Guide

One vault, many agents. You orchestrate.

The lock-in nobody warns you about isn't the app — it's the agent. Keep your knowledge in plain files, and no single AI owns it. Cowork drafts, Codex refactors, ChatGPT generates, a local agent guards your secrets — and you hold the pen.

The vault is neutral ground

Most AI tools want to be the home for your thinking: your knowledge in their database, your annotations in their format, your agent the one they ship, your model the one they lock you to. Then "which AI do I use?" becomes "do I migrate everything?" — and you're fenced inside one vendor's roadmap.

A note.md vault flips it. The vault is a folder of plain markdown with shared conventions — an AGENTS.md that states the house rules, ((file#b-xxxxxx)) block citations for precise references, sidecar .note.md files that hold your judgment, and [[wikilinks]] for a single namespace. Those conventions are a public protocol: any agent can read them, no adapter required. The agents and models become interchangeable workers; the vault is the one thing that doesn't change. It's a git repo, and they're all committing to it.

Assign each job to whoever's best at it

No single agent is best at everything. So don't make one do everything — build a line and put each tool at the station it's strongest at:

StageA good fitWhy
Overnight automationOpenClaw / HermesLong-running, file-based, self-hosted memory
Careful review & revisionClaude Cowork / CodeStrong reasoning; reads your margins before editing
Fast drafting & imagesChatGPT (work mode)Generalist generation, batch image creation
In-repo refactors & scriptsCodexNative AGENTS.md, runs in the working dir
Final judgmentYouThe one thing no model can generate

You pick the agent and the model per job — a cheap fast model to triage, a frontier model to reason, a local model for anything private. The vault doesn't care which; it just holds the files they pass between them.

A loop in practice

Here's a real pipeline, four tools and three models over one vault:

  1. OpenClaw runs overnight, processing a batch of raw notes into drafts/*.md.
  2. You hand the drafts to Claude Cowork on a careful model — "review and revise these, flag anything shaky."
  3. ChatGPT batch-generates the hero images into each doc's _files/ folder.
  4. The finished documents land in note.md, where you read them, cut what overclaims, highlight what matters, and leave the notes only you could write.

Four tools, three models, one vault, one orchestrator. Nobody had to share memory or speak a private protocol — they handed off .md files on disk, and your sidecar .note.md annotations were the steering signal for the next one.

Why files make it work

Keep the vault in git and every agent write is diffable, attributable, and revertible — an agent's bad day is a git revert, not a tragedy.

Set it up

  1. Put an AGENTS.md at your vault root — grab the conventions from llms-full.txt and add house rules (the hard one: agents never write into *.note.md sidecars).
  2. Wire up each agent on the same folder: OpenClaw, Cowork, Codex, ChatGPT, Hermes.
  3. Read and annotate the results in note.md; tell the next agent to read the sidecars first. The loop closes on your disk.

FAQ

Can different AI agents really share one vault?

Yes — that's the design. A vault is plain markdown plus one AGENTS.md describing the conventions. Claude Cowork, Claude Code, Codex, ChatGPT, OpenClaw and Hermes all read and write those files, so you can route each task to whichever agent (and model) is best for it. Keep the vault in git so every write is diffable and revertible.

How do agents hand work off to each other?

Through files. One agent writes markdown into the vault; the next reads it as input. Your annotations live in sidecar .note.md files and act as the steering signal — an agent reads your margins before its next pass. No shared memory or private protocol is needed.

Does this need a special orchestration tool or MCP server?

No. The orchestration is you, and the medium is the filesystem. There's no central database or hidden state — rules in AGENTS.md, output in .md, judgment in .note.md. A Vault MCP server is on the roadmap for agents that prefer a tool interface, but plain files already work today.

Why not just use one AI for everything?

Because no single agent is best at everything. Overnight automation, careful review, fast image generation, private local work, and final judgment are different jobs with different best-fit tools. Splitting them across specialists — over files you own — beats one generalist doing all of it, and keeps you free to swap any worker out.

Own your thinking.

Free. Open. A folder of markdown on your own computer.

Download note.md