经 AI Skill Hub 精选评估，phantom MCP工具 获评「强烈推荐」。已获得 1.4k 颗 GitHub Star，这款AI工具在功能完整性、社区活跃度和易用性方面表现出色，AI 评分 8.2 分，适合有一定技术背景的用户使用。
phantom MCP工具 是一款基于 TypeScript 开发的开源工具，专注于 MCP、AI代理、自主智能 等核心功能。作为 GitHub 开源项目，它拥有活跃的社区支持和持续的版本迭代，代码完全透明可审计，支持本地部署以保护数据隐私。无论是个人使用还是集成到企业工作流，都能提供稳定可靠的解决方案。
phantom MCP工具 是一款基于 TypeScript 开发的开源工具，专注于 MCP、AI代理、自主智能 等核心功能。作为 GitHub 开源项目，它拥有活跃的社区支持和持续的版本迭代，代码完全透明可审计，支持本地部署以保护数据隐私。无论是个人使用还是集成到企业工作流，都能提供稳定可靠的解决方案。
# 方式一：npm 全局安装 npm install -g phantom # 方式二：npx 直接运行（无需安装） npx phantom --help # 方式三：项目依赖安装 npm install phantom # 方式四：从源码运行 git clone https://github.com/ghostwright/phantom cd phantom npm install npm start
# 命令行使用
phantom --help
# 基本用法
phantom [options] <input>
# Node.js 代码中使用
const phantom = require('phantom');
const result = await phantom.run(options);
console.log(result);
# phantom 配置说明 # 查看配置选项 phantom --config-example > config.yml # 常见配置项 # output_dir: ./output # log_level: info # workers: 4 # 环境变量（覆盖配置文件） export PHANTOM_CONFIG="/path/to/config.yml"
<p align="center"> <img src="docs/assets/phantom.svg" alt="Phantom" width="120" height="120" /> </p>
An AI co-worker with its own computer.
<p align="center"> <a href="LICENSE"><img src="https://img.shields.io/badge/license-Apache%202.0-blue.svg" alt="License"></a> <img src="https://img.shields.io/badge/tests-1819%20passed-brightgreen.svg" alt="Tests"> <a href="https://hub.docker.com/r/ghostwright/phantom"><img src="https://img.shields.io/docker/pulls/ghostwright/phantom.svg" alt="Docker Pulls"></a> <img src="https://img.shields.io/badge/version-0.20.2-orange.svg" alt="Version"> </p>
<p align="center"> <a href="https://ghostwright.dev/phantom">Website</a> · <a href="https://ghostwright.dev/phantom">Get a Free Phantom</a> · <a href="docs/">Docs</a> · <a href="https://github.com/ghostwright/phantom/issues">Issues</a> </p>
---
| Feature | Why it matters |
|---|---|
| **Its own computer** | Your laptop stays yours. The agent installs software, runs 24/7, and builds infrastructure on its own machine. |
| **Bring your own model** | Anthropic, Z.AI (GLM-5.1), OpenRouter, Ollama, vLLM, LiteLLM, or any Anthropic Messages API compatible endpoint. Pick your backend in YAML, same agent everywhere. |
| **Self-evolution** | The agent rewrites its own config after every session, validated by LLM judges. Day 30 knows things Day 1 didn't. |
| **Persistent memory** | Three tiers of vector memory. Mention something on Monday, it uses it on Wednesday. No re-explaining. |
| **Dynamic tools** | Creates and registers its own MCP tools at runtime. Tools survive restarts and work across sessions. |
| **Encrypted secrets** | AES-256-GCM encrypted forms with magic-link auth. No plain-text credentials in config files. |
| **Email identity** | Every Phantom has its own email address. Send reports to people outside your Slack workspace. |
| **Web chat** | A full browser-based chat client at /chat with SSE streaming, file attachments, and Web Push notifications. No Slack required. |
| **Shareable pages** | Generates dashboards and tools on a public URL with auth. Share a link, anyone can see it. |
| **MCP server** | Claude Code connects to your Phantom. Other Phantoms connect to your Phantom. It is an API, not a dead end. |
```bash curl -fsSL https://raw.githubusercontent.com/ghostwright/phantom/main/docker-compose.user.yaml -o docker-compose.yaml curl -fsSL https://raw.githubusercontent.com/ghostwright/phantom/main/.env.example -o .env
Phantom is not just for engineers. It is for anyone who wants an AI that remembers, learns, and builds things you can actually share.
The key difference: when an AI runs on your laptop, everything it builds is trapped on localhost. Only you can see it. Phantom runs on a VM with a public domain. Dashboards, tools, pages, APIs - they all get a URL you can send to your team, your manager, or your clients. Your laptop is not a server. Phantom's VM is.
docker compose up -d ```
Your Phantom is running. Qdrant starts for memory, Ollama pulls the embedding model, and the agent boots. Check health at http://localhost:3100/health. With Slack configured, it DMs you when it's ready. Add RESEND_API_KEY for email sending. See Getting Started for full setup.
Security note, Docker socket mount:docker-compose.yamlmounts/var/run/docker.sockinto the Phantom container so it can spawn sibling containers (e.g. sandboxed code execution). This is an intentional architectural trade-off: the socket grants the container root-equivalent access to the Docker daemon, which means a compromised Phantom process could create, modify, or destroy any container on the host. Mitigations: run Phantom on a dedicated machine or VM (not your personal workstation), and do not expose the host's Docker socket to untrusted workloads. See docs/security.md for the full threat model.
bun run phantom init --yes
export ANTHROPIC_API_KEY=sk-ant-...
Phantom是创新的AI代理框架，融合MCP协议和自主演进机制。代码质量好、社区活跃，但需关注自主执行的安全性设计。
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。
✅ Apache 2.0 — 宽松开源协议，可商用，需保留版权声明和 NOTICE 文件，含专利授权条款。
AI Skill Hub 点评：phantom MCP工具 的核心功能完整，质量优秀。对于AI爱好者来说，这是一个值得纳入个人工具库的选择。建议先在非生产环境试用，再逐步推广。
| 原始名称 | phantom |
| 原始描述 | 开源MCP工具：An AI co-worker with its own computer. Self-evolving, persistent memory, MCP ser。⭐1.4k · TypeScript |
| Topics | MCPAI代理自主智能持久记忆AnthropicTypeScript |
| GitHub | https://github.com/ghostwright/phantom |
| License | Apache-2.0 |
| 语言 | TypeScript |
收录时间：2026-05-16 · 更新时间：2026-05-19 · License：Apache-2.0 · AI Skill Hub 不对第三方内容的准确性作法律背书。