Claude Code, Cursor 및 기타 AI 도구에 대한 Persistent 컨텍스트. 데이터베이스를 건너, MCP 서버, 간단한 마크 다운 파일과 좋은 ol의 git에 대한 embeddings.

** 경고:** 이것은 PUBLIC 템플릿입니다. 당신이 그것을 복제하고 메모를 추가하면, 개인 버전을 공개 저장소로 밀어하지 마십시오. 당신의 기억은 비밀을 포함 할 것입니다 (아랍어 개인 비밀 및 보안 위험 비밀), 개인 정보 및 작업 스타일. 로컬을 유지하거나 새로운 사설을 밀어. · ** GitHub의 "Fork"버튼을 사용하지 마십시오 ** - 공공 저장소의 포크는 개인을 만들 수 없습니다. 대신 git clone를 사용하십시오.

두 배는 무엇입니까?

AI 조수는 세션 사이에 모든 것을 잊습니다. 엔지니어링 결정 (나는 특히 중요 한 생각), 코딩 패턴, 프로젝트 컨텍스트.

두 배는 당신이 통제하는 organised markdown 파일로 이것을 해결합니다. AI 조수에 대한 두 번째 뇌로 생각하십시오.

왜 “더블”? Dostoevsky의 소설 "두 배"후 이름 - 그것은 당신의 두 번째 자. 엔지니어링 및 연구뿐만 아니라 비즈니스 아이디어, 개인 노트, 취미, 워크플로우 환경.

키 기능

Double: External Personal Memory for AI

Persistent context for Claude Code, Cursor, and other AI tools. Skips the database, MCP servers, embeddings for simple markdown files and good ol’ git.

WARNING: This is a PUBLIC template. Once you clone it and add your notes, DO NOT push your personal version to a public repo. Your memory will contain secrets (both dark personal secrets and security risk secrets), personal information and your working style. Keep it local or push to a NEW private repo.

DO NOT use GitHub’s “Fork” button - forks of public repos cannot be made private. Use git clone instead (see Quick Start below).

What is Double?

AI assistants forget everything between sessions. Your engineering decisions (which I think are especially important), coding patterns, project context.

Double solves this with organised markdown files that you control. Think of it as a second brain for your AI assistant.

Why “Double”? Named after Dostoevsky’s novel “The Double” - it’s your second self. Not just engineering and research, but business ideas, personal notes, hobbies, workflow preferences.

Key Features

• Smart routing: /sync only loads files relevant to your work - Python session won’t load iOS context
• Concise capture: /handoff writes terse, reusable insights (not verbose essays)
• Context efficient: Compressed memory files reduce token overhead by ~65% while keeping essential knowledge
• No dependencies: Just markdown files and git

Make It Yours

This is a template, not a rigid system. The folder structure, commands, and workflows here are a starting point based on one person’s working style. You should heavily customise it:

• Rename folders to match your mental model
• Delete categories you don’t need (maybe you don’t track business ideas or research)
• Add new ones that fit your work (design/, writing/, client-work/, whatever)
• Modify commands to match your workflow
• Change the rules in meta/ to fit your style

The only critical parts are:

1. Organised markdown files you control
2. A capture → process → load workflow
3. Using absolute paths (~/double/) in commands

Everything else? Change it.

Folder Structure

~/double/
├── business/        # Ideas, metrics, product decisions
├── engineering/     # Technical patterns, best practices, lessons learned
├── tasks/           # Active work, backlog, waiting
├── projects/        # Project-specific context and decisions
├── research/        # Intelligence on companies, people, markets
├── personal/        # Writing style, preferences, workflows
├── meta/            # System rules, processed entries, changelog
└── .claude/
    ├── commands/    # Workflow commands that load context
    └── skills/      # Forked skills (tangent, etc.)

Why ~/double/ in Your Home Directory?