Moshi: a real-time speech dialog framework with support for multiple languages and accents for speech dialog base models
综合介绍 Moshi Chat 是由法国非营利性AI实验室 Kyutai 推出的一款端到端实时AI语音助手。它不仅可以实时收听，还能进行自然对话，支持多模态交互，包括看、听、说的能力。Moshi Ch...
Sorting
QAnything: Local Knowledge Base Q&A System with Highly Integrated RAG Processing Flow
QAnything Comprehensive Introduction QAnything (Question and Answer based on Anything) is a local knowledge base Q&A system launched by NetEase, which supports all kinds of file formats and databases, and can be installed and used offline....
VoiceCraft: open source zero-sample speech cloning and text-to-speech tool
综合介绍 VoiceCraft是一个开源的语音编辑和零样本语音合成工具，基于神经编解码器语言模型。它采用了创新的编码序列生成方法，能够在已有语音序列上进行插入、删除和替换操作，生成自然、连贯的编辑语音...
OpenCharacter: open source uncensored Character.AI alternative
综合介绍 OpenCharacter是一个开源的角色创建工具，旨在为用户提供无过滤、无限制的AI角色创建与互动体验，作为Character.AI替代方案。用户可以使用本地模型创建和运行自己的角色，或者...
PDF to Podcast: Convert PDF to Podcast Utility
综合介绍 受 Notebook LM 的播客生成特性和最近的 Open Notebook LM 开源实现的启发。在本食谱中，我们将实现一个关于如何构建 PDF 到播客管道的详细步骤。 给定任何 PDF...
Unstructured: open source preprocessing unstructured documents, unstructured data processing tools
综合介绍 Unstructured-IO 提供了一系列开源组件，用于处理和预处理图像和文本文档，如 PDF、HTML、Word 文档等。其主要目标是简化和优化数据处理工作流程，特别是为大语言模型（LL...
Zed: A High-Performance Multi-Player Collaborative Code Editor for Rust
综合介绍 Zed 是由 Atom 和 Tree-sitter 的创造者开发的一款高性能、多用户协作的代码编辑器。Zed 采用 Rust 语言编写，旨在提供快速、流畅的编码体验。其主要特点包括支持多人实...
InvSR: Open source image super-resolution project to improve the quality of image resolution
General Introduction InvSR is an innovative open-source image super-resolution project based on diffusion inversion techniques capable of converting low-resolution images into high-quality, high-resolution images. The project utilizes the rich a priori knowledge of images embedded in pre-trained large-scale diffusion models to support, through a flexible sampling mechanism, the...
Easy Voice Toolkit: AI Voice Toolkit for Local Deployment
综合介绍 Easy-Voice-Toolkit 是一个基于开源语音项目的多功能工具箱，提供语音识别、语音转录、语音转换、数据集创建和模型训练等多种自动化音频工具。用户可以根据需要选择性地使用这些工具...
Sana: fast generation of high-resolution images, 0.6B ultra-small size model, low-profile laptop GPU operation
综合介绍 Sana 是由 NVIDIA 实验室开发的一种高效高分辨率图像生成框架，能够在几秒钟内生成最高 4096 × 4096 分辨率的图像。Sana 采用线性扩散变换器和深度压缩自编码器技术，显著...
FlowiseAI: Building a Node Drag-and-Drop Interface for Custom LLM Applications
General Introduction FlowiseAI is an open source, low-code tool designed to help developers build custom LLM (Large Language Model) applications and AI agents. With a simple drag-and-drop interface, users can quickly create and iterate on LLM applications, making the process from testing to production more efficient...
CrewAI: A Multi-Roleplay Collaborative Intelligence Framework to Simplify Complex Tasks
Comprehensive Introduction CrewAI is an advanced framework designed to orchestrate collaboration between role-playing and autonomous AI agents. By facilitating collaborative intelligence, CrewAI enables agents to work together seamlessly to solve complex tasks. Whether you're building an intelligent assistant platform, automating customer service teams, or multi-agent...
MindSearch: open source AI search engine framework to deploy your own Perplexity search engine!
综合介绍 MindSearch是由上海人工智能实验室推出的一款开源AI搜索引擎框架，旨在模拟人类的思维过程进行复杂信息搜集与整合。该工具结合了大规模语言模型（LLM）与搜索引擎的先进技术，通过多智能体...
Tencent Hybrid 3D (Hunyuan3D): Generate high-resolution 3D assets, multiple 3D material generation workflows
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...
Ultravox: an audio multimodal macromodel for real-time end-to-end voice dialog, an open source implementation of GPT-4o voice interaction
综合介绍 Ultravox是一个创新的多模态大语言模型（LLM），专为实时语音处理而设计。与传统的语音识别系统不同，Ultravox无需单独的音频语音识别（ASR）阶段，能够直接将音频转换为高维空间中...
PromptWizard: an open source framework for optimizing prompt projects to improve task performance
综合介绍 PromptWizard是微软开发的一个开源框架，采用自我进化机制，可以让模型自己生成、评价和改进提示词及生成示例，通过不断反馈来提高输出质量。它能够自主优化提示词、生成和选择合适的示例、并...
ChatGPT-on-WeChat: an intelligent dialog bot built on a large model, supporting WeChat and other multi-dialog platform access
综合介绍 ChatGPT-on-WeChat项目是一个基于大模型的智能对话机器人，支持个人微信、微信公众号、企业微信应用、飞书、钉钉等多平台接入。用户可以选择GPT3.5、GPT-4、Claude、文...
NocoDB: Creating Smart Tables on Multiple Databases, Open Source Airtable Alternative
综合介绍 NocoDB 是一个开源的Airtable替代方案，旨在提供一个强大且易于使用的在线数据库管理工具。通过NocoDB，用户可以轻松创建、读取、更新和删除数据库中的数据，无需编写代码。该平台支...
Llama OCR: OCR library that converts images to Markdown in three lines of code using the free Llama 3.2 Vision interface
General Introduction Llama OCR is an OCR (Optical Character Recognition) library based on Llama 3.2 Vision that converts documents to Markdown format. The library was developed by Nutlope and uses Together...
English 
简体中文 
日本語 
한국어 
Español 
Deutsch 
Français 
Português do Brasil