🚀 MJOS v2.5.6 - Enterprise-Grade AI Operating System with Enhanced MCP Support & Bug Fixes. Perfect for Claude Desktop, Cursor, VS Code, and Augment. Features: Intelligent Memory System, Team Collaboration, Fixed MCP Tool Context Binding, Zero Resource L
Enterprise-grade AI team collaboration operating system with memory management, knowledge graphs, team coordination, and MCP protocol integration.
MJOS now supports Model Context Protocol (MCP) and can be used directly in Claude Desktop, Cursor, VS Code, and Augment!
# Run MCP server directly
npx mjos@latest mjos-mcp-server
# Or install globally
npm install -g mjos
{
"mcpServers": {
"mjos": {
"command": "npx",
"args": ["-y", "mjos@latest", "mjos-mcp-server"]
}
}
}
{
"mcpServers": {
"mjos": {
"command": "npx",
"args": ["-y", "mjos@latest", "mjos-mcp-server"]
}
}
}
📋 See MCP Configuration Guide for complete setup instructions for all supported clients.
npm install mjos
import { MJOS } from 'mjos';
async function main() {
// 创建MJOS实例
const mjos = new MJOS();
// 启动系统
await mjos.start();
// 存储记忆
const memoryId = mjos.getMemorySystem().store('重要信息', ['项目', '会议'], 0.8);
// 创建任务
const taskId = mjos.createTask('完成项目文档', '编写完整的API文档');
// 创建智能体
const agentId = mjos.createAgent({
name: '文档助手',
type: 'collaborative',
capabilities: [
{ name: 'writing', type: 'cognitive', parameters: {}, constraints: {} }
]
});
// 分配任务给智能体
const assignmentId = mjos.assignTaskToAgent(taskId, agentId);
// 查看系统状态
console.log(mjos.getStatus());
// 停止系统
await mjos.stop();
}
main().catch(console.error);
# 启动MJOS系统
npm run cli start
# 交互模式
npm run cli interactive
# 查看系统状态
npm run cli status
# 创建任务
npm run cli team create-task
# 查看团队成员
npm run cli team members
# 启动API服务器
npm run cli start --port 3000
# 获取系统状态
curl http://localhost:3000/api/v1/status
# 存储记忆
curl -X POST http://localhost:3000/api/v1/memory/store \
-H "Content-Type: application/json" \
-d '{"content": "重要信息", "tags": ["项目"], "importance": 0.8}'
# 创建任务
curl -X POST http://localhost:3000/api/v1/team/tasks \
-H "Content-Type: application/json" \
-d '{"title": "新任务", "description": "任务描述"}'
from mjos_sdk import MJOSSDK
sdk = MJOSSDK(api_endpoint="http://localhost:3000/api/v1")
# 存储记忆
memory_id = sdk.store_memory("重要信息", ["项目"], 0.8)
# 创建任务
task_id = sdk.create_task("新任务", "任务描述")
import com.mjos.MJOSSDK;
MJOSSDK sdk = new MJOSSDK("http://localhost:3000/api/v1", "api-key");
// 存储记忆
String memoryId = sdk.storeMemory("重要信息", Arrays.asList("项目"), 0.8, null);
// 创建任务
String taskId = sdk.createTask("新任务", "任务描述");
MJOS的记忆系统模拟人类记忆机制：
结构化知识存储和推理：
多智能体协作框架：
自动化业务流程：
┌─────────────────────────────────────────┐
│ 接口层 (Interface) │
├─────────────────────────────────────────┤
│ API Server │ CLI Tool │ Multi-SDK │
├─────────────────────────────────────────┤
│ 协作层 (Collaboration) │
├─────────────────────────────────────────┤
│ Agents │ Roles │ Team │ Communication │
├─────────────────────────────────────────┤
│ 核心层 (Core) │
├─────────────────────────────────────────┤
│ Memory │ Knowledge │ Context │ Reasoning │
├─────────────────────────────────────────┤
│ 基础设施层 (Infrastructure) │
├─────────────────────────────────────────┤
│ Storage │ Security │ Monitoring │ Config │
└─────────────────────────────────────────┘
// 存储记忆
memorySystem.store(content: any, tags: string[], importance: number): string
// 检索记忆
memorySystem.retrieve(id: string): Memory | undefined
// 查询记忆
memorySystem.query(query: MemoryQuery): Memory[]
// 获取统计
memorySystem.getStats(): MemoryStats
// 创建任务
createTask(title: string, description: string): string
// 分配任务
assignTask(taskId: string, memberId: string): boolean
// 获取团队统计
getTeamStats(): TeamStats
// 创建智能体
createAgent(definition: AgentDefinition): string
// 分配任务给智能体
assignTaskToAgent(taskId: string, agentId?: string): string
// 获取智能体状态
getAgent(agentId: string): Agent | undefined
# 运行所有测试
npm test
# 运行集成测试
npm run test:integration
# 生成覆盖率报告
npm run test:coverage
# 监视模式
npm run test:watch
# 数据库配置
MJOS_DB_HOST=localhost
MJOS_DB_PORT=5432
MJOS_DB_NAME=mjos
# Redis配置
MJOS_REDIS_HOST=localhost
MJOS_REDIS_PORT=6379
# 安全配置
MJOS_JWT_SECRET=your-secret-key
MJOS_ENCRYPTION_KEY=your-encryption-key
# 监控配置
MJOS_ENABLE_METRICS=true
MJOS_METRICS_PORT=9090
{
"mjos": {
"enableLearning": true,
"enableCollaboration": true,
"maxAgents": 50,
"maxMemories": 10000,
"defaultStorageProvider": "file",
"enableRealTimeMetrics": true
}
}
欢迎贡献代码！请查看 CONTRIBUTING.md 了解详细信息。
# 克隆仓库
git clone https://github.com/your-org/mjos.git
cd mjos
# 安装依赖
npm install
# 启动开发模式
npm run dev
# 运行测试
npm test
# 构建项目
npm run build
MIT License - 查看 LICENSE 文件了解详细信息。
FAQs
🚀 MJOS v2.5.6 - Enterprise-Grade AI Operating System with Enhanced MCP Support & Bug Fixes. Perfect for Claude Desktop, Cursor, VS Code, and Augment. Features: Intelligent Memory System, Team Collaboration, Fixed MCP Tool Context Binding, Zero Resource L
We found that mjos demonstrated a healthy version release cadence and project activity because the last version was released less than a year ago. It has 1 open source maintainer collaborating on the project.
Did you know?
Socket for GitHub automatically highlights issues in each pull request and monitors the health of all your open source dependencies. Discover the contents of your packages and block harmful activity before you install or update your dependencies.
Research
A supply chain attack on Axios introduced a malicious dependency, plain-crypto-js@4.2.1, published minutes earlier and absent from the project’s GitHub releases.
Research
Malicious versions of the Telnyx Python SDK on PyPI delivered credential-stealing malware via a multi-stage supply chain attack.
Security News
TeamPCP is partnering with ransomware group Vect to turn open source supply chain attacks on tools like Trivy and LiteLLM into large-scale ransomware operations.