Skip to main content

Human-approved project judgment and current state for connected AI agents, surfaced before work.

Project description

Nauro

Give your agents the context code leaves out.

Nauro keeps current state, open questions, and human-approved project judgment in one record, ready for every agent you connect.

Nauro keeps a living project record. It combines project scope, current state, and open questions with human-approved project judgment: intent, goals, decisions, rationale, tradeoffs, and rejected paths. Project judgment is the human-ratified part of the record; context is the relevant slice of the record an agent receives for the work in front of it. Works with Claude, Perplexity, Cursor, Codex, and any MCP client.

How the loop works

  1. Nauro orients the agent with project scope, current state, open questions, and relevant prior judgment.
  2. You and the agent clarify missing intent, constraints, or tradeoffs.
  3. If the work needs new or revised judgment, the agent drafts it and waits for your explicit approval.
  4. The agent plans, recommends, or implements with that context in view.
  5. The agent explains how the context shaped the result, and you accept, correct, except, reopen, or supersede it in conversation.
  6. The agent reports meaningful completed progress as current state, so later connected agents inherit the updated state and approved judgment.

The markdown store, context summaries, BM25 retrieval, advisory checks, and optional sync support this loop. They do not replace your judgment or silently change project truth.

Install

uv tool install nauro     # uv fetches its own Python — nothing else needed

No uv? Install it with curl -LsSf https://astral.sh/uv/install.sh | sh (macOS/Linux) or the PowerShell line on Windows. Already on Python 3.10+? pipx install nauro (or pip install nauro) works too.

Quickstart

See a prior decision in about 30 seconds. No account, MCP wiring, or restart required:

mkdir -p /tmp/nauro-demo && cd /tmp/nauro-demo
nauro init --demo
nauro check-decision "Store dollar amounts as decimal numbers"

nauro init --demo also generates AGENTS.md in the current directory so a coding agent can load the Nauro preflight and demo context before its first task. If the repo already has a hand-authored AGENTS.md, Nauro warns and leaves it unchanged.

You'll see a JSON envelope with the related decisions and a deterministic assessment, e.g.:

{
  "store": "local",
  "related_decisions": [
    {
      "id": "decision-001",
      "title": "Amounts stored in integer cents, never floating point",
      "score": 8.462,
      "status": "active",
      "date": "2026-03-15",
      "rationale_preview": "Every monetary amount (transactions, budgets, balances) is stored as an integer number of cents and formatted to dollars only for display..."
    }
  ],
  "assessment": "Found 5 related decisions. Top match: D001 \"Amounts stored in integer cents, never floating point\"..."
}

The demo project ruled out storing money as floating-point dollars because binary floating point cannot represent a value like 0.10 exactly, so totals accumulate rounding error and a balance that should read 0.00 shows -0.01. This protective example isolates Nauro's retrieval mechanism: it brings a recorded constraint into the proposal flow before an agent can re-propose the rejected field.

If a small repo plus a reliable AGENTS.md or CLAUDE.md keeps agents oriented, Nauro may be more than you need. Nauro is designed for context that must persist across longer histories, sessions, tools, repos, machines, or repeated handoffs.

nauro graph renders the store to one self-contained HTML file and opens it: a node-link map of every decision as the default view, plus drawn supersession lineage, a timeline, and a category browser. The demo store's consolidation, three retired decisions converging on the one that replaced them, draws as a fan. By default the file carries the full decision store, including each decision's body rendered as structured detail in the side panel, and lands in the store directory rather than your repo; --no-include-bodies produces a redacted titles-and-metadata artifact for wider sharing.

nauro doctor checks the store for structural defects: unparseable decision files, dangling or cyclic supersession refs, and status contradictions. It is deterministic and report-only — it never edits the store and always exits 0.

For real-project setup (nauro init / nauro adopt), cross-surface access, MCP tool reference, and architecture details, see the main project README. Don't run nauro setup from /tmp/nauro-demo; that would wire the throwaway demo into your MCP client.

For full Claude Code and Codex onboarding, run nauro adopt --with-skills --with-subagents. This installs the gated nauro-ship-task workflow and Nauro's bundled planner, executor, reviewer, and tech-lead agents into ~/.claude/agents/ and ~/.codex/agents/. Re-running the command refreshes Nauro-owned workflow files and saves differing copies as backups. It leaves third-party skills and agents untouched. Pass --force-overwrite only when you do not want backups.

Why Nauro?

Nauro supports a human-ratified project-judgment loop. It captures what you decided and what you ruled out, with the reasoning, then brings related judgment into agent work. Keyword search over the decision store is one mechanism for putting prior reasoning in front of an agent at proposal time.

No model judges your decisions. The check uses deterministic keyword retrieval (BM25), is advisory, and never blocks a change. Agents draft additions, updates, and supersessions; you explicitly approve each one before propose_decision commits it in one call.

check_decision returns the related prior decisions (the related_decisions list shown above) so the agent can weigh them before proposing; Nauro ranks by keyword relevance and does not judge the proposal. On the approved propose_decision call, near-matches surface as advisory similar_decisions, and a clean proposal commits in one call. What you approve in one tool, every connected agent inherits; for example, a decision recorded in Claude Code is available later in Perplexity. The store is plain markdown in a folder you own. Run it fully locally with no account; cloud sync is opt-in.

Hosted allowance

Nauro includes unlimited local usage, unlimited projects, and 5,000 remote MCP calls per month. For higher hosted limits, contact thomas@nauro.ai. See nauro.ai/pricing for current details.


Apache 2.0 license. Part of the nauro-ai/nauro monorepo.

Named for Peter Naur, whose 1985 paper Programming as Theory Building argued the real program is the theory in the programmer's mind, not the code. Every fresh agent session is the equivalent of losing that programmer.

Project details


Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Source Distribution

nauro-1.6.0.tar.gz (262.7 kB view details)

Uploaded Source

Built Distribution

If you're not sure about the file name format, learn more about wheel file names.

nauro-1.6.0-py3-none-any.whl (314.1 kB view details)

Uploaded Python 3

File details

Details for the file nauro-1.6.0.tar.gz.

File metadata

  • Download URL: nauro-1.6.0.tar.gz
  • Upload date:
  • Size: 262.7 kB
  • Tags: Source
  • Uploaded using Trusted Publishing? Yes
  • Uploaded via: twine/6.1.0 CPython/3.13.12

File hashes

Hashes for nauro-1.6.0.tar.gz
Algorithm Hash digest
SHA256 35cffee46bed990309166a2e18dcb088208f76a294e0ff1f42006104ac5e57eb
MD5 3283a4cefdb36e949b48fefbf96f43d7
BLAKE2b-256 320b1ec7ff449ba3c908a6adb5664f7ca965ecf9bdbb83a72665fbcbb5acc68e

See more details on using hashes here.

Provenance

The following attestation bundles were made for nauro-1.6.0.tar.gz:

Publisher: publish-nauro.yml on Nauro-AI/nauro

Attestations: Values shown here reflect the state when the release was signed and may no longer be current.

File details

Details for the file nauro-1.6.0-py3-none-any.whl.

File metadata

  • Download URL: nauro-1.6.0-py3-none-any.whl
  • Upload date:
  • Size: 314.1 kB
  • Tags: Python 3
  • Uploaded using Trusted Publishing? Yes
  • Uploaded via: twine/6.1.0 CPython/3.13.12

File hashes

Hashes for nauro-1.6.0-py3-none-any.whl
Algorithm Hash digest
SHA256 7fccb7ce68b4228941d8e43991ffb26993e60582519a08674379c84842e2bcdf
MD5 eca75ae1b3cdede81e06859ac33076b9
BLAKE2b-256 974ec1db5463902fc0700feada76391ba68955bca2f83cb9cba1aa3b04c19661

See more details on using hashes here.

Provenance

The following attestation bundles were made for nauro-1.6.0-py3-none-any.whl:

Publisher: publish-nauro.yml on Nauro-AI/nauro

Attestations: Values shown here reflect the state when the release was signed and may no longer be current.

Supported by

AWS Cloud computing and Security Sponsor Datadog Monitoring Depot Continuous Integration Fastly CDN Google Download Analytics Pingdom Monitoring Sentry Error logging StatusPage Status page