barry-ran/QuickDesk

585 sao GitHub và vẫn tăng — barry-ran/QuickDesk là dự án QML mà TopGit đang theo dõi trên nền tảng. QuickDesk is the first AI-native remote desktop — an open-source, free application with a built-in MCP (Model Context Protocol) Server that lets any AI agent see and control remote computers.
Tóm tắt dựng từ metadata GitHub của chính dự án — chưa có bài review TopGit. Trang sẽ tự động cập nhật khi bài review đầy đủ được xuất bản.
TopGit viết bài đầy đủ cho repo có nhiều sao nhất và được yêu cầu nhiều nhất. Trang này là snapshot trong thời gian chờ — xem README gốc ở tab READ ME.
Snapshot
Cộng tác viên hàng đầu
Xem cộng tác viên hàng đầu
QuickDesk
The First AI-Native Remote Desktop
Built-in MCP Server · AI Agents Control Any Remote Computer · Open-Source & Free
English | 中文
Telegram | Issues | Download
QuickDesk is the first AI-native remote desktop — an open-source, free application with a built-in MCP (Model Context Protocol) Server that lets any AI agent see and control remote computers.
While other remote desktop tools only serve human users, QuickDesk extends AI Computer Use from "local machine only" to "any remote machine in the world". Connect Claude, GPT, Cursor, or any MCP-compatible AI to QuickDesk, and it can screenshot, click, type, drag, and automate across remote desktops — just like a human operator, but faster and 24/7.
Built on Google Chromium Remoting technology (the engine behind Chrome Remote Desktop), QuickDesk delivers industrial-grade performance, stability, and security refined over 10+ years by Google.
Main Interface

Remote Desktop

AI Config

Why QuickDesk?
AI-First: The Only Remote Desktop with MCP Support → MCP Integration Guide
- Built-in MCP Server: AI agents connect via standard MCP protocol — no plugins, no hacks, zero configuration
- Dual Transport: stdio mode (AI client spawns process) or HTTP/SSE mode (QuickDesk hosts MCP server for multi-client access)
- Full Computer Use Toolkit: 20+ MCP tools — screenshot, click, type, drag, scroll, hotkeys, clipboard, and more
- Real-Time Visibility: AI operations are displayed in the QuickDesk GUI in real time — the user sees every mouse move and keystroke, and can intervene at any time
- Multi-Device AI Orchestration: AI can connect to and control multiple remote machines simultaneously — batch automation, cross-device workflows, fleet management
- Guided Prompts: 9 built-in MCP prompt templates covering remote operation, server health check, batch automation, system diagnosis, screen analysis, multi-device orchestration, and SOP documentation
High-Performance Foundation
- Open-Source & Free: MIT License, no feature restrictions, no connection limits, commercial use welcome
- Self-Hosted: Deploy your own signaling and TURN relay servers, keep full control of your data
- Commercial-Grade Foundation: Built on Chromium Remoting — the same technology powering Chrome Remote Desktop, refined by Google for 10+ years and proven by billions of users
- Pure C++ Ultimate Performance: Full C++ stack from protocol core to GUI — no GC pauses, no runtime overhead, minimal memory and CPU footprint
- Modern Codecs: H.264, VP8, VP9, AV1 — flexibly switch based on network and hardware conditions
- WebRTC P2P Direct Connection: Prioritizes peer-to-peer connections for lowest latency; automatically falls back to TURN relay when traversal fails
- Cross-Platform: Windows and macOS supported (Linux planned)
- Modern UI: Fluent Design interface built with Qt 6 + QML, with light and dark themes
Comparison
| Feature | QuickDesk | RustDesk | BildDesk | ToDesk | TeamViewer |
|---|---|---|---|---|---|
| AI Agent Support (MCP) | ✅ Built-in | ❌ | ❌ | ❌ | ❌ |
| Open Source | ✅ MIT | ✅ AGPL-3.0 | ❌ | ❌ | ❌ |
| Free for Commercial Use | ✅ | ❌ License required | ❌ | ❌ | ❌ |
| Core Language | C++ | Rust + Dart | — | — | — |
| Remote Protocol | Chromium Remoting (WebRTC) | Custom | Custom | Custom | Custom |
| Protocol Maturity | ⭐⭐⭐⭐⭐ Google 10yr+ | ⭐⭐⭐ | ⭐⭐ | ⭐⭐⭐ | ⭐⭐⭐⭐⭐ |
| P2P Direct | ✅ WebRTC ICE | ✅ TCP Hole Punching | ✅ | ✅ | ✅ |
| Video Codecs | H.264/VP8/VP9/AV1 | VP8/VP9/AV1/H.264/H.265 | — | — | — |
| Self-Hosted | ✅ Full solution | ✅ | ❌ | ❌ | ❌ |
| GUI Framework | Qt 6 (C++) | Flutter (Dart) | — | — | — |
| Memory Usage | ⭐⭐⭐⭐⭐ Very Low | ⭐⭐⭐ Medium | — | ⭐⭐⭐ | ⭐⭐⭐ |
| CPU Usage | ⭐⭐⭐⭐⭐ Very Low | ⭐⭐⭐ Medium | — | ⭐⭐⭐ | ⭐⭐⭐ |
| Windows | ✅ | ✅ | ✅ | ✅ | ✅ |
| macOS | ✅ | ✅ | ✅ | ✅ | ✅ |
| Linux | 🔜 | ✅ | ❌ | ✅ | ✅ |
| iOS/Android | 🔜 | ✅ | ✅ | ✅ | ✅ |
Why Best-in-Class Performance?
-
Pure C++ Full Stack: The entire stack — from low-level protocol to GUI — is implemented in C++. No garbage collection pauses, no VM/runtime overhead. Compared to RustDesk's Dart/Flutter GUI layer or ToDesk's Electron-based approach, CPU and memory usage are significantly lower.
-
Chromium-Level Optimization: Core paths for video encoding/decoding, network transmission, and screen capture directly reuse Chromium's highly optimized C++ code, including SIMD instruction optimization and zero-copy rendering pipelines.
-
Shared Memory Video Transfer: QuickDesk uses shared memory to pass video frames (YUV I420) between processes, eliminating the serialization/deserialization and data copying overhead of traditional IPC.
-
GPU-Accelerated Rendering: YUV data is fed directly into the GPU rendering pipeline via Qt 6's
QVideoSink, achieving zero-CPU-copy video rendering.
Features
AI Integration (MCP Server)
- Built-in MCP Server — AI agents connect via standard protocol, works with Cursor, Claude Desktop, VS Code, and any MCP client
- Dual transport: stdio (AI client launches process) or HTTP/SSE (QuickDesk manages MCP server, multiple AI clients connect)
- Persistent MCP transport mode — remembers your stdio/HTTP choice across restarts
- 40+ MCP tools: screenshot, mouse click/drag/scroll, keyboard type/hotkey, clipboard, OCR text recognition, UI element detection, screen verification, and more
- Host-side skill host with built-in skills (system info, file operations, shell execution) — run structured tools on the remote machine
- Pluggable skills architecture — add custom skill directories, skills auto-load and sync to connected clients
- Skill host toggle in Settings — enable/disable the skill host process with persistent configuration
- MCP Resources: real-time device status, connection info, host details
- 9 MCP Prompts: operation guide, server health check, batch automation, system diagnosis, screen analysis, multi-device orchestration, SOP documentation
- Real-time event streaming: connection state changes, clipboard updates, screen changes, performance stats
- Event-driven tools: wait_for_event, wait_for_connection_state, wait_for_clipboard_change, wait_for_screen_change for reactive automation
- Background automation mode:
show_window=falsefor headless batch operations - Screenshot scaling: adjustable resolution for faster AI processing
Remote Control
- High-definition, low-latency remote desktop display
- Full keyboard and mouse mapping
- Real-time remote cursor synchronization
- Bidirectional clipboard sync
- Adaptive frame rate and bitrate
- Frame rate boost mode (Office / Gaming)
- Privacy screen mode — blacks out the host's physical display and blocks local keyboard/mouse input during remote control, protecting session privacy (Windows 10 2004+)
- Virtual display — creates virtual monitors via IDD driver for multi-screen extension, headless server remote access, privacy isolation, and resolution adaptation (Windows 10 2004+, requires virtual display driver installation)
Connection Management
- 9-digit Device ID + temporary access code mechanism
- Auto-refresh access code (configurable: 30 min to 24 hours, or never)
- Multi-tab simultaneous connections to multiple remote devices
- Connection history with quick reconnect
- Real-time connection status monitoring
Performance Monitoring
- Detailed latency breakdown panel (Capture → Encode → Network → Decode → Render)
- Real-time frame rate, bitrate, and bandwidth statistics
- Input round-trip time (RTT) monitoring
- Encoding resolution and quality information
Personalization
- Fluent Design style interface
- Light and dark theme switching
- i18n support (Chinese / English)
- Video codec preference (H.264 / VP8 / VP9 / AV1)
Self-Hosted Deployment
- Custom signaling server address
- Custom STUN/TURN servers
- Complete server deployment solution (Go signaling server + PostgreSQL + Redis + coturn)
- Web Admin Panel — full-featured management dashboard for the signaling server:
- Real-time monitoring with ECharts trend charts (connections, new devices over 24h/7d/30d)
- Device management with search, filter, sort, pagination, batch operations, and device groups
- User management with batch enable/disable/delete/set-level
- Admin TOTP two-factor authentication (QR code setup, Google Authenticator compatible)
- Operation audit logs with filtering by action/admin/time range
- IP whitelist (CIDR support) for admin panel access control
- Webhook notifications (device online/offline, new device/user, connection failures)
- CSV data export for devices, users, and activity logs
Architecture
QuickDesk uses a modular multi-process architecture:
graph TD
subgraph AI["AI Agent (Claude / GPT / Cursor)"]
A1["MCP Protocol"]
end
subgraph MCP["quickdesk-mcp (Rust Bridge)"]
M1["MCP stdio ↔ WebSocket"]
M2["MCP HTTP/SSE ↔ WebSocket"]
end
subgraph GUI["QuickDesk GUI (Qt 6)"]
direction LR
WS["WebSocket API Server"]
QML["QML/C++"]
MainWin["Main Window"]
RemoteWin["Remote Desktop Window"]
end
subgraph Host["quickdesk-host (Chromium Remoting)"]
H1["Screen Capture"]
H2["Video Encoding"]
H3["Input Event Handling"]
H4["WebRTC Connection"]
end
subgraph Client["quickdesk-client (Chromium Remoting)"]
C1["Video Decoding"]
C2["Input Event Injection"]
C3["Shared Memory Video Frames"]
C4["WebRTC Connection"]
end
subgraph Signaling["Signaling Server (Go + Gin)"]
S1["WebSocket Signaling"]
S2["ICE Config Distribution"]
S3["Device Registration & Auth"]
S4["PostgreSQL + Redis"]
end
subgraph TURN["TURN Server (coturn)"]
T1["Relay when P2P traversal fails"]
end
AI -- "stdio (JSON-RPC)" --> MCP
AI -. "HTTP/SSE" .-> M2
MCP -- "WebSocket" --> WS
GUI -- "Native Messaging\n(stdin/stdout JSON)" --> Host
GUI -- "Native Messaging\n(stdin/stdout JSON)" --> Client
Host -- "WebSocket" --> Signaling
Client -- "WebSocket" --> Signaling
Signaling -- "ICE Config" --> TURN
Host -. "WebRTC P2P / TURN Relay" .-> Client
Tech Stack
| Layer | Technology |
|---|---|
| AI Integration | MCP Server (Rust) + WebSocket API |
| GUI Client | Qt 6 (QML + C++17) |
| UI Style | Fluent Design Component Library (custom-built) |
| Remote Protocol Core | Chromium Remoting (C++) |
| Video Codecs | H.264 / VP8 / VP9 / AV1 |
| Network Transport | WebRTC (ICE/STUN/TURN) |
| IPC | Native Messaging (JSON) + Shared Memory |
| Signaling Server | Go + Gin + GORM |
| Data Storage | PostgreSQL + Redis |
| TURN Relay | coturn |
| Logging | spdlog |
| Build System | CMake 3.19+ |
| CI/CD | GitHub Actions |
Getting Started
Download
Go to Releases to download the latest version:
| Platform | Download |
|---|---|
| Windows x64 | QuickDesk-win-x64-setup.exe |
| macOS ARM64 | QuickDesk-mac-arm64.dmg |
Usage
- Install and run QuickDesk on both the host (remote) and client (local) machines
- The host will automatically generate a Device ID and Access Code
- On the client, enter the host's Device ID and Access Code, then click Connect
- You're now remotely controlling the host machine
Silent install (Windows installer)
The Windows package is built with Inno Setup (scripts/installer/quickdesk.iss). Standard Inno command-line switches apply:
| Switch | Meaning |
|---|---|
/SILENT | No wizard pages; progress window may appear |
/VERYSILENT | Fully unattended (no progress window) |
/DIR="path" | Install directory (optional) |
/TASKS="..." | Comma-separated tasks from [Tasks] |
Available tasks:
| Task | Description |
|---|---|
desktopicon | Create desktop shortcut |
startmenuicon | Create Start Menu shortcut |
vdd | Install virtual display driver (IDD) and related files, required for virtual display feature |
All three tasks are selected by default (Flags: checkedonce — checked on first install, preserves user choice on upgrades). To skip the virtual display driver, explicitly exclude vdd via /TASKS.
Examples:
REM Default tasks (includes virtual display driver when selected in script defaults)
QuickDesk-win-x64-setup.exe /VERYSILENT
REM Explicit tasks
QuickDesk-win-x64-setup.exe /VERYSILENT /TASKS="desktopicon,startmenuicon,vdd"
REM Install without virtual display driver
QuickDesk-win-x64-setup.exe /VERYSILENT /TASKS="desktopicon,startmenuicon"
REM Custom install path
QuickDesk-win-x64-setup.exe /VERYSILENT /DIR="D:\QuickDesk"
After a silent install, QuickDesk.exe is not auto-launched (skipifsilent in the installer script), but the QuickDeskHost Windows service is still installed and started when configured in [Run].
Administrator rights are required (PrivilegesRequired=admin in the script).
Build from Source
Requirements
- CMake 3.19+
- Qt 6.5+ (Multimedia and WebSockets modules required)
- C++17 compiler
Windows
# Requires Visual Studio 2022 + MSVC
# Set Qt path environment variable
set ENV_QT_PATH=C:\Qt\6.8.3
# Build
scripts\build_qd_win.bat Release
# Package (requires Inno Setup)
scripts\publish_qd_win.bat Release
scripts\package_qd_win.bat Release
macOS
# Requires Xcode Command Line Tools
# Set Qt path environment variable
export ENV_QT_PATH=/path/to/Qt/6.8.3
# Build
bash scripts/build_qd_mac.sh Release
# Package
bash scripts/publish_qd_mac.sh Release
bash scripts/package_qd_mac.sh Release
API Key (Optional)
If you deploy your own signaling server with API Key enabled, there are two ways to configure the API Key:
Method 1: Runtime Configuration (Recommended)
In QuickDesk Settings → Network → API Key, enter your signaling server's API Key. This is the recommended approach — no recompilation needed, and each deployment can use its own key.
Method 2: Build-time Injection
You can also inject the API Key at build time as a compile-time default:
# Windows
set ENV_QUICKDESK_API_KEY=your-secret-key
scripts\build_qd_win.bat Release
# macOS
ENV_QUICKDESK_API_KEY=your-secret-key bash scripts/build_qd_mac.sh Release
Priority: Runtime API Key (from Settings) takes precedence over the build-time key. If both are set, the runtime value is used.
Without either configuration, the client can only connect to signaling servers without API Key protection.
WebClient note: The WebClient is a static web page running in the browser. Since API keys embedded in JavaScript are visible via DevTools, the WebClient uses Origin whitelist validation instead of API Key. Configure
ALLOWED_ORIGINSon the signaling server to restrict which domains can access it. Browsers automatically send theOriginheader and JavaScript cannot forge it, so only the WebClient served from your official domain will be allowed.
See Signaling Server Deployment for details.
Self-Hosted Deployment
QuickDesk supports full self-hosted deployment. You can deploy all services on your own servers to ensure data security.
Components
- Signaling Server (required): Handles device registration and signaling relay → Signaling Server Deployment Guide
- TURN Relay Server (recommended): Provides relay when P2P direct connection fails → TURN Server Deployment Guide
Docker Deploy (Signaling Server)
Three deployment methods for the signaling server:
cd SignalingServer
cp .env.example .env && vim .env
# Option 1: Pull pre-built image (recommended)
./deploy-pull.sh
# Option 2: Build from source
./deploy-build.sh
# Option 3: Offline deploy (no internet needed)
./deploy-offline.sh quickdesk-signaling-image.tar.gz
Pre-built Docker images are automatically published to ghcr.io/barry-ran/quickdesk-signaling on each tagged release. See the deployment guide for details.
Client Configuration
In QuickDesk Settings → Network:
- Signaling server address:
ws://your-server.com:8000orwss://your-server.com:8000 - API Key: Enter the API Key configured on your signaling server (if enabled)
- Custom STUN server:
stun:your-server.com:3478 - Custom TURN server:
turn:your-server.com:3478(username and password required)
Project Structure
QuickDesk/
├── QuickDesk/ # Qt GUI client
│ ├── main.cpp # Application entry point
│ ├── src/
│ │ ├── api/ # WebSocket API server + request handlers
│ │ ├── controller/ # Main controller
│ │ ├── manager/ # Business managers (Host/Client/Process/TURN/...)
│ │ ├── component/ # Video rendering, key mapping, cursor sync
│ │ ├── core/ # Config center, user data
│ │ ├── viewmodel/ # MVVM ViewModel
│ │ └── language/ # i18n
│ ├── qml/
│ │ ├── views/ # Main window, remote desktop window
│ │ ├── pages/ # Remote control, settings, about pages
│ │ ├── component/ # Fluent Design component library
│ │ └── quickdeskcomponent/ # QuickDesk-specific components
│ ├── base/ # Base utilities
│ └── infra/ # Infrastructure (database, logging, HTTP)
├── quickdesk-mcp/ # Rust MCP Bridge (stdio ↔ WebSocket)
│ └── src/
│ ├── main.rs # Entry point, CLI args, MCP server startup
│ ├── server.rs # MCP tools, prompts, resources
│ └── ws_client.rs # WebSocket client for Qt API
├── quickdesk-skill-host/ # Rust host-side skill host (Cargo workspace)
│ ├── agent/ # Skill host main binary
│ ├── mcp-server-common/ # Shared MCP server framework
│ └── skills/ # Built-in skill MCP servers
│ ├── sys-info/ # System information skill
│ ├── file-ops/ # File operations skill
│ └── shell-runner/ # Shell execution skill
├── SignalingServer/ # Go signaling server
│ ├── cmd/signaling/ # Entry point
│ └── internal/ # Business logic
├── scripts/ # Build, package, publish scripts
├── docs/ # Documentation
│ ├── mcp-integration.md # MCP integration guide (English)
│ └── MCP接入指南.md # MCP integration guide (Chinese)
├── .github/workflows/ # CI/CD configuration
└── version # Version number
Roadmap
- Windows support
- macOS support
- P2P direct connection + TURN relay
- Multi-tab multi-connection
- Auto-refresh access code
- Video performance stats overlay
- Fluent Design UI
- Light and dark themes
- i18n (Chinese / English)
- MCP Server — AI agents can control remote desktops
- 20+ MCP tools (screenshot, click, type, drag, hotkey, clipboard, etc.)
- MCP Resources & Prompts
- Host-side skill host with built-in skills (sys-info, file-ops, shell-runner)
- OCR-based UI analysis tools (get_ui_state, find_element, screen_diff_summary, etc.)
- Persistent MCP transport mode and skill host settings
- Multi-directory skills loading with user-configurable paths
- Device memory & history retrieval (auto-profiling, operation logs, failure patterns)
- Workflow recording & playback (record, replay, parameterize)
- Trust layer & safety (risk assessment, confirmation dialogs, emergency stop, audit log)
- Privacy screen — blacks out host physical display and blocks local input during remote sessions
- Virtual display — IDD virtual display driver for multi-screen extension, headless remote, and resolution adaptation
- File transfer
- Audio streaming
- Unattended access
- Linux support
- iOS / Android clients
- Address book & device groups
Contributing
Contributions are welcome! Please follow these guidelines:
- Fork the repository and create a feature branch
- Keep code style consistent with the project
- Ensure the build passes before submitting a PR
- Each PR should contain a single feature or fix
License
QuickDesk's own code is licensed under the MIT License, free for commercial use.
The bundled quickdesk-remoting component is based on Chromium and licensed under the BSD 3-Clause License.
For complete third-party license information, see THIRD_PARTY_LICENSES.
Acknowledgments
- Chromium Remoting — Remote desktop protocol core
- Qt — Cross-platform GUI framework
- spdlog — High-performance logging library
- coturn — TURN relay server
Star History
Repo liên quan
Dify is an open-source LLM app platform that packages a visual workflow/agent builder, RAG pipeline, model provider management, and app-level APIs into one self-hostable (or cloud) stack, aimed at teams who want to skip stitching those pieces together themselves.
JavaGuide là một repository tổng hợp kiến thức phỏng vấn Java và backend được duy trì bởi cộng đồng, bao phủ gần như toàn bộ các chủ đề mà một ứng viên backend cần nắm vững: từ Java core (collections, concurrency, JVM), hệ điều hành và mạng máy tính, cho đến cơ sở dữ liệu (MySQL, Redis), kiến trúc phân tán, và các công cụ devops như Docker, Git. Điểm mạnh rõ rệt là mỗi phần đều đi kèm bài tổng hợp câu hỏi phỏng vấn được đánh dấu "必看" (bắt buộc đọc), kèm theo phân tích source code chi tiết cho các cấu trúc dữ liệu phổ biến như HashMap, ConcurrentHashMap, và các topic nâng cao như AQS, JMM. Repository cũng mở rộng sang AI application development với một repo riêng (AIGuide) về LLM, Agent, RAG và MCP, phản ánh xu hướng hiện tại trong việc tuyển dụng backend. Nhược điểm là nội dung rất dàn trải — hơn 100 file markdown trải dài từ BigDecimal đến Elasticsearch, nên nếu bạn đã có nền tảng vững ở một số phần, việc lọc đúng nội dung cần ôn tập đòi hỏi thêm effort. Cá nhân tôi thấy đây là tài liệu tốt nhất để "làm quen" với toàn cảnh backend Java trước khi đi sâu vào từng chủ đề riêng lẻ, nhưng không nên dùng nó thay cho việc đọc source code thật hoặc tài liệu chính thức.
User-friendly AI Interface (Supports Ollama, OpenAI API, ...)
A cross-platform desktop All-in-One assistant for Claude Code, Codex, OpenCode,DeepSeek Harness and more. Only official website: ccswitch.io
Trả lời nhanh
barry-ran/QuickDesk có bao nhiêu sao?
barry-ran/QuickDesk có 585 sao GitHub — tải lại trang để xem số mới nhất, hoặc xem trực tiếp github.com/barry-ran/QuickDesk. TopGit phản chiếu số sao của GitHub nhưng không cam kết đến từng phút.
barry-ran/QuickDesk có phải mã nguồn mở không?
Có — barry-ran/QuickDesk phát hành theo license MIT, nghĩa là mã nguồn mở để đọc, fork và (tùy license) tái sử dụng. Mã: github.com/barry-ran/QuickDesk.
barry-ran/QuickDesk còn đang phát triển không?
Commit gần nhất trên barry-ran/QuickDesk là 3 tháng trước (theo timestamp GitHub). Repo có 97 fork — một chỉ báo về mức độ quan tâm của cộng đồng.
barry-ran/QuickDesk dùng license gì?
barry-ran/QuickDesk phát hành theo license MIT. Nên mở file LICENSE trên GitHub để xác nhận — license metadata đôi khi lệch với thực tế dự án.
barry-ran/QuickDesk là gì?
barry-ran/QuickDesk (barry-ran/QuickDesk) là dự án QML trên GitHub. Theo mô tả gốc: QuickDesk is the first AI-native remote desktop — an open-source, free application with a built-in MCP (Model Context Protocol) Server that lets any AI agent see and control remote computers.
barry-ran/QuickDesk viết bằng ngôn ngữ gì?
barry-ran/QuickDesk chủ yếu viết bằng QML. Trường "language" của GitHub dựa trên phần lớn byte ở nhánh mặc định.
Cùng nhóm AI Tools còn repo nào?
barry-ran/QuickDesk thuộc nhóm AI Tools trên TopGit, cùng 10 topic GitHub. Trang Trending và Topics liệt kê các repo cùng số sao và cùng ngôn ngữ để so sánh.
Đọc thêm về barry-ran/QuickDesk ở đâu?
Trang TopGit này là một snapshot — tab "Readme" hiển thị nguyên văn README của repo (đã bỏ link, giữ ảnh). Repo GitHub ở github.com/barry-ran/QuickDesk là nguồn chính thức.
Đọc đầy đủ README ở tab phía trên.
QuickDesk có đáng để bạn bỏ thời gian?
ChatGPT, Claude và Perplexity đều đọc được trang này. Hỏi thử xem họ nghĩ gì về QuickDesk.