Autopilot for Claude Code — $99/mo

Tell it what you want
and how long it has.

Brainfile puts Claude Code on Autopilot: it does the work, proves it, and gets better. A run protocol plus the files that make it stick — a backlog that never runs empty, a ledger that never forgets a directive until it's proven done, memory that compounds instead of resetting to zero, and a brief waiting for you at the end of every run.

30-day free trial, no card — then $99/mo 30-day money-back guarantee Works on your existing Claude plan 10-minute install
6
Core v1 features
10
Pattern files in the pull
15
Role packs included
10 min
To full install
$0
Additional API costs
The core offer — v1

Six features.
Every one ships as real files.

No hosted runner, no app to log into. Autopilot is a run protocol your own Claude executes in your own project — plus the plain files that make it compound. Everything below is in the pull on day one, including the bf launcher: type bf 8h in any terminal and a timed Autopilot run starts, ending with a written brief.

01 · Autopilot loop

It selects the work, does it, and proves it.

Pre-flight reads your ledger + backlog and picks the highest-leverage plan for the time you gave it. The work loop verifies every item — "it exists" is not "it works". Post-flight re-checks the evidence and writes learnings back into your rules, so the next run starts smarter. Recurring schedules included — with the honest keep-your-computer-awake setup (you start each run; Claude can't open your laptop).

In your pack: AUTOPILOT.md — the full protocol.
02 · Never-empty backlog

Runs never stop early because the list ran out.

The backlog is built from work classes that refill themselves: each one states the next increment and the rule that generates the one after it. When a run plan is exhausted, Autopilot pulls the next highest-leverage increment instead of stopping.

In your pack: brain/backlog.md — 5 starter classes, seeded with YOUR goals at interview.
03 · Never-forgets ledger

Every directive tracked until it's PROVEN done.

Anything you ask for gets a row that stays OPEN until there's an evidence line — what was checked and what it showed. "I did it" is not evidence. Items blocked on you surface in every brief; nothing is silently dropped.

In your pack: brain/ledger.md — re-read at the start of every run.
04 · Memory + interview onboarding

Questions that GENERATE your files.

Your first session is an interview: business, goals, rules, tools, your Autopilot schedule, your brief preference. Claude writes the answers into CLAUDE.md, seeds your backlog from your month-1 goals, and starts your decision log — so session 50 starts as warm as session 1.

In your pack: INTERVIEW-ME.md · see the actual question set →
05 · End-of-run brief

Accomplished / needs you / next priorities.

Every run can end with a written brief: what shipped (with evidence), what's blocked on you, and a ranked recommendation for the next run. It's a plain file — your run dashboard without an app to log into. The template is yours to customize, and it's opt-in at interview time.

In your pack: templates/END-OF-RUN-BRIEF.md — see a real example below.
06 · Conversation history

Decisions stop dying in scrollback.

An append-only log Claude maintains at the end of every session: what you asked, what was decided, what was deferred and where it's tracked. Auditable, searchable, and honest — corrections get a new entry, past entries are never rewritten.

In your pack: CONVERSATION-HISTORY.md — the pattern + entry format.
your-project/ after the pullwhat actually lands in your repo
your-project/
├── CLAUDE.md              ← generated from YOUR interview
├── AUTOPILOT.md           ← the run protocol
├── INTERVIEW-ME.md        ← the questions that generate your files
├── START-HERE.md
├── CONVERSATION-HISTORY.md
├── templates/
│   └── END-OF-RUN-BRIEF.md
└── brain/
    ├── backlog.md         ← never runs empty
    ├── ledger.md          ← never forgets
    ├── decisions.md       ← created in your first session
    ├── runs/              ← plans + briefs, one per run
    └── freshness/         ← the weekly living feed
brain/ledger.mdactual file · shipped in the pull
# brain/ledger.md — the never-forgets ledger

Every directive you give Claude gets a row here, and it
stays OPEN until it is **proven** done — with evidence,
not vibes.

## Rules for Claude
1. **Capture:** a directive not in the ledger doesn't exist.
2. **Prove:** PROVEN_DONE requires an evidence line —
   what was checked and what it showed. "I did it"
   is not evidence.
3. **Surface:** rows blocked on you get NEEDS_YOU and
   appear in every brief until resolved.
4. **Review:** every pre-flight lists OPEN rows, oldest first.
brain/runs/2026-07-11-brief.mdreal example — the brief from the run that rebuilt this page
# Run brief — 2026-07-11 (one working session)

## Goal
Rebuild brainfile.io around Autopilot — six v1 features, honest counts, new onboarding page.

## Accomplished (with evidence)
- Home page reworked around the Autopilot story — evidence: this page; every feature above maps to a file in the pull
- Pack manifest updated to honest counts (10 pattern files + 15 role packs) — evidence: call list_pack_contents on our live MCP server and count
- Onboarding page with the real interview question set — evidence: /onboarding.html

## Needs you
- Nothing — all clear.

## Next priorities (recommendation for the next run)
1. Collect votes from the "what should Autopilot learn next?" ladder below and build the winner.

## Learnings written this run
- Rule added: every new page section ships with a feedback link.

The brief above is not a mockup — it's the end-of-run brief this run produced, in the same template your pack ships. Disagree with the feature set? Tell us →

No extra API costs

Runs on your existing Claude subscription.

Other AI tools charge API costs on top of a subscription. Brainfile runs on YOUR Claude Code account — Pro, Max, or Team. No additional API charges. Ever.

The math is simple: Brainfile is the operating system. Claude is the engine. You already have the engine.

Typical AI SaaS subscription
$99/mo
+ API costs on top
$50–200/mo
Total monthly cost
~$150–300/mo
vs
Brainfile OS
$99/mo
+ Your Claude plan (you already have it)
$0 extra
Total monthly cost
$99/mo flat
See what's inside

The gap between "free CLAUDE.md tips"
and a system that runs

Karpathy's CLAUDE.md is 66k stars and 1 file. Brainfile is the Autopilot protocol, 10 pattern files, 15 role packs, and a versioned update feed. Here's exactly what you get — browse every file in the box.

Free CLAUDE.md (DIY)
$0
  • 1 instruction file (hand-maintained)
  • No memory across sessions
  • No autonomous agents
  • No quality enforcement
  • Breaks on model updates
  • 8+ hours to set up properly
  • Manual updates forever
Brainfile OS
Brainfile OS
$99/mo
  • The Autopilot protocol — tell Claude what you want and how long it has; pre-flight, verified work loop, post-flight learnings
  • Persistent memory — Claude knows your business across every session
  • 10 pattern files + 15 role packs — never-empty backlog, never-forgets ledger, interview onboarding, end-of-run brief, conversation history, plus a role-tuned CLAUDE.md per profession
  • Interview onboarding — questions that generate YOUR files, not placeholders you fill by hand
  • Freshness feed — versioned update packs as Claude changes, every item traceable to a real change
  • 15 min install — one pull command, let Claude interview you
  • Continuous improvement — new packs added as they prove out on our own businesses
Get Brainfile →

30-day money-back guarantee · cancel anytime

See exactly what you get

The actual files in the box —
not a mockup.

Every excerpt below is unedited, straight from the pack you pull on day one. No fabricated screenshots, no fake reviews — just the real artifact, including the freshness feed that keeps it alive.

○  Without Brainfile

You re-explain your stack, your rules, and what you're building at the start of every session. Claude opens cold and generic each time — no memory of yesterday's decisions.

✓  With Brainfile

Claude reads your Brainfile — business, rules, decisions, and the latest freshness feed — and starts warm. It already knows your context on session 50 the way it did on session 1.

INTERVIEW-ME.mdactual file · pulled day 1
# Interview Me — run this first

Paste this whole file's instruction into Claude Code in
your project, or just say:

> "Read INTERVIEW-ME.md and interview me to fill in my
>  Brainfile."

## Instructions to the agent

You are setting up this user's Brainfile (their Claude Code
operating system). Your job in this first session is to
**interview the user and personalize their operating
profile** so every future session starts already knowing
their business. Do this now:

1. **Ask, don't assume.** Interview the user with these
   questions — ONE at a time, waiting for each answer:
   - What's your business/project, in one line? Who does it serve?
   - What are you trying to get done with Claude over the next month?
   - What are your top 3 non-negotiable rules (things Claude must always or never do)?
CLAUDE.starter.mdactual file · pulled day 1
# CLAUDE.md — Starter Operating System (Brainfile)

This is a starter operating profile. Replace the bracketed
parts with your business, then let the freshness feed
evolve it.

## Who you are working for
- Business: [your business]
- What we do: [one line]
- Who we serve: [customer]

## Operating rules (edit freely)
1. **Think before act.** Clarify the ask, map where it
   belongs, check current state, plan, build, verify.
2. **Spec before build.** No feature without a 3-line
   written spec.
3. **Verify before "done".** "It runs" is not "it's
   correct" — check the actual output a user sees.
4. **Every error becomes a permanent check**, not just a note.
5. **Keep a memory.** Persist decisions in `brain/` so
   sessions don't reset to zero.
brain/freshness/2026-07-04.mdactual freshness feed · v2 · the retention mechanic
# Brainfile Freshness Feed — v2 (2026-07-04)

Your weekly Brainfile update. Recurring value: the same improvements we ship to our own
operating system, plus what changed in Claude Code — with how to apply each to your brain/.
(Dogfood: we run these on our own six live businesses.)

## What we shipped to our own Brainfile (apply to yours)
- **START-HERE.md orientation in every role pack.** Activation guidance now travels INSIDE
  the artifact. *Apply:* add a root START-HERE.md so cold-opening the folder orients you in
  30 seconds (install -> confirm-it-loaded prompt -> first personalizations -> how it compounds).

## What changed in Claude Code (real release highlights, source-linked)
Source: https://code.claude.com/docs/en/changelog
- Changed the "default" permission mode to "Manual" across the CLI, VS Code, and JetBrains.
- `AskUserQuestion` dialogs no longer auto-continue by default; opt into an idle timeout via `/config`.
- Improved screen-reader output: decorative glyphs hidden, transcript symbols read as short labels.

This is the real v2 feed shipping in the pack today. The next feed ships with the next Claude Code change — we never backfill fake updates.

Under the hood

Don't take our word for it.
Poke the live infrastructure yourself.

Everything below is running in production right now — an open MCP server, a public registry listing, machine-readable docs. Every claim on this page is verifiable from your own terminal before you spend a dollar.

brainfile.io/mcplive MCP server · free scope · no account
$ curl -s https://brainfile.io/mcp
{"ok":true,"server":"brainfile","version":"1.0.0",
 "transport":"streamable-http (JSON-RPC 2.0 over POST)",
 "tools":["get_starter_file","list_pack_contents","get_freshness_sample"],
 "scope":"free (no token) — the on-ramp"}

get_starter_file

Returns the full, unedited text of the three starter files — INTERVIEW-ME.md, START-HERE.md, and CLAUDE.starter.md. The same files the paid pull ships. No account needed.

list_pack_contents

Returns the whole pack manifest: the 10 free pattern files (5 readable right here over MCP, all 10 in the free no-card trial pull), plus the 15 role packs — listed honestly as locked, with the unlock link.

get_freshness_sample

Returns the actual freshness-feed entry shipping in the pack today (markdown + structured feed.json) — the weekly living-system update that keeps your install current.

Point Claude, Cursor, or ChatGPT at https://brainfile.io/mcp and call the tools yourself — 2-minute setup guide →

Live & verifiable

Listed in the Official MCP Registry

Brainfile is published in the Model Context Protocol's official registry as io.brainfile/brainfile — domain-verified, status: active. Any MCP client can discover and connect to it.

Verify: search the registry API for io.brainfilesee the live listing →
Live & verifiable

Machine-readable by design: llms.txt

We practice what we sell. This site publishes /llms.txt — a plain-text summary AI assistants read directly, cross-linked with our other properties — so when someone asks their AI about Brainfile, it gets the honest source, not a scrape.

Included guide — not software

The "interview me" onboarding

INTERVIEW-ME.md is a markdown guide in the pack: open Claude Code and say "Read INTERVIEW-ME.md and interview me to fill in my Brainfile." Claude asks about your business, goals, and non-negotiable rules — one question at a time — then writes the answers into your CLAUDE.md and starts your decision log. It's instructions your own Claude follows, not an app we run.

Verify: pull the full file over MCP with get_starter_file — or read the excerpt above.
The operating system your AI keeps

Five patterns that separate
"an AI with a prompt" from an operating system.

These are the working patterns we run every day on our own six live businesses. Your pack ships each pattern as plain files and rules your Claude reads — the pattern, not our internal systems.

Pattern 01

Persistent memory files

A CLAUDE.md + brain/ folder your AI reads at the start of every session. No re-explaining your stack, rules, or goals — Claude knows your business on session 50 the way it did on session 1.

In your pack: CLAUDE.starter.md + the brain/ layout it defines.
Pattern 02

Nothing is "done" without evidence

The rule we live by: work isn't complete because the AI says so — it's complete when the output is verified. On our own system, tasks literally cannot be marked done until an evidence file exists. Your starter ships the same rule: "Verify before 'done' — 'it runs' is not 'it's correct'."

In your pack: CLAUDE.starter.md operating rule #3.
Pattern 03

Self-improving checklists

Every error becomes a permanent rule, not a note that gets forgotten. Correct your AI once and the correction is encoded — your operating system gets stricter exactly where you got burned.

In your pack: CLAUDE.starter.md operating rule #4 + the freshness feed showing this applied to our own OS.
Pattern 04

Registries — nothing gets forgotten

Anything worth maintaining gets a registry entry with a review cadence. If it's not registered, that's a blind spot to fix. It's how a growing AI setup avoids the silent rot of things nobody is watching.

In your pack: the brain/ layout + freshness-feed apply-hints teach this structure.
Pattern 05

Decision logs

Decisions get written to brain/decisions.md once — and never re-litigated. Your AI stops asking you the same questions and stops quietly reversing choices you already made.

In your pack: the interview creates brain/decisions.md in your first session (INTERVIEW-ME.md step 3).
Free Download

Get the Brainfile OS Starter Kit — Free

See what a production-grade CLAUDE.md looks like before you buy:

  • Annotated CLAUDE.md — every section explained
  • Sample brain/ memory structure for a solo founder
  • 1 pre-built agent (Revenue Agent) — plug in and run

No spam. We send a monthly update on what changed in Claude + your install. Unsubscribe anytime.

Pricing

One plan to start. Everything in v1.

The Autopilot protocol, all 10 pattern files, all 15 role packs, and the freshness feed — one flat price, on your existing Claude plan.

Start here · one-time

Not ready to commit? Get the $249 AI-Ops Audit first.

We point the same drift detector, deploy gate, visual-QA, and launch-readiness gates that guard our own six live businesses at your Claude Code setup — and hand you a scored report + prioritized fix list. One-time, no subscription. It's the low-friction way to see exactly where your setup stands before you run the full OS.

$249
ONE-TIME
See the audit →
Start here
Brainfile Starter
$99
/month

30-day free trial first — no card. Cancel anytime.

  • The Autopilot protocol — tell Claude what you want and how long it has; it does the work, proves it, and gets better
  • All 10 v1 pattern files — never-empty backlog, never-forgets ledger, interview onboarding, end-of-run brief template, conversation history, memory starter
  • All 15 role packs — a role-tuned CLAUDE.md per profession (Founder, Developer, Trader, Consultant, Lawyer…). Subscriber-only — the free trial ships everything else, not these.
  • Freshness feed — versioned update packs as Claude Code and best practices change, traceable to real changes (never filler)
  • Works on your existing Claude plan — Pro, Max, or Team; $0 additional API costs
  • 30-day money-back guarantee — cancel anytime
🛡️
30-day money-back guarantee. If Brainfile doesn't change how you work with Claude Code in the first 30 days, we'll refund every dollar. No questions asked.

Prefer to pay yearly? $999/year — the same single plan, billed annually ($83/mo). See what's included →

Built in the open

What should Autopilot learn next?

v1 is the six features above. The next capability gets built when it wins the vote — one click, no email needed. We don't display counts (no fake momentum); the ladder is real and we build the winner.

Something else entirely? Tell us what Autopilot should learn →

Setup

From zero to your first Autopilot run
in 15 minutes.

No coding experience required. Install is one pull command. Configuration is a first-session interview Claude runs for you.

Step 01

📦 Install

5 minutes

Start your trial and we email you a one-line pull command (also shown on screen). Run it in your project root to pull Brainfile in — re-run it anytime to get the newest freshness feed: curl -sSL https://brainfile.io/pull.sh | bash -s -- [email protected] <token>. That's the install.

Step 02

⚙️ Configure

10 minutes

Start claude and say "interview me and fill in my Brainfile." Claude walks the [CUSTOMIZE] markers — your business, goals, metrics, preferences — and writes them in. No generic setup.

Step 03

🚀 Run

Ongoing — compounds

Say "Read AUTOPILOT.md. You have 2 hours. Run autopilot." Claude selects the work, does it, proves it, and leaves you a brief. Memory and rules compound run by run.

FAQ

Common questions.

Brainfile is Autopilot for Claude Code. It's a run protocol plus a structured set of plain files — a never-empty backlog, a never-forgets ledger, persistent memory, an interview that generates your setup, an end-of-run brief template, and a conversation log — that let you tell Claude what you want and how long it has, and trust that the work gets done, proven, and remembered. Think of it as the operating system layer on top of Claude Code.
No. Installation is one pull command in your terminal — it lands the whole system in your project folder as plain markdown files, no code, no build step. Re-run the same command anytime for the newest updates. Configuration is a plain-language interview Claude runs for you in your first session. You do need a Claude Code account (Anthropic's Claude Pro, Max, or Team plan includes Claude Code access). If you can use Claude, you can run Brainfile.
This is exactly why the subscription matters. As Claude updates — new capabilities, new behaviors, new best practices for CLAUDE.md structure — you receive versioned freshness packs with clear merge instructions, where every item traces to a real change (never filler). Canceled users keep the version they last synced, but it drifts out of date as Claude evolves. Think of it like antivirus software: the initial install isn't what protects you, the continuous updates do.
Yes — everything is a plain markdown file you can edit directly. The step that makes it yours is the first-session interview: Claude asks about your business, goals, rules, and schedule, then writes the answers into your files — your backlog gets seeded from YOUR month-1 goals, your brief template is yours to restructure, and every role pack is editable. Your customizations persist through updates because the freshness feed is additive — it never overwrites your rules.
You're not paying for files — you're paying for the distilled operating judgment of six live businesses we run on this exact pattern every day: the Autopilot protocol, the 10 pattern files, 15 role packs, and a freshness feed that updates your install as Claude evolves. The DIY version takes 8+ hours of consulting to set up ($5,000+) and months of iteration to get right. Agencies charge $500–1,500/mo just to keep configs current. Brainfile does it for $99/mo — and gets smarter every month.
Skills are atoms. Brainfile is the operating system that uses them. A skill helps Claude do one task — write a tweet, query a database, format a report. Brainfile gives Claude a run protocol with verification built in, persistent memory across sessions, a ledger that never forgets a directive, and a self-improvement loop that learns from every error. You can absolutely plug Anthropic skills into a Brainfile — that's the point. The skills marketplace solves the “how does Claude do X?” problem. Brainfile solves the “how does Claude get my work done and prove it?” problem.
No — and we won't pretend otherwise. Autopilot runs inside YOUR Claude Code session: you start each run (one sentence), and Claude works the time budget you gave it. The protocol includes the honest setup for long runs — keeping your computer awake (macOS caffeinate / Windows power settings) and a recurring schedule recorded in your CLAUDE.md at interview time. Nothing runs on our servers; your work never leaves your machine.
Your Brainfile keeps working at the version you last synced — it doesn't break or disappear. But it won't receive new updates as Claude changes behavior, new agent capabilities won't be added, and your quality checks won't evolve with new Claude Code features. The longer you're away, the more the gap widens between your Brainfile and what's possible. Cancel anytime. No lock-in. Reactivate anytime to get current — we'll show you exactly what you missed.
Get started

Ready to put Claude Code
on Autopilot?

30-day free trial, no card. Works on your existing Claude subscription.

Start free — 30 days, no card Talk to us first

30-day money-back guarantee · Cancel anytime · [email protected]

We're listening

Have feedback or found a bug?

Tell us what's working, what's broken, or what you wish Brainfile did. We read every message — it goes straight into our build queue.

Send feedback →

or email [email protected]

Better together
Prompts that use your brainfile

Your brainfile gives AI persistent context — who you are, how you work, what matters right now. PromptSharp is what to do with it: a professional prompt library that runs ON that context. Brainfile is the memory; PromptSharp is the playbook. Together they compound — every prompt starts already knowing you.

A PromptSharp prompt, auto-filled from your brainfile
> Draft my weekly stakeholder update: wins, risks, and asks — in my voice, against my current priorities.
With your brainfile loaded, “my voice”, “my stakeholders” and “current priorities” fill themselves from your context files — zero re-explaining.
Browse the prompt library →

Want both? The All-Access + Brainfile annual bundle covers the pair.