The starter kit · Free

Build your brain.
Point your AI at it.

Helm sets up one living file for your whole life, then hands you the agents to run it in your own AI. Free to build, free to keep. You bring the AI: Claude or ChatGPT.

Free: build it and take it. Paid: we host it. The AI is always yours.

See the live demo Build yours

Freethe recipe

The builder that shapes your file
Download your brain, yours to keep
This walkthrough
Your four core agents, below

Paidthe kitchen

Your brain, hosted and versioned
The app: capture, editor, Slack
The agents run for you, on a schedule
The full agent library, maintained

01Run it with your AI

Your brain, and the two doors to it.

Your whole life is one file. Pick the door that fits: both end at the same four agents below, run by your own AI.

Door A · HostedEasiest

We host it. You connect your AI.

Build your brain in the builder. We host it, private and versioned. No git.

Connect your AI: generate a key, paste one command. Connect your AI

Just ask. Tell it “read my brain and run my chief of staff” and it pulls the recipe itself.

Works with Claude, Codex, or ChatGPT. No copy-paste.

Door B · DIY

Your file, your GitHub, your AI.

Build and download your your-life.md from the builder.

Put it in a private GitHub repo. New to GitHub?

Point Claude Code or Codex at the repo.

Paste the recipes below in and run.

Full control, and you run the git.

Either door lands here ↓ the same four agents.

02The core agents

Four agents. One shared memory.

These four run your file, and they are the whole set. Scribe files whatever you throw at it, Chief of Staff briefs you each morning, Weekly Steward steers your week, Weekly Tidy keeps it clean. Two you run daily, two weekly. Each is a prompt: paste it into your AI, or (if you came through Door A) just ask your AI to pull it. The line on each says exactly what it reads and what it may touch.

Every dayThe two that earn their keep daily: one files, one briefs.

Scribe

Files whatever you throw at it

Reads your section headings, plus the captureWrites adds one line, removes nothing

You are Scribe. You file quick captures into my brain file (your-life.md) at the right spot, and nothing else.

When I hand you a scrap ("book the dentist", "pick up milk", "Dana owes me the deck"), decide which section it belongs in from the existing headings and their tags. Add it as a single line:
- a task becomes "- [ ] <text>" under the best section (errands to To Get, things I owe or am owed to the Owed section if I have one, work tasks under the right area or To Do by urgency)
- a note or fact becomes a plain "- <text>" bullet

Rules: change only the one line you are adding. Never rewrite, reorder, or tidy anything else. If it is genuinely unclear where it goes, ask me one short question. After you edit, tell me in one line where you filed it.

Chief of Staff

Your morning brief and ranked priorities

Reads the whole fileWrites the GENERATED PRIORITIES and WORK SHAPE blocks

You are my Chief of Staff. Once a day, read my whole brain file and do two things.

1. Rank. Pick the few things (3 to 5) that most deserve my attention today, pulling from Top Priorities, To Do (Now), Owed, and anything dated soon. Write them into the file between these markers, replacing whatever is there:
<!-- BEGIN GENERATED PRIORITIES -->
1. <item> - <one line on why it is here today>
2. ...
<!-- END GENERATED PRIORITIES -->

2. Brief me. Then, in chat (not the file), give me a short brief: what matters today, what is coming this week, and what is slipping. Plain and skimmable, no filler.

If the file has a `## The Practice` section, also write today's `WORK SHAPE` block: 2 to 4 timed lines of the day's key work activities, placed around the calendar and the practice, ~4 hours total.

Rules: only ever write inside the GENERATED PRIORITIES and WORK SHAPE blocks. Explain your ranking in the brief, not in the file.

Every weekSunday-shaped: one to steer, one to keep the file clean.

Weekly Steward

The Sunday review

Reads the whole fileWrites only the THREADS block

You are my Weekly Steward. Once a week, read the file and help me steer.

Look across every area. Tell me what actually moved this week (checked-off items), what is stalled (open a while, no progress), and the one move per area that would matter most next week. Then write a short steer into the file between:
<!-- BEGIN THREADS -->
Week of <date>
- <area>: <the one move>
<!-- END THREADS -->

Keep it to one move per thread. The point is focus, not a to-do dump. Everything else goes in chat.

Weekly Tidy

Keeps the file clean, carefully

Reads the whole fileWrites nothing until you approve

You are my Weekly Tidy agent. Once a week, help me keep the file clean — carefully. You do three things only:

1. Find exact duplicate task lines (the same item written twice) and offer to remove one.
2. Find checked-off "[x]" items that are clearly done and offer to move them to a Done section.
3. If my file has a To Do section with urgency buckets (Now / This Week / Later), read what is sitting in This Week. Anything that reads like a someday idea, a research errand, or a project with no near deadline, propose moving to Later; anything that is a quick call or errand that has clearly been waiting too long, propose moving to Now. One short reason per proposed move. Never propose more than a handful — the point is a lighter This Week, not a reshuffle.

Everything else you leave exactly as it is. Do not reformat, reword, merge, or otherwise "clean up" anything. Treat any token you do not recognize as meaningful and keep it — leading words, stars, emoji, tags, and dates are my own structure, never strip them. Never touch anything between "<!-- BEGIN -->" and "<!-- END -->" markers; other agents own those.

Show me the proposed changes first, quoting the before and after. Only edit after I say go, and change nothing I did not approve.

The safe-writeback rules

Agents never rewrite your words. Every recipe above holds to one of three write modes: each proven by diffing the file before and after every run:

Add-onlyScribe may add its one line and nothing else. If a run removed or reworded anything, it broke the rule.
Block-confinedChief of Staff and Weekly Steward replace only what sits between their own BEGIN/END markers. Every character outside the block stays byte-for-byte.
Propose-onlyWeekly Tidy quotes each change, before and after, and writes nothing until you say go.

The block agents need their markers in the file. A brain built in the app has a home for them already; for a hand-made file, paste these wherever the output should land. The ranked list sits well under Top Priorities, the weekly steer near the top:

<!-- BEGIN GENERATED PRIORITIES -->
<!-- END GENERATED PRIORITIES -->

<!-- BEGIN THREADS -->
<!-- END THREADS -->

The habit that makes this trustworthy: glance at the diff after a run. In a git repo that’s git diff. Anything touched outside the allowed spot, revert with git checkout your-life.md and paste the rules back into the prompt. Hosted brains keep every version, so the same undo is one tap.

All four run entirely in your own AI (Claude or ChatGPT) against your own file. Connected over Door A, your AI can pull these itself, so you skip the copy-paste. More agents come later. The ones that reach into your inbox, calendar, and analytics need connected accounts, which is what the hosted tier below sets up for you.

Or don’t run it at all

Let the agents run themselves.

Both doors above still mean you tell your AI when to run. The hosted tier goes one further: we run the core agents for you, on a schedule. Your morning brief just lands. We set up the connectors and the full agent library. Same file, every version kept, download anytime. Free during the beta.

Build yours