# Ai Brain

> Shared Obsidian vault for Claude Desktop, Claude Code, Codex, and Cowork - one brain, multiple agents, via filesystem MCP.

- **Type:** MCP server
- **Install:** `agentstack add mcp-cyril-36-ai-brain`
- **Verified:** Yes — security-reviewed for prompt injection and unsafe behavior
- **Seller:** [Cyril-36](https://agentstack.voostack.com/s/cyril-36)
- **Installs:** 0
- **Category:** [Productivity](https://agentstack.voostack.com/c/productivity)
- **Latest version:** 0.1.0
- **License:** MIT
- **Upstream author:** [Cyril-36](https://github.com/Cyril-36)
- **Source:** https://github.com/Cyril-36/ai-brain

## Install

```sh
agentstack add mcp-cyril-36-ai-brain
```

Requires the [AgentStack CLI](https://agentstack.voostack.com/docs/cli). Works with Claude Code, Cursor, and any MCP-compatible agent.

## About

# AI Brain

Most AI agents have no shared memory. Claude Desktop forgets what Codex did yesterday. Claude Code starts every session from scattered context. AI Brain makes one Obsidian vault the long-term brain for all of them: every agent reads and writes the same Markdown files through filesystem MCP.

Use it when you want Claude Desktop, Claude Code, Codex, Cowork, and similar tools to coordinate through one durable, human-readable workspace.

## What Makes This Different

- `AGENTS.md` is the master protocol every agent can follow.
- `ACTIVE_CONTEXT.md` is the handoff file every agent reads first.
- `CLAUDE.md` imports the shared protocol for Claude Code.
- `02-Projects/_template/` gives each serious project a real workspace: plan, context, TODOs, decisions, logs, prompts, and commands.
- Profile notes use `needs-verification: true` so agents do not treat unconfirmed personal facts as ground truth.
- Skills and workflows turn repeated agent tasks into reusable playbooks.

## The Loop

Capture -> Plan -> Execute -> Reflect -> Learn -> Strategize -> Coordinate.

The vault is designed so agents can capture useful context, plan inside the right project folder, execute with a work log, reflect through reviews, store reusable knowledge, make long-term moves, and coordinate through `ACTIVE_CONTEXT.md`.

## Quick Start

```bash
git clone 
cp -R ai-brain/template ~/Brain
cd ~/Brain
```

Then open `~/Brain` in Obsidian and configure your AI tools to use the filesystem MCP server for that path.

See [docs/SETUP.md](docs/SETUP.md) for Claude Desktop, Claude Code, Codex, and Cowork setup.

## First Prompts To Try

```text
Read AGENTS.md and ACTIVE_CONTEXT.md. Tell me what this vault is set up to do.
```

```text
Use the project kickoff workflow to create a project folder for my new app.
```

```text
Run a weekly brain update and create a weekly review note.
```

## Why Not Just...

| Option | Good For | Why This Template Exists |
|---|---|---|
| A folder of notes | Fast capture | Usually lacks agent rules, handoffs, and project-state conventions. |
| PARA | Organizing personal knowledge | This adds AI-agent protocols, verification flags, and repeatable workflows. |
| Zettelkasten | Linking ideas over time | This is more operational: projects, decisions, logs, setup, and handoffs. |
| Notion or hosted AI memory | Polished databases and hosted UX | Markdown stays portable, local-first, git-friendly, and readable by many tools. |

## Repo Layout

```text
ai-brain/
├── docs/
└── template/
    ├── AGENTS.md
    ├── CLAUDE.md
    ├── ACTIVE_CONTEXT.md
    ├── 01-Profile/
    ├── 02-Plans/
    ├── 02-Projects/
    ├── 03-Skills/
    ├── 04-Workflows/
    ├── 05-Knowledge/
    ├── 06-Journal/
    └── 99-Inbox/
```

The `template/` folder is the actual vault. Copy it somewhere else before using it.

## Who This Is For

- Developers, students, researchers, and builders using more than one AI coding/chat tool.
- People who want agents to remember project decisions without relying on private chat history.
- Anyone who wants Obsidian as the human-readable UI over an AI-friendly Markdown knowledge base.

## What You Get

- Agent protocol: `AGENTS.md`
- Claude Code shim: `CLAUDE.md`
- Handoff file: `ACTIVE_CONTEXT.md`
- Profile placeholders with verification flags
- Project workspace scaffold
- Profile verification, project kickoff, weekly update, and long-term planning skills
- Weekly, monthly, quarterly, and yearly review folders
- Knowledge folders for books, courses, videos, articles, and research papers

## License

MIT. Use it, fork it, adapt it, and make it yours.

## Source & license

This open-source MCP server is cataloged on AgentStack and links to its original source — we do not rehost the code.

- **Author:** [Cyril-36](https://github.com/Cyril-36)
- **Source:** [Cyril-36/ai-brain](https://github.com/Cyril-36/ai-brain)
- **License:** MIT

Install and usage instructions live in the source repository linked above.

## Pricing

- **Free** — Free

## Security capabilities

Automated source analysis of v0.1.0 — what this tool can access:

- **Network access:** no
- **Filesystem access:** no
- **Shell / process execution:** no
- **Environment & secrets:** no
- **Dynamic code execution:** no

*"Yes" means the capability is present in the source — more access means more to trust, not that it is unsafe.*


## Versions

- **0.1.0** — security scan: passed — Imported from the upstream source.

## Links

- Listing page: https://agentstack.voostack.com/l/mcp-cyril-36-ai-brain
- Seller: https://agentstack.voostack.com/s/cyril-36
- Browse the marketplace: https://agentstack.voostack.com/browse

---
Listed on AgentStack — the marketplace for AI agent skills and MCP servers. Every listing is security-reviewed. Creators keep 70%.