Pinned Repositories
AFFiNE
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 and ready to use.
Agent-S
Agent S: an open agentic framework that uses computers like a human
agentic-cursorrules
A practical approach to managing multiple AI agents in Cursor through strict file-tree partitioning and domain boundaries.
agents
Build real-time multimodal AI applications 🤖🎙️📹
AgentVerse
🤖 AgentVerse 🪐 provides a flexible framework that simplifies the process of building custom multi-agent environments for large language models (LLMs).
AI-Code-Convert
AI Code Translator，Generate Code or Natural Language To Programming Language
AI-ContentCraft
AI ContentCraft is an all-in-one content creation suite that helps creators generate stories, podcast scripts, and multimedia content using AI-powered text generation, speech synthesis, and image generation capabilities.
ChatGPT_JCM
GPT多模型聊天项目，GPT-4已发布，接口开放后本项目将第一时间适配。后期会一点一点的将OpenAI接口进行接入大家支持一下呗，微信群号在下方，右上角点个Star，我会一直更新下去。
lama-cleaner
Image inpainting tool powered by SOTA AI Model. Remove any unwanted object, defect, people from your pictures or erase and replace(powered by stable diffusion) any thing on your pictures.
screenpipe
rewind.ai x cursor.com = your AI assistant that has all the context. 24/7 screen & voice recording for the age of super intelligence. get your data ready or be left behind
hyzwz's Repositories
hyzwz/agents
Build real-time multimodal AI applications 🤖🎙️📹
hyzwz/AI-ContentCraft
AI ContentCraft is an all-in-one content creation suite that helps creators generate stories, podcast scripts, and multimedia content using AI-powered text generation, speech synthesis, and image generation capabilities.
hyzwz/bailing
百聆 是一个类似GPT-4o的语音对话机器人，通过ASR+LLM+TTS实现，时延低至800ms，低配置也可运行，支持打断
hyzwz/brown-chat
hyzwz/CoolCline
Cool Cline is an agentic coding assistant that combines the best features of Cline, Roo Clineand Bao Cline. Working seamlessly with your **Command Line Interface** and **Editor**, it brings you the most powerful AI development experience. Thanks to all their Clines contributors!
hyzwz/cursor-tools
Give Cursor Agent an AI Team and Advanced Skills
hyzwz/deepseek-free-api
🚀 DeepSeek-V3大模型逆向API【特长：良心厂商】（官方贼便宜，建议直接走官方），支持高速流式输出、多轮对话，联网搜索，r1深度思考，零配置部署，多路token支持，仅供测试，如需商用请前往官方开放平台。
hyzwz/gemini-deepgram-livekit-agent
hyzwz/gemini-multimodal-live-demo
Chat Application Starter Kit — Gemini Multimodal Live API + Pipecat
hyzwz/gemini-proxy
使用Cloudflare Worker代理Gemini 多模态 API
hyzwz/Gemini-Search
Perplexity style AI Search engine clone built with Gemini 2.0 Flash and Grounding
hyzwz/gemini-teacher
English pronunciation correction teacher built with gemini
hyzwz/gemini-webrtc-web-simple
Gemini Multimodal Live + WebRTC in a single `app.ts`
hyzwz/geminiCoder
Create apps with Gemini
hyzwz/Genesis
A generative world for general-purpose robotics & embodied AI learning.
hyzwz/GraphAgent
"GraphAgent: Agentic Graph Language Assistant"
hyzwz/midscene
An AI-powered automation SDK can control the page, perform assertions, and extract data in JSON format using natural language.
hyzwz/miniperplx
A minimalistic AI-powered search engine that helps you find information on the internet. Powered by Vercel AI SDK! Search with models like Grok 2.0.
hyzwz/multimodal-live-api-web-console
A react-based starter app for using the Multimodal Live API over websockets with Gemini
hyzwz/one-hub
OpenAI 接口管理 & 分发系统，改自songquanpeng/one-api。支持更多模型，加入统计页面，完善非openai模型的函数调用。
hyzwz/openai-gemini
Gemini ➜ OpenAI API proxy. Serverless!
hyzwz/OSUM
西北工业大学ASLP实验室OSUM项目官方库
hyzwz/pipecat
Open Source framework for voice and multimodal conversational AI
hyzwz/repomix
📦 Repomix (formerly Repopack) is a powerful tool that packs your entire repository into a single, AI-friendly file. Perfect for when you need to feed your codebase to Large Language Models (LLMs) or other AI tools like Claude, ChatGPT, and Gemini.
hyzwz/secure-computer-use
Secure AI computer use powered by E2B Desktop Sandbox
hyzwz/smolagents
🤗 smolagents: a barebones library for agents. Agents write python code to call tools and orchestrate other agents.
hyzwz/stagehand
An AI web browsing framework focused on simplicity and extensibility.
hyzwz/TEN-Agent
TEN Agent is a conversational AI powered by TEN, integrating Gemini 2.0 Multimodal Live API, OpenAI Realtime API, RTC, and more. It offers real-time capabilities to see, hear, and speak, along with advanced tools like weather checks, web search, and RAG.
hyzwz/TransRouter
Trans Router
hyzwz/VITA
✨✨VITA-1.5: Towards GPT-4o Level Real-Time Vision and Speech Interaction