Tags: ai open source projects Page 7

General Introduction MoshiVis is an open source project developed by Kyutai Labs and hosted on GitHub. It is based on the Moshi speech-to-text model (7B parameters), with about 206 million new adaptation parameters and a frozen PaliGemma2 visual coder (400M parameters), allowing the model to use real-time speech...

General Introduction MiniMind is an open source project created by developer jingyaogong. Its core goal is to allow ordinary people to quickly train their own AI models.MiniMind's main feature is that it takes 2 hours to train a 26M parameter GPT model from scratch on a single NVIDIA 3090 graphics card....

General Introduction WritingBench is an open source project developed by the X-PLUG team and hosted on GitHub. It is a tool designed to test the writing ability of large models, providing 1239 real-world writing tasks. These tasks cover 6 major domains and 100 sub-domains , knot...

General Introduction Free-Search is an open source API tool developed by Hanzla Javaid and hosted on GitHub. Its main function is to provide real-time Google search results through a custom search engine and crawl web content to return structured data. This tool is designed for AI agents and large language...

General Introduction AI-ClothingTryOn is a Python-based open source desktop application created by developer speedTD and hosted on GitHub. It utilizes Google Gemini Artificial Intelligence technology to allow users to upload photos of people and pictures of clothes to generate virtual try-on effects. Users can...

General Introduction OpenDeepSearch is an open source search tool developed by the sentient-agi team. It combines Large Language Modeling (LLM) and Intelligent Reasoning Agents to allow users to search the web for information and get accurate answers in a simple way. The goal of this tool is to make search more open...

General Introduction Vibe Draw is an open source project developed by Martin Sit that allows users to turn hand-drawn sketches into beautiful 3D models. The goal of this tool is simple: to make 3D modeling easy for anyone, without the need for great artistic skills or complex software. It uses artificial intelligence tech...

General Introduction OAK (Open Agent Kit) is an open source tool to help developers quickly build, customize and deploy AI intelligences. It can connect to any Large Language Model (LLM), such as those from OpenAI, Google, or Anthropic, and also supports adding functionality via plugins.OAK was designed with a clear goal...

Comprehensive Introduction Flowgram.ai is an open source process building engine developed by ByteDance. It is based on node editing , to help developers quickly create workflows , support for fixed layout and free linking two modes . The project is written in TypeScript , the code is hosted on GitHub , open source and free ...

General Introduction Cursor Auto Register is an open source project hosted on GitHub. It was created by developer ddCat-main to help users automatically register and manage accounts for the Cursor AI code editor.Cursor is an artificial intelligence code editing tool, but a free trial account...

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 on March 26, 2025, and the code and model files tor...

General Introduction IndexTTS is an open source text-to-speech (TTS) tool hosted on GitHub and developed by the index-tts team. It is based on XTTS and Tortoise technologies, and provides efficient and high-quality speech synthesis through improved module design.IndexTTS uses tens of thousands of hours of...

Comprehensive introduction Dify-Plus is an AI application development platform based on the secondary development of the Dify open source project. It adds a new management center based on Dify and optimizes the functionality for enterprise scenarios. The project was initially for internal use by enterprises , and later found that the community has similar needs , then open source sharing.Dify-Pl...

General Introduction Rankify is an open source Python toolkit developed by the Data Science Group at the University of Innsbruck, Austria. It focuses on information retrieval, reordering and retrieval augmentation generation (RAG), providing a unified framework. The toolkit comes with 40 built-in pre-retrieved benchmark datasets and supports 7 retrieval techniques...

General 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 to enhance the quality of image and video generation by optimizing the guidance strategy and zero-initialization method....

General Introduction Bonsai is an open source language model developed by deepgrove-ai with a parameter size of 500 million, using ternary weights. It is designed based on the Llama architecture and the Mistral classifier, with linear layers adapted to support ternary weights. The model mainly uses DCLM ...

General Introduction Motia is an open source AI agent framework for software engineers, hosted on GitHub and developed by the MotiaDev team. It allows developers to quickly write, test, and deploy intelligent agents in familiar programming languages (e.g. Python, TypeScript, Ruby).The core of Motia...