uddin-rajaul/brain-os-template — explained in plain English
Analysis updated 2026-05-18
Give an AI coding assistant a persistent memory across sessions instead of starting from scratch.
Maintain a structured wiki of project decisions, patterns, and learned facts.
Set a custom personality and communication style for your AI assistant.
Track daily session notes and a running log of project changes.
| uddin-rajaul/brain-os-template | 0-bingwu-0/live-interpreter | 0cm-labs/tokenizer-benchmark | |
|---|---|---|---|
| Stars | 2 | 2 | 2 |
| Language | — | Python | Python |
| Setup difficulty | easy | moderate | moderate |
| Complexity | 2/5 | 2/5 | 2/5 |
| Audience | vibe coder | general | researcher |
Figures from each repo's GitHub metadata at analysis time.
Just clone the template and start an AI coding assistant inside the folder, no external dependencies or accounts needed.
Brain OS is a folder template for people who work with AI coding assistants like Claude Code, OpenCode, Cursor, or Codex, and want those tools to remember things across sessions. Instead of the AI re-reading all your notes every time you ask it something, the idea here is that the AI reads your source material once, pulls out the important facts, and writes them into a structured set of markdown pages that stay up to date over time. You read this wiki, and the AI is the one who keeps writing and maintaining it. The template is organized into folders with clear jobs. A RAW folder holds your original source documents, which the AI reads but never changes. Separate folders cover active projects, ongoing responsibilities, reference material, session notes, and an archive for things no longer active. A handful of instruction files, including one named for Claude and another for other assistants, tell the AI exactly how to read and update this structure, while a personality file lets you set the tone and style you want the assistant to use. Using it starts with cloning the template, opening your AI coding assistant inside that folder, and telling it to read the instructions and set itself up. From there, each working session begins with the AI reading a small file describing the current state, so it does not need much context to get going. As you work, the AI only writes new information when something genuinely new comes up, and at the end of a session it updates the current state file and adds an entry to a running log. The project argues that the tedious part of keeping a personal wiki is not writing it, but the ongoing bookkeeping of updating links and catching contradictions, which is exactly the kind of repetitive task an AI assistant does not get tired of doing. The template draws on ideas from note taking methods like PARA and Zettelkasten, and is compatible with Obsidian. It is released under the MIT license.</content>
A folder template that lets AI coding assistants build and maintain a persistent, structured knowledge base of markdown notes across sessions.
Licensed under MIT, so anyone can use, modify, and redistribute it freely, including for commercial purposes, as long as the copyright notice is kept.
Setup difficulty is rated easy, with roughly 5min to a first successful run.
Mainly vibe coder.
This repo across BitVibe Labs
Don't trust strangers blindly. Verify against the repo.