking skills through...

Comprehensive Introduction GFPGAN (Generative Facial Prior GAN) is an open source face repair algorithm developed by Tencent ARC (Applied Research Center). The algorithm utilizes a pre-trained facial GAN...

General Introduction Spark-TTS is an open source Text-to-Speech (TTS) tool developed by the SparkAudio team, hosted on GitHub, designed to help users efficiently convert text into natural and fluent speech...

Comprehensive Introduction SemHash is a lightweight and flexible tool for de-duplicating datasets by semantic similarity. It combines the fast embedding generation of Model2Vec with the efficient ANN (approximate nearest neighbor) similarity search of Vicinity.SemHa...

General Introduction MobileAgent is a powerful mobile device operation assistant designed to improve the efficiency and automation of mobile device operation through multi-agent collaboration and enhanced visual perception modules. It is developed by X-PLUG team and supports Android and ...

General Introduction codemcp is an open source tool designed for Claude Desktop users, developed by Edward Z. Yang on GitHub. It makes Claude Desktop a useful...

General Introduction k8m is a lightweight, cross-platform Mini Kubernetes AI Dashboard designed to simplify cluster management. It is built on AMIS and is available through kom as a Kubernetes API guest...

Synthesis Muyan-TTS is an open source text-to-speech (TTS) model designed for podcasting scenarios. It is pre-trained with over 100,000 hours of podcast audio data and supports zero-sample speech synthesis to generate high-quality natural speech. The model is based on Llama-3.2-3...

Comprehensive Introduction VLM-R1 is an open source visual language modeling project developed by Om AI Lab and hosted on GitHub. The project is based on DeepSeek's R1 approach, combined with the Qwen2.5-VL model through reinforcement learning...

Comprehensive Introduction Easy Dataset is an open source tool designed specifically for fine-tuning large models (LLMs), hosted on GitHub. It provides an easy-to-use interface that allows users to upload files, automatically segment content, generate questions and answers, and ultimately output a suitable...

General Introduction Gemini Cursor is a desktop intelligent assistant based on Google's Gemini 2.0 Flash (experimental) model. It enables visual, auditory, and voice interactions through a multimodal API, providing real-time low-latency use...

General Introduction AiPy is an open source Python command-line tool developed by the Knownsec team. It combines the Large Language Model (LLM) and the Python runtime environment to allow users to automatically generate and run Pytho...

General Introduction MediaCrawler is a social media content crawler tool designed for developers. By providing a powerful crawler function, it can quickly grab videos, images, comments, likes, retweets and other data from social platforms such as Xiaohongshu, Shake, Shutter, B, Weibo and other...

Comprehensive Introduction UniAPI is an API forwarder compatible with the OpenAI protocol, and its core function is to manage APIs from multiple big model service providers through a unified OpenAI format, such as OpenAI, Azure OpenAI, Clau...

General Introduction Kolors Virtual Try-On is a virtual try-on app by the Kwai-Kolors team on the Hugging Face platform. The app utilizes advanced artificial intelligence technology to help users try on virtual...

General Introduction Sonic is an innovative platform focusing on global audio perception designed to generate vivid portrait animations driven by audio. Developed by a team of researchers from Tencent and Zhejiang University, the platform utilizes audio information to control facial expressions and head movements to generate natural and smooth animated videos.S...

General Introduction AI RSS is an innovative tool that converts web content into RSS feeds through AI technology. It consists of two main parts: a browser plugin and a server side. The browser plugin allows users to select lists from web pages and generate structured data description (SDD) files...

General Introduction Dia is an open source text-to-speech (TTS) model developed by Nari Labs that focuses on generating hyper-realistic dialog audio. It transforms text scripts into realistic multi-character dialog in a single process, supports emotion and intonation control, and even generates non-verbal representations...

General Introduction Zola is a free and open source AI chat application developed by developer Julien Thibeaut (GitHub username ibelick) and hosted on GitHub. Its best feature is that it supports multiple AI modes...

General Introduction olmOCR is an open source tool developed by the AllenNLP team at the Allen Institute for Artificial Intelligence (AI2) that focuses on converting PDF files...

General Introduction Genesis is a generative physics world designed for general purpose robotics and embodied AI learning. It provides a unified simulation platform that supports the simulation of a wide range of materials and physical phenomena.Genesis aims to unlock generative AI and physics simulation by combining...

General Introduction Open WebUI Artifacts Overhaul is a fork project based on Open WebUI, developed by developer Nick Tonjum. It is an open source tool focused on improving AI generated code...

Comprehensive Introduction Tencent Hunyuan3D (Hunyuan3D 2.0) is an advanced large-scale 3D synthesis system from Tencent designed to generate high-resolution textured 3D assets. The system consists of two core components: Hunyuan3D-DiT, a large-scale shape generation model, and Hunyuan3D-DiT, a large-scale texture...

General Introduction HyperChat is an open source chat client developed by BigSweetPotatoStudio, hosted on GitHub, and designed to provide a comprehensive overview of the BigSweetPotatoStudio language model by integrating APIs from several large language models (LLMs) such as OpenAI, Cla...

General Introduction LangGraph CodeAct is a framework open-sourced on GitHub by the LangChain AI team, based on the CodeAct architecture (see paper arXiv:2402.01030 for details). It does this by generating...

Comprehensive Introduction Kolors is a large-scale text-to-image generation model developed by the Racer team, based on potential diffusion techniques. The model is trained on billions of text-image data pairs, and is capable of generating high-quality, complex semantically accurate images with support for both Chinese and English input.Kolors in visual quality...

General Description Fullmoon is an application designed for iOS devices and aims to provide the ability to chat privately with native large language models. The app is optimized for Apple Silicon and is supported on iPhone, iPad and Mac. Users of the chat...

General Introduction The Gemini OpenAI API Agent is a free and server-maintenance-free OpenAI-compatible endpoint. Users can easily deploy it to platforms such as Vercel, Netlify and Cloudflare for personal use. The program ...

In the rapid development of the Internet today, download tools as an important means for users to obtain information and resources, plays an indispensable role. This article will systematically analyze five open source download tools: AB Download Manager, XDM (Xtreme Download ...

General Introduction SuperCoder is an intelligent tool that runs in the terminal and is designed for programmers. It utilizes AI technology to help users search for code, view project structure, edit files and fix bugs.The project is open sourced by huytd on GitHub and supports...

Comprehensive Introduction PocketFlow is a lightweight AI application development framework with only 100 lines of code, developed by The-Pocket team and open-sourced on GitHub. It pursues a minimalist design , the core code control in 100 lines , no external dependencies ...

General Introduction Cognee is a reliable data layer solution designed for AI applications and AI agents. Designed to load and build LLM (Large Language Model) contexts to create accurate and interpretable AI solutions through knowledge graphs and vector stores. The framework favors cost-saving, interpretable...

General Introduction Anubis is an open source tool developed by the TecharoHQ team to protect websites from AI crawlers. It adds a SHA256 Proof-of-Work challenge to the HTTP request...

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...

General Introduction MCP Containers is an open source project, hosted on GitHub, focused on providing containerized solutions for Model Context Protocol (MCP) servers. It simplifies through Docker containers...

General Description Whisper Input is an open source voice transcription tool that allows users to start recording voice by pressing the Option button and end the recording by lifting the button. The tool calls Groq Whisper Large V3 Turbo ...

Comprehensive Introduction WeChatAI is a Python-based WeChat group chat and personal intelligent assistant, supporting a variety of large language models (such as DeepSeek, Gemini, Tongyi Thousand Questions), which can realize intelligent conversations, auto-replies and other functions. The project uses modern ...

Comprehensive Introduction Agent TARS is a multimodal AI intelligence open-sourced by ByteDance.The core feature is to visually understand web content and combine command line and file system operations to help users complete complex computer tasks. Instead of requiring manual operations like traditional tools, it can self...

General Introduction YOLOE is an open source project developed by the Multimedia Intelligence Group (THU-MIG) at Tsinghua University School of Software, with the full name "You Only Look Once Eye". It is based on the PyTorch framework, which belongs to the YOLO series of extensions ...

General Introduction Fabric is an open source AI framework developed by Daniel Miessler to simplify and automate everyday computer tasks and make artificial intelligence easier to use. It helps users efficiently through modular design and preset prompt words (Patterns)...

Comprehensive Introduction Tencent Mixed Yuan Text Generation Video (available in Yuanbao APP) is a video generation platform based on AI technology launched by Tencent. The platform utilizes the Tencent Mixed Yuan Big Model with powerful cross-domain knowledge and natural language understanding to generate high-quality videos based on users' text descriptions...

Comprehensive Introduction Leffa is a unified framework for generating controllable character images, enabling precise manipulation of character appearance (e.g., virtual fitting) and pose (e.g., pose transfer). The framework significantly reduces distortion of fine-grained details by directing the target query to focus on the correct reference key in the attention layer, with ...

General Introduction WhisperChain is an AI-based open source project hosted on GitHub and led by developer Chris Choy. It is mainly used to convert speech into text and automatically optimize the expression through AI technology to remove redundancy...

Comprehensive Introduction AutoGen is an open source framework developed by a team of Microsoft researchers focused on simplifying the building of large language model (LLM) applications through multi-intelligent body conversations. It allows developers to create AI agents that can talk to each other and collaborate to solve tasks. This approach not only improves the performance of LLM...

Comprehensive Introduction NarratoAI is a fully automated tool that integrates movie and TV narration, automated editing, dubbing and subtitle generation. It relies on large-scale language modeling (LLM) technology to automatically generate copy and automatically edit videos with corresponding voiceovers and subtitles, providing users with a one-stop...

General Introduction ACE++ is an open source project developed by the ali-vilab team at Alibaba Tongyi Lab (Tongyi Lab). It is based on the FLUX.1-Fill-dev model and aims to achieve image generation and compilation through simple textual commands...

General Introduction Screenshot-to-Code is an open source tool that utilizes artificial intelligence to convert screenshots, design drafts, and Figma designs into clean, functional code. The tool supports multiple front-end technology stacks, including HTML, Tailwind CS...

General Introduction DiffPortrait360 is an open source project affiliated with the CVPR 2025 paper "DiffPortrait360: Consistent Portrait Diffusion for 360...

General Introduction Flashcard is an open source language learning tool designed to provide an alternative to Duolingo. Developed by Steven Lynn (GitHub username: stvlynn), the project features a modern user interface and multilingual...

General Introduction MathTranslate is an online tool specialized in translating LaTeX documents, especially for scientific papers. The tool is able to keep LaTeX expressions (e.g. mathematical expressions) unchanged and finally compiles LaTeX documents into...

Comprehensive Introduction Qwen2.5-Omni is an open source multimodal AI model developed by Alibaba Cloud Qwen team. It can process multiple inputs such as text, images, audio and video, and generate text or natural speech responses in real time. The model was released in 2025 on 3 ...

General Introduction MiMo is an open source large language modeling project developed by Xiaomi, focusing on mathematical reasoning and code generation. The core product is the MiMo-7B family of models, which contains a base model (Base), a supervised fine-tuning model (SFT), a strong chemical trained from the base model...

General Introduction Trackers is an open source Python tool library focused on multi-object tracking in video. It integrates several leading tracking algorithms, such as SORT and DeepSORT, and allows users to combine different object detection models (such as YOLO...

General Introduction Local Deep Research is an open source AI research assistant designed to help users conduct deep research and generate detailed reports for complex problems. It supports local operation, allowing users to accomplish research tasks without relying on cloud services. The tool ...

General Description AI Auto Free is a powerful automation tool designed to help users make unlimited use of AI-driven Integrated Development Environments (IDEs) such as Cursor and Windsurf. The program offers cross-platform support and includes multiple language capabilities...

General Introduction CoAI.Dev (formerly Chat Nio) is a chat platform that integrates multiple AI models and supports distributed streaming, image generation, cross-device conversation synchronization and sharing. It implements a subscription and Token billing system, Key transit service and multi...

Comprehensive Introduction Qwen-Agent is an intelligent agent application framework developed based on Qwen 2.0 and above, with capabilities such as command following, tool usage, planning and memorization. The framework provides a variety of sample applications such as browser assistants, code interpreters and custom assistants...

General Introduction AI ContentCraft is a versatile content creation tool that integrates text generation, speech synthesis, image generation and more. It helps creators quickly generate stories, podcast scripts, and accompanying audio and video content. The tool supports multiple language conversions and can batch...

Comprehensive Introduction WeChat Markdown Editor (WeChat Markdown Editor) is a highly concise WeChat graphic layout tool designed to help users easily create beautiful WeChat posts. The editor supports all basic Markdown ...

General Description AnkiAIUtils is a set of AI-enhanced tools designed for the Anki flashcard learning system. Developed by a medical student, the tool is designed to automatically improve cards that users are struggling with during the learning process through AI technology. It can intelligently provide users with personalized...

General Introduction Eko is a production-grade JavaScript framework designed to build efficient intelligent agent workflows through natural language descriptions. It is designed to enable developers to automate everyday tasks using AI technologies without deep programming.Eko provides a uni...

General Introduction Morphik Core is an open source project developed by the morphik-org team and hosted on GitHub. It used to be called DataBridge Core, but is now renamed Morphik Core.This...

Comprehensive Introduction CogAgent is an open source visual language model developed by Tsinghua University Data Mining Research Group (THUDM), aiming to automate the operation of cross-platform graphical user interface (GUI). The model is based on CogVLM (GLM-4V-9B) and supports bilingual Chinese and English...

Comprehensive Introduction DeepClaude is a high-performance Large Language Model (LLM) inference API and chat interface that integrates the chained inference (CoT) capabilities of DeepSeek R1 with the creativity and code generation of the Anthropic Claude model...

General Introduction X-Kit is an open source tool designed to crawl and analyze X (formerly Twitter) user data and tweets. Developed by GitHub user xiaoxiunique, the tool is designed to help users automate the process of obtaining basic information and tweets about a given X user and...

The goal of table recognition is to parse tables in images, accurately identify table structures and cell locations, and reduce them to structured table formats (e.g., HTML). In today's information age, a large amount of important tabular data still exists in an unstructured state (e.g., scanned documents with pictures of statistical tables...).

Comprehensive Introduction Klavis AI is an open source platform focused on simplifying the use and integration of the Model Context Protocol (MCP), an open standard that allows AI applications to dynamically connect with external tools and data sources.Klavis AI provides Slack...

General Introduction LogoCreator is an open source Logo generator based on Together AI and Flux model, focusing on providing fast and professional Logo design services for businesses and individuals. The project is developed and open-sourced by developer Nutlope in Git...

General Introduction TinyZero is a veRL-based reinforcement learning model designed to replicate the performance of DeepSeeK-R1 Zero in countdown and multiplication tasks. Surprisingly, the project costs only $30 to run (using 2xH2...

General Introduction DiffSynth-Engine is an open source project launched by ModelScope, hosted on GitHub.It is based on diffusion modeling technology, focusing on efficiently generating images and videos, suitable for developers to deploy AI models in production environments ...

Comprehensive Introduction Baichuan-Audio is an open source project developed by Baichuan Intelligence (baichuan-inc), hosted on GitHub, focusing on end-to-end voice interaction technology. The project provides a complete audio processing framework that enables speech ...

Comprehensive Introduction TxAgent is an open-source AI tool developed by Harvard University's Medical and Scientific Artificial Intelligence Team (MIMS) to help physicians analyze drug interactions and develop personalized treatment plans. It combines patient-specific situations through multi-step reasoning and real-time retrieval of biomedical knowledge...

Comprehensive Introduction Metaverse AI (open source version) is a project hosted on GitHub, developed by libn-net team. It can clone digital human images and voices through AI technology to generate short videos, and also supports dubbing and subtitling. This tool provides Windo...

General Introduction multi-model-bolt.new is a modified version of Bolt.new that allows the use of TogetherAI models, supporting features such as deployment, mobile response and voice input. Users can be prompted directly in the browser, run...

General Introduction RapBank is a dataset and toolset designed for rap lyrics generation. The project was created by NZqian to provide researchers and developers with a high-quality rap lyrics data by collecting and processing rap songs from YouTube...

General Introduction FlowDown-App is a lightweight and efficient AI conversation client, developed by a team of developers using Swift and UIKit, aiming to provide users with a fast and smooth intelligent conversation experience. The app is divided into a standard version (FlowDown...

General Introduction Yutu is a powerful open source command line tool designed for YouTube users, hosted on GitHub and developed by the eat-pray-ai team. It uses terminal operations to realize the YouTube videos, playlists, frequency...

General Introduction AIDE (AI-assisted Development Extension) is a powerful VSCode AI-assisted development extension, focusing on providing unique and practical AI programming assistance. It is different from GitHu...

General Introduction Cursor Talk to Figma MCP is an open source project that connects the AI programming tool Cursor with the design software Figm...

General Introduction Hugging Face's Open R1 project is a fully open-source DeepSeek-R1 replication project designed to build the missing parts of the R1 pipeline so that everyone can replicate and build upon them. The project is designed to be simple and consists mainly of training and evaluating...

General Introduction Search-R1 is an open source project, developed by PeterGriffinJin on GitHub, built on the veRL framework. It trains Large Language Models (LLMs) through Reinforcement Learning (RL) techniques, allowing the models to autonomously learn...

General Introduction Neural4D is an innovative AI-based platform focused on helping users quickly generate high-quality 3D models and animations with simple text or image input. Developed by DreamTech, it relies on the world's leading end-to-end 3D generation of large models technology...

General Introduction code2prompt is an open source command line tool, created and hosted on GitHub by developer Mufeed VH, designed to help users quickly convert entire code bases into prompts suitable for the Large Language Model (LLM) (prompt...

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...

General Introduction openapi-mcp-server is an open source tool designed to transform OpenAPI v3.1 compliant APIs into AI usable resources. It is maintained by janwilmake and is based on Model Contex...