ghostwright/phantom

팬텀 AI 동료가 자기 컴퓨터를 가진 경우.

웹사이트 · 무료 팬텀 받기 · 문서 · 쟁점

---

아이디어

오늘날 AI 에이전트는 일회용입니다. 채팅을 열고 답변을 받으면 탭을 닫으면 맥락이 사라집니다. 다음에는 처음부터 다시 시작하세요. 모든 세션이 첫날입니다.

Phantom은 다른 접근법을 취합니다: **AI에게 전용 컴퓨터를 부여하세요. ** 소프트웨어를 설치하고, 데이터베이스를 돌리고, 대시보드를 구축하며, 지난주에 말한 내용을 기억하며 매일 업무 실력이 눈에 띄게 나아지는 전용 기계입니다. 당신의 노트북은 당신의 것입니다. 에이전트의 작업 공간은 독립적입니다.

이것은 챗봇이 아닙니다. Slack에서 실행되고, /chat에 웹 채팅 인터페이스를 하며, 자체 이메일 주소를 가지고 있고, 자체 도구를 만들고, 허락 없이 인프라를 구축하는 동료입니다. 저희 말만 믿지 마세요 - 아래로 스크롤해서 Phantoms가 실제로 어떤 프로덕션 팬텀을 구축했는지 확인해 보세요.

이게 실제로 어떤 모습일지

이건 목업이 아니에요. 생산 중인 팬텀 인스턴스에서 일어난 일이에요.

처음부터 분석 플랫폼을 구축했습니다

팬텀이 데이터 분석을 돕도록 요청받았다.

Phantom An AI co-worker with its own computer.

Website · Get a Free Phantom · Docs · Issues

---

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.

This is not a chatbot. It is a co-worker that runs on Slack, has a web chat interface at /chat, has its own email address, creates its own tools, and builds infrastructure without asking for permission. Don’t take our word for it - scroll down to see what production Phantoms have actually built.

What This Actually Looks Like

These are not mockups. They happened on production Phantom instances.

Built an analytics platform from scratch

A Phantom was asked to help with data analysis. It installed ClickHouse on its own VM, downloaded the full Hacker News dataset, loaded 28.7 million rows spanning 2007-2021, built an analytics dashboard with interactive charts, and created a REST API to query the data. Then it registered that API as an MCP tool so it could use it in future sessions and other agents could query it too.

Nobody asked it to build any of this. It identified analytics as useful and built the entire stack.

28.7 million items. 755K unique authors. 4.3 million stories. Built, loaded, and served by a Phantom on its own machine.

Extended itself with a channel it was never built with

Phantom ships with Slack, Telegram, Email, and Webhook channels. It does not ship with Discord. When asked “Can I talk to you on Discord?”, the Phantom said: “Not right now. Discord isn’t wired up. That said, I could build it.”