CLEO MCP Server

平台与服务

by kryptobaseddev

面向独立开发者与 AI coding agents 的任务管理协议,采用双网关 2-gateway CQRS 模式提升协作与执行效率。

让独立开发者和AI编程代理在统一任务协议下顺畅协作,双网关CQRS把分发与执行效率进一步拉高。

什么是 CLEO MCP Server

面向独立开发者与 AI coding agents 的任务管理协议,采用双网关 2-gateway CQRS 模式提升协作与执行效率。

README

CLEO - Contextual Language Engine & Orchestrator

npm version CI License: MIT Node.js Version

ko-fi

CLEO is a comprehensive task management and agent orchestration system designed for AI-powered software development workflows. It provides structured task tracking, session management, memory systems, and multi-provider AI integration through a unified interface.

What is CLEO?

CLEO stands for Contextual Language Engine & Orchestrator. It's built to solve the coordination challenges that arise when working with multiple AI coding assistants across complex software projects.

Core Capabilities

  • Task Management: Hierarchical task tracking with dependencies, priorities, and lifecycle states
  • Session Management: Contextual work sessions with automatic state persistence
  • Agent Orchestration: Multi-agent coordination with protocol compliance
  • Memory Systems: Persistent knowledge storage with brain-like retrieval
  • Multi-Provider Support: Works with Claude Code, OpenCode, Cursor, and more
  • MCP Server: Full Model Context Protocol integration for AI assistants

Monorepo Structure

This monorepo contains 6 packages that work together to provide the complete CLEO ecosystem:

PackagePurposeDescription
@cleocode/contractsType DefinitionsDomain types, interfaces, and contracts - the foundation of the type system
@cleocode/coreBusiness LogicTask management, sessions, memory, orchestration, and lifecycle management
@cleocode/adaptersProvider IntegrationUnified adapters for Claude Code, OpenCode, Cursor, and other AI providers
@cleocode/agentsAgent ProtocolsSubagent templates and protocol definitions for autonomous execution
@cleocode/skillsSkill DefinitionsPre-built skills and capabilities for common development workflows
@cleocode/cleoCLI & MCP ServerCommand-line interface and Model Context Protocol server

Quick Start

Installation

bash
# Install globally for CLI access
npm install -g @cleocode/cleo

# Or use with npx (no installation required)
npx @cleocode/cleo init

Initialize a Project

bash
# Navigate to your project
cd my-project

# Initialize CLEO
cleo init

# Or use the shorthand
cleo init --with-examples

Basic Usage

bash
# Add a task
cleo add "Implement user authentication" --priority high

# List tasks
cleo list

# Start a work session
cleo session start "Authentication Feature"

# Show current task context
cleo current

# Complete a task
cleo complete T1234

Using the MCP Server

CLEO includes a full MCP (Model Context Protocol) server for AI assistants:

bash
# Start the MCP server
cleo mcp

# Or configure in your MCP settings (Claude Desktop, etc.)
{
  "mcpServers": {
    "cleo": {
      "command": "cleo",
      "args": ["mcp"]
    }
  }
}

Development Setup

Prerequisites

  • Node.js >= 24.0.0
  • pnpm >= 10.30.0 (package manager)

Clone and Install

bash
# Clone the repository
git clone https://github.com/cleocode/cleo.git
cd cleo

# Install dependencies
pnpm install

# Build all packages
pnpm build

# Run tests
pnpm test

Package Development

bash
# Build a specific package
pnpm build:contracts
pnpm build:core
pnpm build:cleo

# Type checking
pnpm typecheck

# Linting
pnpm lint
pnpm lint:fix

Database Operations

bash
# Generate migrations
pnpm db:generate

# Open Drizzle Studio
pnpm db:studio

Architecture Overview

code
┌─────────────────────────────────────────────────────────────┐
│                    @cleocode/cleo                           │
│              CLI + MCP Server Entry Point                   │
└─────────────────────────────────────────────────────────────┘
                              │
┌─────────────────────────────────────────────────────────────┐
│                    @cleocode/core                           │
│     Tasks • Sessions • Memory • Orchestration • Lifecycle   │
└─────────────────────────────────────────────────────────────┘
                              │
        ┌─────────────────────┼─────────────────────┐
        │                     │                     │
┌───────▼───────┐   ┌────────▼────────┐   ┌────────▼────────┐
│   adapters    │   │     memory      │   │   orchestration │
│   sessions    │   │     brain       │   │   phases        │
│   tasks       │   │     sticky      │   │   lifecycle     │
│   compliance  │   │     inject      │   │   release       │
└───────────────┘   └─────────────────┘   └─────────────────┘
                              │
┌─────────────────────────────────────────────────────────────┐
│                  @cleocode/contracts                        │
│            Types • Interfaces • Contracts                   │
└─────────────────────────────────────────────────────────────┘
                              │
        ┌─────────────────────┼─────────────────────┐
        │                     │                     │
┌───────▼───────┐   ┌────────▼────────┐   ┌────────▼────────┐
│   adapters    │   │     agents      │   │     skills      │
│  (providers)  │   │  (protocols)    │   │ (definitions)   │
└───────────────┘   └─────────────────┘   └─────────────────┘

Key Features

Task Management

  • Hierarchical tasks with parent-child relationships
  • Priority levels and sizing estimates
  • Dependency tracking and blocker identification
  • Automatic sequencing and critical path analysis
  • Archive and restore functionality

Session Management

  • Contextual work sessions with automatic persistence
  • Session notes and progress tracking
  • Safe stop and checkpoint mechanisms
  • Briefing generation for context handoff

Memory Systems

  • Brain-like knowledge storage with semantic search
  • Sticky notes for ephemeral context
  • Memory bridges for cross-session persistence
  • Context injection for AI assistants

Agent Orchestration

  • Subagent spawning with protocol compliance
  • Wave-based parallel execution
  • Consensus workflows for multi-agent decisions
  • LOOM (Logical Order of Operations Methodology) lifecycle

Multi-Provider Support

  • Claude Code integration with statusline sync
  • OpenCode adapter with spawn hooks
  • Cursor support
  • Extensible adapter architecture

Commands Overview

CLEO provides 80+ commands organized into domains:

DomainCommands
Tasksadd, list, show, find, complete, update, delete, archive, start, stop, current, next
Sessionsession, briefing, phase, checkpoint, safestop
Memorymemory, memory-brain, observe, context, inject, sync, sticky, note
Checkvalidate, verify, compliance, doctor, analyze
Pipelinerelease, lifecycle, promote, upgrade, specification, roadmap, plan
Orchestrationorchestrate, ops, consensus, contribution, decomposition, implementation
Researchresearch, extract, web, docs
Nexusnexus, init, remote, push, pull, snapshot, export, import
Adminconfig, backup, skills, migrate, grade, map, commands

Contributing

We welcome contributions! Please see our Contributing Guide for details.

Development Workflow

  1. Fork the repository
  2. Create a feature branch (git checkout -b feature/amazing-feature)
  3. Make your changes
  4. Run tests (pnpm test)
  5. Commit with conventional commits (feat:, fix:, docs:, etc.)
  6. Push to your fork
  7. Open a Pull Request

Code Style

  • TypeScript with strict mode enabled
  • Biome for linting and formatting
  • Conventional commit messages
  • Comprehensive test coverage with Vitest

Documentation

Community

Support

If CLEO helps your workflow, consider supporting development:

ko-fi

License

MIT License - see LICENSE for details.

Star History

Star History Chart

常见问题

CLEO MCP Server 是什么?

面向独立开发者与 AI coding agents 的任务管理协议,采用双网关 2-gateway CQRS 模式提升协作与执行效率。

相关 Skills

MCP构建

by anthropics

Universal
热门

聚焦高质量 MCP Server 开发,覆盖协议研究、工具设计、错误处理与传输选型,适合用 FastMCP 或 MCP SDK 对接外部 API、封装服务能力。

想让 LLM 稳定调用外部 API,就用 MCP构建:从 Python 到 Node 都有成熟指引,帮你更快做出高质量 MCP 服务器。

平台与服务
未扫描109.6k

Slack动图

by anthropics

Universal
热门

面向Slack的动图制作Skill,内置emoji/消息GIF的尺寸、帧率和色彩约束、校验与优化流程,适合把创意或上传图片快速做成可直接发送的Slack动画。

帮你快速做出适配 Slack 的动图,内置约束规则和校验工具,少踩上传与播放坑,做表情包和演示都更省心。

平台与服务
未扫描109.6k

接口设计评审

by alirezarezvani

Universal
热门

审查 REST API 设计是否符合行业规范,自动检查命名、HTTP 方法、状态码与文档覆盖,识别破坏性变更并给出设计评分,适合评审接口方案和版本迭代前把关。

做API和架构方案时,它能帮你提前揪出接口设计问题并对齐最佳实践,评审视角系统,团队协作更省心。

平台与服务
未扫描9.0k

相关 MCP Server

Slack 消息

编辑精选

by Anthropic

热门

Slack 是让 AI 助手直接读写你的 Slack 频道和消息的 MCP 服务器。

这个服务器解决了团队协作中需要 AI 实时获取 Slack 信息的痛点,特别适合开发团队让 Claude 帮忙汇总频道讨论或发送通知。不过,它目前只是参考实现,文档有限,不建议在生产环境直接使用——更适合开发者学习 MCP 如何集成第三方服务。

平台与服务
82.9k

by netdata

热门

io.github.netdata/mcp-server 是让 AI 助手实时监控服务器指标和日志的 MCP 服务器。

这个工具解决了运维人员需要手动检查系统状态的痛点,最适合 DevOps 团队让 Claude 自动分析性能数据。不过,它依赖 NetData 的现有部署,如果你没用过这个监控平台,得先花时间配置。

平台与服务
78.3k

by d4vinci

热门

Scrapling MCP Server 是专为现代网页设计的智能爬虫工具,支持绕过 Cloudflare 等反爬机制。

这个工具解决了爬取动态网页和反爬网站时的头疼问题,特别适合需要批量采集电商价格或新闻数据的开发者。不过,它依赖外部浏览器引擎,资源消耗较大,不适合轻量级任务。

平台与服务
34.5k

评论