Google PageRank for AI agents. 25,000+ tools indexed.

phantom MCP Server

ghostwright/phantom

Score: 73.8 Rank #575 Agent Framework
Are you the maintainer of ghostwright/phantom? Claim this listing →

An AI co-worker with its own computer. Self-evolving, persistent memory, MCP server, secure credential collection, email identity. Built on the Claude Agent SDK.

Add AgentRank to Claude Code Discover and compare tools like ghostwright/phantom — your AI finds the right one automatically
Get API Access →
claude mcp add agentrank -- npx -y agentrank-mcp-server

Overview

ghostwright/phantom is a TypeScript MCP server licensed under Apache-2.0. An AI co-worker with its own computer. Self-evolving, persistent memory, MCP server, secure credential collection, email identity. Built on the Claude Agent SDK. Topics: ai-agents, ai-coworker, anthropic, autonomous-agents, bun, claude, docker, llm, mcp, self-evolution, slack, typescript.

Ranked #575 out of 29331 indexed tools.

In the top 2% of all indexed tools.

Has 1,190 GitHub stars.

Actively maintained with commits in the last week.

Ecosystem

TypeScript Apache-2.0 34,499 npm/wk
ai-agentsai-coworkeranthropicautonomous-agentsbunclaudedockerllmmcpself-evolutionslacktypescript

Score Breakdown

StarsFreshnessIssue HealthContributorsDependents
Stars 15% 1,190

1,190 stars → well-known project

Freshness 25% 1d ago

Last commit 1d ago → actively maintained

Issue Health 25% 14%

3/21 issues closed → many open issues

Contributors 10% 5

5 contributors → small team

Dependents 25% 0

No dependents → no downstream usage

npm Downloads 13% 34,499/wk

34,499 weekly installs → widely installed

PyPI Downloads N/A
Forks 140
Description Detailed
License Apache-2.0

Weights: Freshness 25% · Issue Health 25% · Dependents 25% · Stars 15% · Contributors 10% · How we score →

How to Improve

Issue Health high impact

You have 18 open vs 3 closed issues — triaging stale issues improves health

Dependents medium impact

No downstream dependents detected yet — adoption by other projects is the strongest trust signal

Badge all embed codes →

AgentRank score for ghostwright/phantom
[![AgentRank](https://agentrank-ai.com/api/badge/tool/ghostwright--phantom)](https://agentrank-ai.com/tool/ghostwright--phantom/?utm_source=badge&utm_medium=readme&utm_campaign=agentrank_badge)
<a href="https://agentrank-ai.com/tool/ghostwright--phantom/?utm_source=badge&utm_medium=readme&utm_campaign=agentrank_badge"><img src="https://agentrank-ai.com/api/badge/tool/ghostwright--phantom" alt="AgentRank"></a>

Embed Widget docs →

Embed a rich score widget on your site or blog.

<script src="https://agentrank-ai.com/embed.js" data-tool="ghostwright/phantom"></script>

Matched Queries

"mcp server""mcp-server"

From the README

<p align="center">
  
</p>

<h1 align="center">Phantom</h1>
<p align="center">An AI co-worker with its own computer.</p>

<p align="center">
  <a href="LICENSE"></a>
  
  <a href="https://hub.docker.com/r/ghostwright/phantom"></a>
  
</p>

<p align="center">
  <a href="https://ghostwright.dev/phantom">Website</a> &middot;
  <a href="https://ghostwright.dev/phantom">Get a Free Phantom</a> &middot;
  <a href="docs/">Docs</a> &middot;
  <a href="https://github.com/ghostwright/phantom/issues">Issues</a>
</p>

---

## The Idea

AI agents today are disposable. You open a chat, get an answer, close the tab, and the context is gone. Next time you start from scratch. Every session is day one.

Phantom takes a different approach: **give the AI its own computer.** A dedicated machine where it installs software, spins up databases, builds dashboards, remembers what you told it last week, and gets measurably better at your job every day. Your laptop stays yours. The agent's workspace is its own.

T
Read full README on GitHub →

Get the weekly AgentRank digest

Top movers, new tools, ecosystem insights — straight to your inbox.