智能代理操作系统 是 AI Skill Hub 本期精选MCP工具之一。综合评分 7.5 分,整体质量较高。我们推荐使用将其纳入你的 AI 工具库,帮助提升工作效率。
智能代理操作系统 是一款遵循 MCP(Model Context Protocol)标准协议的 AI 工具扩展。通过 MCP 协议,它可以让 Claude、Cursor 等主流 AI 客户端直接访问和操作外部工具、数据源和服务,实现 AI 能力的无缝扩展。无论是文件操作、数据库查询还是 API 调用,都可以通过自然语言在 AI 对话中直接触发,极大提升生产效率。
智能代理操作系统 是一款遵循 MCP(Model Context Protocol)标准协议的 AI 工具扩展。通过 MCP 协议,它可以让 Claude、Cursor 等主流 AI 客户端直接访问和操作外部工具、数据源和服务,实现 AI 能力的无缝扩展。无论是文件操作、数据库查询还是 API 调用,都可以通过自然语言在 AI 对话中直接触发,极大提升生产效率。
# 方式一:通过 Claude Code CLI 一键安装
claude skill install https://github.com/benjaminkernbaum-ux/stoic-agentos
# 方式二:手动配置 claude_desktop_config.json
{
"mcpServers": {
"--------": {
"command": "npx",
"args": ["-y", "stoic-agentos"]
}
}
}
# 配置文件位置
# macOS: ~/Library/Application Support/Claude/claude_desktop_config.json
# Windows: %APPDATA%/Claude/claude_desktop_config.json
# 安装后在 Claude 对话中直接使用 # 示例: 用户: 请帮我用 智能代理操作系统 执行以下任务... Claude: [自动调用 智能代理操作系统 MCP 工具处理请求] # 查看可用工具列表 # 在 Claude 中输入:"列出所有可用的 MCP 工具"
// claude_desktop_config.json 配置示例
{
"mcpServers": {
"________": {
"command": "npx",
"args": ["-y", "stoic-agentos"],
"env": {
// "API_KEY": "your-api-key-here"
}
}
}
}
// 保存后重启 Claude Desktop 生效
<p align="center"> <h1 align="center">⚡ Stoic AgentOS</h1> <p align="center"><strong>Open-Source Observability & Memory for AI Agent Fleets</strong></p> <p align="center">Trace, monitor, and persist knowledge across autonomous AI agents — the open-source LLMOps platform that fits alongside Langfuse, Helicone, and Phoenix.</p> </p>
<p align="center"> <a href="https://github.com/benjaminkernbaum-ux/stoic-agentos/blob/master/LICENSE"> <img src="https://img.shields.io/badge/License-MIT-9b59ff.svg" alt="MIT License"></a> <a href="https://github.com/benjaminkernbaum-ux/stoic-agentos/actions/workflows/ci.yml"><img src="https://github.com/benjaminkernbaum-ux/stoic-agentos/actions/workflows/ci.yml/badge.svg?branch=master" alt="CI"></a> <a href="https://www.npmjs.com/package/stoic-agentos-sdk"><img src="https://img.shields.io/npm/v/stoic-agentos-sdk?logo=npm&logoColor=white&label=npm&color=CB3837" alt="npm version"></a> <a href="https://www.npmjs.com/package/stoic-agentos-sdk"><img src="https://img.shields.io/npm/dm/stoic-agentos-sdk?logo=npm&logoColor=white&label=downloads&color=blue" alt="npm downloads"></a> <a href="https://pypi.org/project/stoic-agentos-sdk/"><img src="https://img.shields.io/pypi/dm/stoic-agentos-sdk?logo=python&logoColor=white&label=pypi&color=3776AB" alt="PyPI downloads"></a> <br/> <a href="https://github.com/benjaminkernbaum-ux/stoic-agentos/graphs/commit-activity"><img alt="Commits last month" src="https://img.shields.io/github/commit-activity/m/benjaminkernbaum-ux/stoic-agentos?labelColor=%2032b583&color=%2012b76a"></a> <a href="https://github.com/benjaminkernbaum-ux/stoic-agentos/issues?q=is%3Aclosed"><img alt="Issues closed" src="https://img.shields.io/github/issues-search?query=repo%3Abenjaminkernbaum-ux%2Fstoic-agentos%20is%3Aclosed&label=issues%20closed&labelColor=%207d89b0&color=%205d6b98"></a> <a href="https://github.com/benjaminkernbaum-ux/stoic-agentos/discussions/"><img alt="Discussion posts" src="https://img.shields.io/github/discussions/benjaminkernbaum-ux/stoic-agentos?labelColor=%209b8afb&color=%207a5af8"></a> <a href="https://github.com/benjaminkernbaum-ux/stoic-agentos/stargazers"><img src="https://img.shields.io/github/stars/benjaminkernbaum-ux/stoic-agentos?style=flat&logo=github&labelColor=%2332b583&color=%2312b76a" alt="GitHub Stars"></a> <a href="https://github.com/benjaminkernbaum-ux/stoic-agentos/network/members"><img src="https://img.shields.io/github/forks/benjaminkernbaum-ux/stoic-agentos?style=flat&logo=github&labelColor=%235462eb&color=%234040b0" alt="GitHub Forks"></a> <br/> <a href="https://twitter.com/intent/follow?screen_name=stoicagentos" target="_blank"><img src="https://img.shields.io/twitter/follow/stoicagentos?logo=X&color=%20%23f5f5f5" alt="follow on X"></a> <a href="https://www.linkedin.com/company/stoicagentos/" target="_blank"><img src="https://custom-icon-badges.demolab.com/badge/LinkedIn-0A66C2?logo=linkedin-white&logoColor=fff" alt="follow on LinkedIn"></a> <a href="https://stoicagentos.com"><img src="https://img.shields.io/badge/dashboard-live-brightgreen?logo=vercel&logoColor=white" alt="Dashboard Live"></a> </p>
<p align="center"> <a href="./README.md"><img alt="English" src="https://img.shields.io/badge/English-d9d9d9"></a> <a href="./README.cn.md"><img alt="简体中文" src="https://img.shields.io/badge/简体中文-d9d9d9"></a> <a href="./README.ja.md"><img alt="日本語" src="https://img.shields.io/badge/日本語-d9d9d9"></a> <a href="./README.kr.md"><img alt="한국어" src="https://img.shields.io/badge/한국어-d9d9d9"></a> <a href="./README.es.md"><img alt="Español" src="https://img.shields.io/badge/Español-d9d9d9"></a> <a href="./README.pt.md"><img alt="Português" src="https://img.shields.io/badge/Português-d9d9d9"></a> </p>
<p align="center"> <img src="launch-assets/01_hero.png" alt="Stoic AgentOS Dashboard" width="800" /> </p>
---
| Feature | Description |
|---|---|
| 🤖 **Agent Monitoring** | Real-time status, heartbeats, error tracking for your entire fleet |
| 🧠 **Knowledge Persistence** | Agents remember decisions across sessions — no more re-learning |
| 📊 **Usage Analytics** | Observations/month, agent runs, error rates at a glance |
| 📦 **Multi-Workspace** | Group agents by project, repo, or team |
| ⚡ **Auto-Capture** | wrapAgent() logs start, success, and errors automatically |
| 🔑 **API Key Management** | Generate, list, and revoke keys from the dashboard |
| 💳 **Usage-Based Billing** | Free tier with real limits, upgrade when you need more |
| 🔒 **Row-Level Security** | Full RLS on Supabase — your data is isolated per org |
| 🧠 **Claude-Powered Insights** | Auto-summarize activity (Haiku 4.5) and diagnose failing agents (Sonnet 4.6 + thinking) |
| 🔐 **BYOK** | Bring your own Anthropic key — stored encrypted in Supabase Vault, never plaintext |
npm install
npm install stoic-agentos-sdk
git clone https://github.com/benjaminkernbaum-ux/stoic-agentos.git cd stoic-agentos cp .env.selfhost.example .env.selfhost
Sign up at stoicagentos.com → Dashboard → Settings → Generate Key
| Method | Endpoint | Auth | Description |
|---|---|---|---|
POST | /api/v1/observations | API Key | Create observation |
GET | /api/v1/observations | API Key | List observations |
POST | /api/v1/agents | API Key | Register agent |
GET | /api/v1/agents | API Key | List agents |
POST | /api/v1/agents/heartbeat | API Key | Agent heartbeat (upsert) |
POST | /api/v1/knowledge-items | API Key | Create knowledge item |
POST | /api/v1/workspaces | API Key | Create workspace |
GET | /api/v1/stats | API Key | Dashboard stats |
POST | /api/v1/api-keys | JWT | Generate API key |
DELETE | /api/v1/api-keys/:id | JWT | Revoke API key |
POST | /api/v1/billing/checkout | JWT | Start Stripe checkout |
POST | /api/v1/billing/portal | JWT | Open customer portal |
import { AgentOS } from 'stoic-agentos-sdk';
// Initialize
const os = new AgentOS({ apiKey: 'sk_live_xxx', workspace: 'my-app' });
// Core methods
os.capture({ type, title, content, metadata }) // Log observation
os.wrapAgent(name, fn) // Auto-monitor function
os.getObservations({ limit, type }) // Query observations
os.getStats() // Dashboard stats
// Claude-powered insights (v2.1+)
await os.summarize({ hours: 168 }) // AI briefing of recent activity
await os.analyzeAgent(agentId) // Diagnose an agent's health
await os.ask('Why did the email-agent fail?') // Free-form Q&A
docker compose -f docker-compose.selfhost.yml up -d ```
What you get: - 🔌 API Server (Express + TypeScript) → http://localhost:4444 - 🛡️ Non-root container, health checks, auto-restart - 📦 512MB memory limit, optimized for single-instance - 🔑 Optional: Stripe billing, Anthropic AI, Upstash Redis
For the dashboard frontend, run npm run dev in the project root or deploy to Vercel/Netlify.
See self-hosting docs for Kubernetes and Terraform guides.
---
AgentOS uses Anthropic Claude for AI-powered insights — summarizing observations, diagnosing agent failures, answering free-form questions about your fleet.
Models: Haiku 4.5 for fast summaries, Sonnet 4 with adaptive thinking for deep diagnosis.
Three surfaces: - API: POST /insights/{summarize,analyze-agent,ask} — see API Reference - SDK: os.summarize(), os.analyzeAgent(id), os.ask(q) (above) - MCP server: agentos_summarize_observations, agentos_analyze_agent, agentos_ask tools
BYOK (Bring Your Own Key): Customers can route inference through their own Anthropic account from Settings → Anthropic API Key. Keys are stored encrypted in Supabase Vault (vault.secrets, pgsodium at rest) and accessed only by the API's service role. When no per-org key is set, the platform falls back to the ANTHROPIC_API_KEY env var.
Cost tracking: Every Claude call is logged to anthropic_usage with token counts and cache hits. The Settings tab shows call count, token usage, and estimated cost over a 7/30/90-day window.
Caching: All requests use cache_control: { type: 'ephemeral' } so repeated system prompts hit the prefix cache at ~10% of input cost.
Stoic AgentOS 是专为 AI Agent 集群打造的操作系统。它提供了一个统一的控制面板,旨在帮助开发者对大规模 AI Agent 舰队进行实时监控、编排以及知识持久化管理,确保您的 Agent 在复杂任务中保持高效且有序的运行状态。
Stoic AgentOS 提供全方位的 Agent 管理能力:支持实时监控 Agent 的运行状态、心跳及错误追踪;具备知识持久化功能,让 Agent 能够跨会话记忆决策,避免重复学习;内置 Usage Analytics 仪表盘,可直观查看每月观测值、运行次数及错误率;同时支持 Multi-Workspace 功能,方便按项目或团队对 Agent 进行分组管理。
在开始使用之前,请确保您的开发环境已安装 npm,并具备基础的 Node.js 运行环境,以便进行依赖包的安装与项目的构建。
您可以通过 npm 快速集成 Stoic AgentOS。请在您的项目根目录下运行命令:`npm install stoic-agentos-sdk`,即可将 SDK 添加到您的项目中进行开发。
快速上手指南:首先通过 `npm install stoic-agentos-sdk` 安装 SDK。随后在代码中引入 `AgentOS` 类,并使用您的 API Key 进行初始化。您可以调用 `os.capture` 来记录观测数据,或使用 `os.wrapAgent` 自动监控特定函数的执行情况,实现 Agent 行为的自动化记录。
Stoic AgentOS 提供完善的 RESTful API 接口,所有请求均需通过 API Key 进行身份验证。开发者可以通过 `POST /api/v1/observations` 创建观测记录,使用 `GET /api/v1/observations` 获取列表,并通过 `POST /api/v1/agents` 注册新的 Agent,实现对 Agent 数据的精细化管理。
Stoic AgentOS 深度集成了 Anthropic Claude 模型,为您的 Agent 集群提供 AI 驱动的洞察力。系统利用 Haiku 4.5 进行快速摘要,并配合具备自适应思维能力的 Sonnet 4.6 进行深度故障诊断。通过 API 接口,您可以针对观测数据进行自由提问,实现对 Agent 运行状态的智能化分析与问答。
高质量的AI代理管理工具
该工具未明确声明开源协议,商业使用前请联系原作者确认授权范围,避免侵权风险。
AI Skill Hub 为第三方内容聚合平台,本页面信息基于公开数据整理,不对工具功能和质量作任何法律背书。
建议在沙箱或测试环境中充分验证后,再部署至生产环境,并做好必要的安全评估。
经综合评估,智能代理操作系统 在MCP工具赛道中表现稳健,质量良好。如果你已有明确的使用需求,可以直接上手体验;如果还在评估阶段,建议对比同类工具后再做决策。
| 原始名称 | stoic-agentos |
| 原始描述 | 开源MCP工具:The Operating System for AI Agent Fleets - monitor, orchestrate, and persist kno。⭐6 · JavaScript |
| Topics | ai-agentsai-opsjavascript |
| GitHub | https://github.com/benjaminkernbaum-ux/stoic-agentos |
| 语言 | JavaScript |
收录时间:2026-05-25 · 更新时间:2026-05-30 · License:未公布 · AI Skill Hub 不对第三方内容的准确性作法律背书。
选择 Agent 类型,复制安装指令后粘贴到对应客户端