ADRs4AI - Versioned deliberation records for human-AI work
Show HN: ADRs for AI – Deliberation records for human–AI work, versioned in Git
ADRs4AI captures the thinking that usually evaporates when you work with an AI. Dump your reasoning into a seed, and your agent chunks it into ADRs that preserve your actual words, the options considered, the reasoning, and open questions — each with the AI's recommendation, rationale, confidence, and a falsifier. Answer with one judgment: accept or override. Everything lives in Git, searchable with a single grep and surfaced through a VS Code extension, an MCP server, and an iOS client with one-tap Accept that lands answers as commits. The record does the remembering, so the work stays resumable and the thinking compounds.
It does not make an AI persistent, and it does not make anyone remember. It makes the work resumable — and the thinking compound.
- wrlach
This is cool, I have been working with something in a similar vein (https://github.com/wlach/idr-tools), though it seems like you emphasize keeping a decision log more than I do. For me, that aspect has been a lot less useful than structuring my thoughts about how implementation should proceed. It probably depends a lot on what you're trying to do.
This might be my bias, but I feel like the site doesn't really immediately answer the question of why I would want to use these? What nagging issue does it solve? Some real world examples and case studies would go a long way to answering those questions. The theoretical stuff (papers, prior art, etc.) looks interesting but IMO does not belong on the front page.
- diegof79
The title got me interested. However, I couldn’t bear your site, sorry.
My feedback: cut the slop. I see a wall of text with explanations that are full of marketing phrases, filler sentences, and there isn’t a clear, curated explanation.
Again, sorry for my blunt feedback.
- 4b11b4
wait over a year?
What were the design decisions which you have settled on and what did you throw out?