Skip to content

The decision system
for building software
with AI.

Nauro gives connected agents human-approved project judgment and current state before they plan or change work.

The Nauro app tour

A recorded tour of the Nauro app over a seeded demo store: the decision list, quick-open search, one decision's full record, a supersession chain walk, the timeline, and the citation map.

How Nauro helps connected AI stay consistent

Without human oversight, AI can drift.

  • Last session we discussed…
  • Which version did we agree to?
  • What changed since last session?
  • Why did we choose this?
  • We already ruled that out.
  • That was approved as an exception.
  • That reverses the previous decision.
  • Has this shipped?
  • Which decision is current?
  • What is still unresolved?
  • Where did we leave this?
  • Was that a temporary exception?
  • I approved the earlier version.
  • What are we still assuming?
  • That was true before the migration.
  • Does this conflict with a decision?

Watch Nauro work with your agents.

Codex to Claude Code judgment handoff demo

Codex checks Pareto's existing concurrency policy, recommends a top-tier change while keeping the default at six, and records it after the user approves. In a later Claude Code session, the agent retrieves the approved limit and rejects an unsupported increase to ten.

Connect Nauro to your agents

  1. 1Download the macOS app, or install the CLI with uv tool install nauro.
  2. 2Run nauro adopt at your repository root.
  3. 3Agents load the record before they work. You approve what enters it.

The record is local Markdown. You do not need an account, and cloud sync stays off until you enable it.

Full setup guide

How is this different?

From AGENTS.md or CLAUDE.md?
Those files carry standing instructions, not history. Nauro writes your AGENTS.md context section from the record and keeps what a flat file cannot hold: each decision’s rationale, rejected alternatives, and supersession chain, retrievable by any connected agent.
From Cursor rules or agent memory?
Rules and memory belong to one tool. The record is vendor-neutral local Markdown, read over MCP by Claude Code, Codex, Cursor, and anything else you connect. Nothing enters it without your approval.
From committed ADRs?
ADRs wait to be reread. Nauro decisions are retrieved: before a change, agents check the proposal against the record and get the related history ranked by relevance.
What happens when a decision goes stale?
It is superseded, never silently edited. The old decision keeps its number and points forward, the new one carries the reasoning, and you approve the change. Agents always see the current rule with its lineage.
When do I not need this?
If committed decisions plus an agent instruction keep one repo aligned, keep them. Nauro is for judgment that must stay current across sessions, agents, and tools.

The decision system
for building software
with AI.