AI open source project

Comprehensive Introduction Tifa-DeepsexV2-7b-MGRPO-GGUF-Q4 is an efficient language model designed to support complex role-playing and multi-round conversations. Deeply optimized based on Qwen 2.5-7B, it has excellent text generation and dialogue...

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...

综合介绍 ComfyUI-disty-Flow 是一个为 ComfyUI 提供用户友好界面的自定义节点。它旨在通过提供替代用户界面来简化工作流程的运行，而不是替代工作流程的创建。ComfyUI-dis...

综合介绍 MiniRAG是一个极其简单的检索增强生成（RAG）框架，旨在通过异构图索引和轻量级拓扑增强检索，使小模型也能实现良好的RAG性能。该项目由香港大学数据科学实验室（HKUDS）开发，主要解决...

综合介绍 H2O GPT 是一个开源项目，旨在提供私有化的聊天和文档处理功能。该项目基于 Apache 2.0 许可证，支持多种 GPT 模型，包括 LLaMa2、Mistral、Falcon 等。用...

综合介绍 Claude Engineer 是一个由 Doriandarko 开发的交互式命令行界面（CLI），利用 Anthropic 的 Claude-3.5-Sonnet 模型来协助软件开发任务...

综合介绍 Paper Reviewer 是一个开源项目，旨在从 arXiv 论文生成综合评审，并将其转化为博客文章。该项目为 Hugging Face 的 Daily Papers 网站提供支持，自动...

综合介绍 Scraperr 是一个自托管的网页数据抓取工具，用户可以通过指定 XPath 元素来抓取网页数据。用户提交 URL 和相应的抓取元素，结果将显示在表格中，并可下载为 Excel 文件。Sc...

General Description Meetily is an AI-powered meeting assistant developed by Zackriya Solutions that captures meeting audio in real-time, performs voice transcription, and generates meeting summaries. It is unique in that all processing is done locally on the device, ensuring user privacy...

Comprehensive Introduction DeepSeek-VL2 is a series of advanced Mixture-of-Experts (MoE) visual language models that significantly improve the performance of its predecessor, DeepSeek-VL. The models are useful in visual question and answer, optical character recognition, text...

Comprehensive Introduction Lecca is a powerful AI platform that allows users to configure and deploy Large Language Models (LLMs) with multiple tools and workflows. Users can easily build, customize and automate their AI agents.Lecca offers a wide selection of AI providers and models...

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 ...

综合介绍 VideoSeal是由Facebook Research开发的开源视频水印工具，旨在提供高效的视频水印嵌入与提取功能。该工具支持最新的开源模型，包含预训练模型、训练代码、推理代码和评估工具...

General Introduction Languine is a powerful translation tool developed by Midday to help developers streamline the localization process for their apps. With Languine, developers can leverage AI technology to quickly generate accurate and contextualized translations that support over...

综合介绍 OpenAI Realtime API Next.js 是一个基于Next.js框架的开源项目，旨在帮助开发者快速构建实时语音AI应用。该项目集成了OpenAI的实时API和WebRTC技术...

综合介绍 Kolors是由快手团队开发的大规模文本到图像生成模型，基于潜在扩散技术。该模型训练于数十亿对文本-图像数据对，能够生成高质量、复杂语义准确的图像，并支持中英文输入。Kolors在视觉质量...

综合介绍 R1-V 是一个开源项目，旨在通过低成本的强化学习（RL）实现视觉语言模型（VLM）的突破。该项目利用可验证的奖励机制，激励 VLMs 学习通用的计数能力。令人惊叹的是，R1-V 的 2B ...

综合介绍 GraphRAG Visualizer 是一个基于网页的工具，旨在帮助用户可视化和探索来自 Microsoft GraphRAG 的工件。通过上传由 GraphRAG 索引管道生成的 Par...

综合介绍 Stagehand是一个专注于简洁性和可扩展性的AI网页浏览框架。它完全兼容Playwright，提供了三个简单的AI API（act、extract和observe），这些API构建在基础...