Hình ảnh, video, âm thanh
Tạo và sửa ảnh, video, giọng nói, nhạc. 135 mục, xếp theo sao GitHub rồi lượt tải npm.
- agentscope
Build and run agents you can see, understand and trust.
★ 36.040 Chưa kiểm
- mastra
Mastra is the modern TypeScript framework for AI-powered applications and agents.
★ 29.532 ↓ 26.404/tuần Chưa kiểm
- text-to-cad
Design physical products with AI
★ 26.367 Chưa kiểm
- FunASR
Open-source speech recognition toolkit for training, inference, streaming ASR, VAD, punctuation, speaker diarization pipelines, and OpenAI-compatible/MCP serving.
★ 21.032 Chưa kiểm
- nuclear
Streaming music player that finds free music for you
★ 18.950 Chưa kiểm
- leon
🧠 Leon is your open-source personal assistant.
★ 17.682 Chưa kiểm
- social-auto-upload
自动化上传视频到社交媒体：抖音、小红书、视频号、tiktok、youtube、bilibili
★ 16.561 Chưa kiểm
- lamda
Android Full-Stack Device Control Platform: WebRTC/H.264 remote desktop, UI/OCR/image-matching automation, one-click MITM, built-in Frida, proxy/VPN/frp/P2P networking, MCP/Agent, 160+ APIs, designed for multi-device clusters and engineered deployments.
★ 8.740 Chưa kiểm
- modly
Desktop app to generate 3D models from images or prompt using local AI — runs entirely on your GPU
★ 8.664 Chưa kiểm
- melonJS
A modern & fully featured HTML5 game engine (2D & 3D) for JavaScript/TypeScript, with WebGL/WebGPU rendering, built-in physics, Tiled map & glTF support and WebAudio.
★ 6.506 Chưa kiểm
- deepchat
🐬DeepChat - A smart assistant that connects powerful AI to your personal world
★ 6.396 Chưa kiểm
- AIGC-Interview-Book
【三年面试五年模拟】AIGC/LLM/AI Agent算法工程师面试资源平台。涵盖AIGC、LLM大模型、AI Agent、具身智能、传统深度学习、计算机视觉、自然语言处理、自动驾驶、机器学习、强化学习、大数据挖掘、世界模型、元宇宙、AGI等AI行业面试笔试干货经验与核心跨周期知识。
★ 5.240 Chưa kiểm
- B
An autonomous, context-aware AI desktop companion. Built with Python, featuring real-time screen vision, custom ONNX voice synthesis, active window tracking, and a dynamic floating UI with reactive facial expressions.
★ 5.182 Chưa kiểm
- davinci-resolve-mcp
MCP server integration for DaVinci Resolve Studio
★ 4.121 Chưa kiểm
- liteflow
Lightweight, fast, stable, programmable component-based rule engine — where AI Agents orchestrate just like ordinary components. Uniquely designed DSL: component reuse, sync/async & dynamic orchestration, multi-language scripting, nested rules, hot deployment and smooth refresh. If you can orchestra
★ 3.909 Chưa kiểm
- py-xiaozhi
Open-source AI assistant ecosystem with MCP integrations, multimodal workflows, IoT support, and cross-platform voice interaction.
★ 3.552 Chưa kiểm
- ableton-mcp
Control Ableton Live with any LLM: create tracks, arrange clips & compose music via MCP
★ 3.388 Chưa kiểm
- KiCAD-MCP-Server
KiCAD MCP is a Model Context Protocol (MCP) implementation that enables Large Language Models (LLMs) like Claude to directly interact with KiCAD for printed circuit board design.
★ 3.341 Chưa kiểm
- Konnect
AI-assisted PCB design for KiCAD 10. Native KiCAD plugin — a single Rust binary exposing 217 schematic, layout, routing, placement, design-review, and manufacturing tools to Claude, or the LLM of your choosing
★ 1.462 Chưa kiểm
- xiaozhi-esp32-server-java
小智ESP32的Java企业级管理平台，提供设备监控、音色定制、角色切换和对话记录管理的前后端及服务端一体化解决方案
★ 1.426 Chưa kiểm
- OpenFic
专为小说创作打造的跨平台、用户友好、AI Native 的一站式 Vibe Writing 工具。A cross-platform, user-friendly, AI-native, all-in-one Vibe Writing tool designed specifically for novel writing.
★ 1.307 Chưa kiểm
- OneBox
A free AI agent & toolbox for Android | 一站式安卓 AI 智能体 & 工具箱
★ 1.188 Chưa kiểm
- tuui
A desktop MCP client designed as a tool unitary utility integration, accelerating AI adoption through the Model Context Protocol (MCP) and enabling cross-vendor LLM API orchestration.
★ 1.160 Chưa kiểm
- ToRA
ToRA is a series of Tool-integrated Reasoning LLM Agents designed to solve challenging mathematical reasoning problems by interacting with tools [ICLR'24].
★ 1.124 Chưa kiểm
- gpt-image-canvas
Local professional AI canvas built with tldraw.
★ 741 Chưa kiểm
- touchdesigner-mcp
MCP server for TouchDesigner
★ 633 Chưa kiểm
- Agentfy
🤖 Agentfy is a modular microservices architecture designed to process user requests and execute workflows across multiple social media platforms. ASK ONCE, LET THE AGENT DO THE REST!
★ 616 Chưa kiểm
- aihub
All-in-one Kotlin app that aggregates multiple AI assistants in a single tabbed interface, featuring webview integration, Material Design 3, and persistent session management.
★ 567 Chưa kiểm
- nota
Nota — a free DAW for macOS, Windows and Linux. No subscription, no account — just open it and make music.
★ 539 Chưa kiểm
- Trae-Proxy
An intelligent API proxy tool designed to intercept and redirect OpenAI API requests.一个智能的API代理工具，专门用于拦截和重定向OpenAI API请求到自定义后端服务。支持多后端配置、动态模型映射和流式响应处理。
★ 196 Chưa kiểm
- ableton-live-mcp
Control Ableton Live from an AI assistant. 156 tools for building, editing MIDI, mixing, and mastering in a running Live set. Typed, tested on Live 12.
★ 80 Chưa kiểm
- dsh-image-gen
Bring ChatGPT-like image generation to DeepSeek Harness — Gemini, OpenAI, Seedream, DashScope, local ComfyUI & more.
↓ 23.514/tuần Chưa kiểm
- sharp-mcp
MCP server for image session management and processing
↓ 14.779/tuần Chưa kiểm
- tokportal-mcp
Public MCP server for the TokPortal API.
↓ 2.085/tuần Chưa kiểm
- dsh-hoi4-modding
HOI4（钢铁雄心4）模组开发工具包（DSH 组合包）：1 个模组工程师 agent、15 个技能、20 个 MCP 工具，配 163 篇参考库与以原版 1.19.4.2 为参照的知识库。装进 DeepSeek Harness 后自动注册 15 个技能并在本地挂载 20 个工具；纯 Python 标准库零依赖；离线预览可内联本机游戏里的 DDS 图标与事件图，事件窗按游戏 .gui 的真实版面排版，改盘即刷新。面向 1.19.x。
↓ 1.422/tuần Chưa kiểm
- agentwallet-mcp
MCP server for AgentWallet: self-custody local signing on EVM and Solana, or hosted wallets. Sign, broadcast, pay x402 invoices, and accept x402 payments.
↓ 1.105/tuần Chưa kiểm
- sbuilder-mcp
MCP server that designs and operates a Store Builder site — pages, data, theme and publish — through the platform's own API and live-edit protocol.
↓ 579/tuần Chưa kiểm
- @openephemeris/mcp-server
Astrology app for ChatGPT and Claude: real charts from NASA JPL DE440, not AI guesses.
↓ 549/tuần Chưa kiểm
- @roxyapi/sdk
TypeScript SDK for RoxyAPI: astrology, Vedic astrology, forecasts, human design, Chinese zodiac, feng shui, numerology, tarot and 18+ domains behind one key, verified against NASA JPL Horizons
↓ 396/tuần Chưa kiểm
- sensenova-u1-mcp
SenseNova U1 Fast MCP Server — 商汤科技文生图 API 的 MCP 服务
↓ 391/tuần Chưa kiểm
- Klype AI
Voice and context layer: draft, check and approve posts in a real person's measured voice.
↓ 267/tuần Chưa kiểm
- @jiujiang/jishi-mcp-server
MCP Server for JiShi Design
↓ 225/tuần Chưa kiểm
- youtube-data-mcp-server
YouTube MCP Server Implementation
↓ 216/tuần Chưa kiểm
- @mseep/flux-cloudflare-mcp
MCP for Flux Image Generation with Cloudflare Worker
↓ 151/tuần Chưa kiểm
- myspAIce
myspAIce, give your AI a social life: games, music, friendships. An immersive world. Just walk in.
↓ 136/tuần Chưa kiểm
- paraplex-mcp
Build and edit 3D motion design scenes in your open Paraplex tab, look at frames, and export.
↓ 131/tuần Chưa kiểm
- productaura
Product Aura turns one product photo into a complete set of listing and ad images for Amazon, Etsy, Shopify, TikTok Shop and social ads. CLI and MCP server.
↓ 122/tuần Chưa kiểm
- etincel-nonfiction
Trainable non-fiction writing voice, presets, and an anti-AI-tells audit for Claude, via MCP.
↓ 107/tuần Chưa kiểm