Jason-Cyr

Jason-Cyr / ai-shared-brain

Public

Give your AI agent persistent memory with markdown files. Starter kit from the video: My AI and I Share a Brain.

13
3
100% credibility
Found May 06, 2026 at 13 stars -- GitGems finds repos before they trend. Get early access to the next one.
Sign Up Free
AI Analysis
AI Summary

A starter kit of markdown template files that enables AI agents with file access to build and maintain persistent, shared memory about the user and their interactions.

How It Works

1
💡 Discover Shared Brain

You learn about a simple way to give your AI helper a real memory that lasts between chats, using everyday text files.

2
🗂️ Choose Your AI Helper

Pick an AI tool that can read and save files on its own, like a smart coding buddy with its own workspace folder.

3
Get the Starter Files
💾
Quick Download

Grab the zipped folder from the web page and unzip it right into place.

📋
Copy by Hand

Make the few text files yourself using the examples as a guide.

4
✏️ Add Your Personal Touch

Fill in details about yourself, your daily life, and how you want your AI to act and talk.

5
🚀 Start Chatting

Begin conversations with your AI – it always checks the files first to recall everything from before.

6
⏳ Watch Memories Build

Over a few days, your AI starts noting down key moments, lessons, and your preferences into its own memory files.

🧠 Your AI Remembers You

Now your AI companion knows your world deeply, picks up seamlessly, and feels like a true partner.

Sign up to see the full architecture

5 more

Sign Up Free

Star Growth

See how this repo grew from 13 to 13 stars Sign Up Free
Repurpose This Repo

Repurpose is a Pro feature

Generate ready-to-use prompts for X threads, LinkedIn posts, blog posts, YouTube scripts, and more -- with full repo context baked in.

Unlock Repurpose
AI-Generated Review

What is ai-shared-brain?

ai-shared-brain gives your AI agent persistent memory through plain markdown files dropped into its workspace. You customize basic identity details for yourself and the agent, then it reads them on startup, logs daily notes, and curates long-term knowledge over sessions—no databases, APIs, or fine-tuning required. Works with file-reading agents like OpenClaw, Claude Code, Cursor, or Codex; just git clone or download into the workspace to give your agent read-write access, like granting collaborator permissions to a private repo.

Why is it gaining traction?

It skips bloated tools like vector stores or RAG pipelines for dead-simple markdown that you can read and edit yourself, building real context as the agent writes episodic and distilled memories. The hook is transparency: no black box, just files that persist between chats, standing out for devs tired of resetting agent state. Early buzz from the creator's video shows it hooks users wanting to give agents ongoing "brain" access without setup hassle.

Who should use this?

AI workflow builders using OpenClaw or Claude Code for daily tasks, like designers prototyping agents or devs giving GitHub repo access to chatty assistants. Perfect for solo creators experimenting with persistent personal AIs, not teams needing enterprise-scale memory.

Verdict

At 13 stars and 1.0% credibility, it's raw and unproven but boasts clear docs and MIT license—clone it into your agent's folder for a low-risk test if you have file access tools. Worth forking to give your agent a shared brain upgrade.

(178 words)

Sign up to read the full AI review Sign Up Free

Similar repos coming soon.