ADRs4AI
Public draft — quietly published, comments invited. This site iterates in the open; that's the method. The toolkit's code repositories are briefly private while licenses are finalized — they open with the launch.

ADRs4AI

Your thinking stops disappearing. Your decisions start compounding.

Pinion pictogram — dark side down — amber default, tintableDocument grown for breathing room around the untouched scale; stroke at ~87% of bold; default color is the project amber (#D97706) via the root color attribute — any external CSS color overrides it (Peacock-tintable), and it can never render invisible-black.
The template A repository starter: ADR & seed templates, the directives, the inbox protocol, task-runner recipes. Adopt whole or by feature — it works from your first seed.
The VS Code extension Tree views of your open questions, diagnostics that catch malformed records as you type, deep links, and an MCP server so your agents can query the record.
The iOS client Your project's open questions, in your pocket: sign in, import a repo, review, and one-tap Accept that lands real answers as commits.

The most valuable byproduct of the collaboration between a human and an AI is the thinking — and in ordinary practice, all of it evaporates. You can already make good decisions with your AI. Every session produces reasoning you will need again, and lose by default. This keeps the why, so it compounds.

How it works, in twenty seconds

The iOS client: a recommendation with its rationale, and one-tap Accept

Dump your thinking into a seed — messy is fine, dictation is fine; capture first. Your AI chunks it into ADRs that keep what usually evaporates: your actual words, the options considered, the reasoning, the open questions. Every question is findable by one grep — ### QST: — or surfaced by the editor extension, the MCP server, the phone in your pocket; and each arrives with the AI’s options, its recommendation, its rationale, its stated confidence, and what would prove it wrong — so answering streamlines to accept or override: Cognitive load down, bandwidth freed for the deliberations that matter. It’s where conversations become decisions that keep their reasons — deliberative programming, in one habit.

You don’t need to be an experienced engineer to start. The method was built through daily practice by one human and a growing crew of AI collaborators, and its whole point is that the record does the remembering — as much for the veteran with too many projects, as for the beginner building their very first one.

The VS Code extension's Open Questions view: a real question, four options, an attributed recommendation, an answer box

The extension’s Open Questions view, on this project’s own record: A question, its options, an attributed recommendation — and the answer box. Question 16 of 75, that day.

What it is not

Not transcript archival. Not vector-database “memory.” Not an orchestration platform. Not a claim that an AI possesses persistent identity — the record holds, minds change, and the work resumes either way.

The idea underneath

The most valuable thing that happens between a human and an AI is not the code, the draft, or the answer. It’s the thinking — and in ordinary practice, all of it evaporates. […] It does not make an AI persistent, and it does not make anyone remember. It makes the work resumable — and the thinking compound.

— from What is ADRs4AI?, the founding essay. A stranger can read it cold; its authorship and review record are public, because that is the method.

From the blog