JMacCyber

Jmac Memory OS — Documentation skill for Claude Code

Documentation community

Connect your models and chats together with one central git memory.

How to install Jmac Memory OS

This entry records only its repository, not the path inside it, so there is no exact command to give. Open JMacCyber/jmac-memory-os and copy the folder into ~/.claude/skills/, or the file into ~/.claude/agents/.

What Jmac Memory OS does

Connect your models and chats together with one central git memory. Plain Markdown facts in a git repo you own — Claude Code, ChatGPT, Cursor, Codex and anything that uses APIs, Integrations or MCPs reading the same folder. No server, no database, no account.

Alternatives in Documentation

PDF — Extract text, create PDFs, merge/split documents, and handle forms 94.1k ★
会话管理（Session Manager）需求文档（PRD / Markdown） — 目标：对 Codex / Claude Code 的本地会话记录进行可视化管理，并提供“一键复制 / 一键终端恢复”能力 31.7k ★
CC GUI（Claude Or Codex） — 原名：Claude Code GUI 简体中文 · English <a href="https://trendshift.io/repositories/19332" target="_bla 2.2k ★

README

JMac Memory OS — Git Memory

**Connect your models and chats together with one central git memory.**

![One memory, every model: Claude Code, Codex, Cursor and Copilot read the folder directly; ChatGPT, Claude, Gemini, Grok and Perplexity connect through an API, an integration or MCP; all of them point at one git repo you own](docs/one-memory.svg)

Your AI assistants forget everything between sessions. This gives them one memory, in a git repo you own, that every one of them can read.

Write a fact in Claude Code. Ask ChatGPT about it. Get it back.

python3 bin/memos-init ~/my-memory --git

That makes a repo. Push it to a **private** GitHub repo, connect your tools, and they share one memory. No server, no database, no account with anyone, no subscription. The memory is markdown files in your own git.

Why a git repo

Because nearly every AI client can already read one, and most can write to one.

The table below is read from vendor documentation on 21 September 2026. Claude Code is the one row tested on a real repo. Vendors add and drop connector support often, so check your own client before you build on a row.

Client	Read	Write
Claude Code, Codex, Cursor, Gemini CLI, Copilot, Windsurf, Aider	Yes	Yes
ChatGPT	Yes	Yes
Claude, Gemini, Grok, Mistral Vibe, Perplexity, M365 Copilot	Yes, via connector	Yes, via connector
Amazon Q, DeepSeek Harness, Qwen Chat	Yes, via connector	Yes, via connector

"Via connector" means you point the client at your repo with whatever it supports: a GitHub integration, the GitHub API, or GitHub's hosted MCP server. All three read the same folder. You host nothing.

Two with no connector surface in their documentation on that date: Meta AI and the DeepSeek consumer app.

The format in one screen

memory/
  INDEX.md                  one line per live memory
  ships-on-fridays.md       one memory, one fact
  archive/
    postgres-is-the-database.2026-09-21.md