v0.1.3 — Live on PyPI · VS Code Marketplace

The Future of Git.

Version-control your AI assistant's context. Diff sessions. Roll back mistakes. Sync to your team.

Python 3.8+
memgit — zsh~/projects/my-app
🔒Local-first — nothing leaves your machine by default📖MIT open source — every line auditable on GitHub🚫Zero telemetry — no call-home, no analyticsSHA-256 verified — cryptographic integrity on every object

Works with the AI tools you already use

Claude CodeMCP + auto-sync
Cursor.cursorrules
VS CodeMarketplace
Gemini CLIGEMINI.md
Copilotvia HTTP API
Codex CLIinstructions.md

The Problem

Your AI starts from zero. Every. Single. Session.

01
💡

You teach it everything

Your AI learns your architecture, your team's conventions, the bugs you've already solved. It gets smart. The session is productive.

02
●●●

Session ends.

Context gone. The AI assistant's memory evaporates. Everything it learned about your codebase — gone.

03
🔄

You explain it again.

Re-architect in chat. Re-establish your conventions. Redo the same debugging explanations. Every. Single. Session.

“It's 2005 — the year before git — for AI context management. Nobody has built the version control layer yet.”

How it works

Every session. Versioned.

Every memory change is tracked. Roll back, diff, search — exactly like you do with code.

$ memgit log
◉ c3a891f "Added React hooks rules + fixed routing memory" 2h ago
│ memories: +3 added, 1 modified
◉ b7f3e2a "Removed stale API endpoint, updated auth context" yesterday
│ memories: 1 removed, 2 modified
◉ a1d9f3c "Fixed prefer-callbacks rule — was causing errors" 2 days ago
│ memories: 1 modified
◉ 9d1c4e8 "Initial import from claude-code (108 memories)" Jul 1
memories: 108 added

Token Savings

95% fewer tokens. Same context quality.

claude.md loads everything on every session. memgit uses BM25 relevance scoring to load only the 8 memories most relevant to your current task.

95%
token reduction
$31
saved/year at 10 sessions/week

* Numbers from memgit stats on a real 108-memory store

claude.md (all memories)
12,840 tokens$0.064/session
mem-search (top-20 obs)
6,100 tokens$0.031/session
memgit BM25 top-8
640 tokens$0.003/session

Multi-IDE Support

One memory store. Works everywhere.

Write a memory in Claude Code. Your Cursor session has it in 2 seconds. Your Gemini session too.

Claude Codelive
MCP server

Auto-sync hook on session end. 5 native tools: search, write, forget, log, diff.

Cursorlive
.cursorrules injection

memgit injects relevant context into .cursorrules before each session.

VS Codelive
Marketplace Extension

TreeView sidebar, memory diff viewer, vscode.lm tool registration.

Windsurflive
.windsurfrules

Same injection pattern as Cursor. Auto-detects Windsurf config path.

Gemini CLIcoming
GEMINI.md + tools.json

Section-marker injection + native tool definitions for Gemini 2.5 Pro.

JetBrainscoming
AI Assistant plugin

AIAssistantContextProvider + Tool Window (Active / History / Threads).

Codex CLIcoming
instructions.md

Injects relevant context into .openai/instructions.md before each run.

ChatGPT / Any LLMlive
HTTP API

OpenAPI 3.1 HTTP server. Any LLM with tool-use can call memgit's REST API.

The Future of Git

Git was invented because code needed history.
memgit was invented because AI context does too.

In 1991, Linus Torvalds was frustrated. Code was shared as patches emailed between developers. No way to see who changed what, no way to roll back a mistake, no way to merge two people's work. So he built git — every change became a permanent, addressable object.

That same frustration exists today — but for AI context.

Your AI assistant accumulates knowledge: your architecture decisions, your team's coding conventions, the bugs you've already solved. But when the session ends, it's gone. The next session starts blank. Your colleague's Cursor has no idea what your Claude figured out last week. When a “helpful” instruction turns out to be wrong, you can't roll it back.

We're in 2005. The year before git. For AI context management.

memgit is the missing layer. Every piece of AI context becomes a versioned object with a hash. Every session creates a checkpoint. memgit diff HEAD~1 HEAD shows what your AI learned today. memgit push syncs your entire context to your team.

The teams that figure this out first will have an AI advantage that compounds with every session. Their AI knows what yours doesn't. That gap widens every week.

In ten years, every engineering team will have a shared AI memory repository — versioned, audited, and as foundational as their code repository. memgit is the tool that makes that possible today.

1991
git invented — code gets version history
2008
GitHub launches — teams collaborate on code
2024
AI IDEs everywhere — developers use AI daily
2026
memgit — AI context gets version history
← YOU ARE HERE
20??
Team AI memory repos, audited AI decisions

Security & Privacy

Built to be trusted.

Your AI context contains your architecture decisions, your team's conventions, your business logic. We take that seriously.

🔒

Local-first. Always.

Your memories live in .memgit/ on your own machine. By default, zero bytes leave your computer. The free tier is completely offline — no account, no server, no network calls.

Verified: no outbound connections in free tier
📖

100% open source

Every line of the CLI, TOON parser, MCP server, and VS Code extension is MIT licensed and on GitHub. Read the code, audit it, fork it. Nothing is hidden behind a build step.

github.com/code4161/memgit
📄

Human-readable format

TOON is plain text. Open .memgit/objects/ in any editor. grep it, diff it with standard tools, commit it to your own git repo. No binary blobs, no proprietary encoding.

$ cat .memgit/objects/ab/c123 → readable
🚫

Zero telemetry

The CLI sends no analytics, crash reports, or usage metrics. There is no call-home mechanism. You can run memgit on an air-gapped machine and it works identically.

Confirmed: grep -r 'telemetry' — returns nothing
🔓

No vendor lock-in

Export your entire memory store to markdown anytime with memgit export. Your context was yours before memgit, and it stays yours. Cancel Sync and your local data is untouched.

$ memgit export --format=markdown → your data back

Verified integrity

Every memory object is SHA-256 content-addressed. memgit fsck verifies the entire store locally. The same cryptographic model git uses — no silent corruption possible.

$ memgit fsck → OK (108 objects verified)
☁️

About cloud sync (coming Phase 4)

When Sync launches, your memory objects will be transmitted over TLS 1.3 and stored encrypted at rest using AES-256. You authenticate with OAuth (GitHub) — we never see your password. You control your data: delete your account and all objects are purged within 24 hours. The sync tier will publish a full security doc before launch.

Found a security issue? Report it privately on GitHub →

Get Started

Start in 30 seconds.

Free. Open source. No account needed. Works with your existing Claude Code memories.

1Install

py
pipPython 3.8+
pip install memgit
🍺
HomebrewmacOS / Linux
brew tap code4161/tap && brew install memgit
N
npm (MCP server)Node.js 16+
npx memgit-mcp
VS Code ExtensionMarketplace
→ VS Code Marketplace
ChocolateyWindows — pending approval
choco install memgit

2Set up your AI tool

$
memgit initInitialize and import your existing AI memory files
$
memgit setup claude-codeWire MCP server + auto-commit hook (or: memgit setup all)
$
memgit search "your query"AI now reads only the relevant memories — 95% fewer tokens