Lists (1)
Stars
Automatic integrate all Xiaomi devices to HomeAssistant via miot-spec, support Wi-Fi, BLE, ZigBee devices. 小米米家智能家居设备接入Hass集成
一款轻量级、高性能、功能强大的内网穿透代理服务器。支持tcp、udp、socks5、http等几乎所有流量转发，可用来访问内网网站、本地支付接口调试、ssh访问、远程桌面，内网dns解析、内网socks5代理等等……，并带有功能强大的web管理端。a lightweight, high-performance, powerful intranet penetration proxy serv…
An AI-powered research assistant that performs iterative, deep research on any topic by combining search engines, web scraping, and large language models. The goal of this repo is to provide the si…
收录并持续精选 10,000+ 个 Telegram 频道、群组与机器人，分类清晰，搜索即得，帮你省下自己找资源的时间。
The open source platform for AI-native application development.
主要记录大语言大模型（LLMs） 算法（应用）工程师相关的知识及面试题
Everything about ComfyUI, including workflow sharing, resource sharing, knowledge sharing, tutorial sharing, and more.关于ComfyUI的一切，工作流分享、资源分享、知识分享、教程分享等
OpenUI let's you describe UI using your imagination, then see it rendered live.
Vue前台 + Django3.1 + DjangoRestful Framework + Ant Design Pro V4 开发的二手书商城网站及后台管理
There can be more than Notion and Miro. AFFiNE(pronounced [ə‘fain]) is a next-gen knowledge base that brings planning, sorting and creating all together. Privacy first, open-source, customizable an…
🏆 An awe-inspiring collection of resources, encompassing a wide range of tools, documents, resources, applications, and use cases related to ChatGPT.
A mnhv1 protocol server which help mnh punch NAT hole. 一个使用mnhv1协议协助mnh打NAT洞的服务器
A NAT hole punching tool that allows peers directly connect to your NATed server without client. 一个对端不需要客户端就可以直接连接的NAT打洞工具
Create Customized Software using Natural Language Idea (through LLM-powered Multi-Agent Collaboration)
Crawl a site to generate knowledge files to create your own custom GPT from a URL
ACM Multimedia 2023: DocDiff: Document Enhancement via Residual Diffusion Models. Also contains 1597 red seals in Chinese scenes, along with their corresponding binary masks.
The definitive Web UI for local AI, with powerful features and easy setup.
fastllm是后端无依赖的高性能大模型推理库。同时支持张量并行推理稠密模型和混合模式推理MOE模型，任意10G以上显卡即可推理满血DeepSeek。双路9004/9005服务器+单显卡部署DeepSeek满血满精度原版模型，单并发20tps；INT4量化模型单并发30tps，多并发可达60+。
ChatGLM3 series: Open Bilingual Chat LLMs | 开源双语对话语言模型
This project is based on the scripting capabilities of several excellent iOS proxy tools (e.g. Surge, Quantumult X)