One Platform. All Phases. Every Device.
统一平台 · 全开发阶段 · 跨全设备
AutoDev Xiuper is an AI-native, multi-agent development platform built on Kotlin Multiplatform. It covers all seven phases of the software development lifecycle (Requirements → Development → Review → Testing → Data → Deployment → Operations) and runs on 8+ platforms: IntelliJ IDEA, VS Code, CLI, Web, Desktop, Android, iOS, and Server.
- IntelliJ IDEA Plugin: JetBrains Marketplace
- VSCode Extension: Visual Studio Marketplace
- CLI Tool:
npm install -g @xiuper/cli - Web App: web.xiuper.com
- Desktop & Android: GitHub Releases
- iOS: Build from source.
| Module | Platform | Status | Description |
|---|---|---|---|
| mpp-idea | IntelliJ IDEA | ✅ Production | Jewel UI, Agent toolwindow, code review, remote agent |
| mpp-vscode | VSCode | ✅ Production | Xiuper Agent |
| mpp-ui (Desktop) | macOS/Windows/Linux | ✅ Production | Compose Multiplatform desktop app |
| mpp-ui (CLI) | Terminal (Node.js) | ✅ Production | Terminal UI (React/Ink), local/server mode |
| mpp-ui (Android) | Android | ✅ Production | Native Android app |
| mpp-web (Web) | Web | ✅ Production | Web app |
| mpp-server | Server | ✅ Production | JVM (Ktor) |
| mpp-ios | iOS | 🚧 Production Ready | Native iOS app (SwiftUI + Compose) |
Xiuper Edition marks a major milestone in AI-assisted development:
- One Platform: Unified Kotlin Multiplatform architecture—write once, run anywhere
- All Phases: Seven specialized agents covering the full software development lifecycle
- Requirements → Development → Review → Testing → Data → Deployment → Operations
- Every Device: Native support for 8+ platforms without compromising performance
- IDE: IntelliJ IDEA, VS Code
- Desktop: macOS, Windows, Linux (Compose Multiplatform)
- Mobile: Android, iOS (Native + Compose)
- Terminal: CLI (Node.js + React/Ink)
- Web: Web app
- Server: Remote agent server (Ktor)
- Multi-LLM Support: OpenAI, Anthropic, Google, DeepSeek, Ollama, and more
- DevIns Language: Executable agent scripting language for workflow automation
- MCP Protocol: Extensible tool ecosystem via Model Context Protocol (MCP)
- Code Intelligence: Tree-sitter based parsing for Java, Kotlin, Python, JavaScript/TypeScript, Go, Rust, C#
- Global Ready: Full internationalization (Chinese/English)
AutoDev Xiuper includes seven specialized agents mapped to the SDLC:
| Agent | SDLC Phase | Description | Capabilities | Status |
|---|---|---|---|---|
| Knowledge | Requirements | Requirements understanding and knowledge construction with AI-native document reading and analysis | DocQL / Context Engineering | ✅ Stable |
| Coding | Development | Autonomous coding agent with complete file system, shell, and tool access capabilities | MCP / SubAgents / DevIns DSL | ✅ Stable |
| Review | Code Review | Professional code review analyzing code quality, security, performance, and best practices | Linter / Summary / AutoFix | ✅ Stable |
| Testing | Testing | Automated testing agent that generates test cases, executes tests, and analyzes coverage | E2E / Self-healing / Coverage | 🚧 WIP |
| ChatDB | Data | Database conversation agent supporting Text-to-SQL and natural language data queries | Schema Linking / Multi-DB / Query | ✅ Stable |
| WebEdit | Deployment | Web editing agent for browsing pages, selecting DOM elements, and interacting with web content | Inspect / Chat / Mapping | 🔄 Beta |
| Ops | Operations | Operations monitoring agent for log analysis, performance monitoring, and alert handling | Logs / Metrics / Alerts | 🚧 Coming |
Each agent focuses on a specific phase of the lifecycle, providing end-to-end AI assistance—from requirements to production operations.
In addition to SDLC agents, AutoDev Xiuper includes specialized agents for specific use cases:
| Agent | Purpose | Description | Capabilities | Status |
|---|---|---|---|---|
| Artifact | Quick Demos | Generate self-contained, executable artifacts (HTML/JS, React, Node.js, Python) inspired by Claude's Artifacts | Interactive preview / Auto-fix / Multi-format support | ✅ Stable |
Artifact Agent focuses on creating complete, runnable artifacts without file system or shell access. It's ideal for:
- Quick prototyping and demos
- Interactive web applications
- Data visualizations
- Python scripts with dependencies
- SVG graphics and Mermaid diagrams
SubAgents are specialized micro-agents invoked by the main Coding Agent for focused tasks. They follow the "agent as tool" architecture pattern:
| SubAgent | Purpose | Key Features | Platform Support |
|---|---|---|---|
| NanoDSL Agent | Generate AI-native UI code from natural language descriptions | Token-efficient DSL / Component generation / State management / HTTP requests | All platforms |
| PlotDSL Agent | Generate statistical charts and data visualizations from natural language | ggplot2-inspired syntax / Multiple chart types / Themes / Lets-Plot rendering | JVM Desktop & Android |
| Chart Agent | Generate chart configurations for ComposeCharts library | Pie/Line/Column/Row charts / Data analysis / Cross-platform rendering | All platforms |
| Analysis Agent | Intelligently analyze and summarize any type of content (logs, errors, JSON, code, etc.) | Content type detection / Smart summarization / Metadata extraction | All platforms |
| Codebase Investigator | Investigate codebase structure, patterns, dependencies, and architectural issues | Architecture analysis / Pattern detection / Dependency mapping / Issue identification | All platforms |
| Domain Dict Agent | Generate domain dictionaries from codebase analysis for better context understanding | Hot file detection / Class/method extraction / Domain term identification | All platforms |
| Error Recovery Agent | Analyze errors and suggest fixes with self-healing capabilities | Error pattern recognition / Fix suggestion / Auto-retry logic | All platforms |
| SQL Revise Agent | Revise and optimize SQL queries based on schema and execution feedback | Schema-aware correction / Query optimization / Syntax validation | All platforms |
| E2E Testing Agent | Perform end-to-end testing with visual understanding and self-healing locators | Natural language test scenario generation / Multi-modal perception / Self-healing | All platforms |
SubAgents enable modular, composable workflows: complex work is decomposed into focused sub-tasks, each handled by a specialized agent.
This code is distributed under the MPL 2.0 license. See LICENSE in this directory.