Nauro
OfficialEnables Perplexity to access and surface project decisions from a shared store, maintaining context across chat sessions when pointed at the adopt prompt.
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.
The record combines project scope, state, open questions, and the rationale behind decisions. Nauro surfaces the relevant slice before work, then carries approved judgment and reported progress into later sessions and connected tools.
Status: Stable (1.x). Semantic versioning covers the CLI, local stdio MCP contract, on-disk store format, and curated nauro-core import API. Cloud sync and hosted MCP are versioned separately.
See it in practice
https://github.com/user-attachments/assets/f75ede99-db11-4460-bc09-801c86df1e19
A real Codex session, then a Claude session in Pareto, Nauro's development mock project.
Related MCP server: DecisionGraph MCP Server
Install
uv tool install nauroInstall uv with curl -LsSf https://astral.sh/uv/install.sh | sh on macOS or Linux, or use the Windows instructions. With Python 3.10 or newer, pipx install nauro also works.
Try the demo
Pennykeep, the bundled demo, needs no account or agent setup:
mkdir -p /tmp/nauro-demo && cd /tmp/nauro-demo
nauro init --demo
nauro check-decision "Store dollar amounts as decimal numbers"The top result is D001, Amounts stored in integer cents, never floating point. Its rationale explains why floating point makes money totals drift.
Use it on your repo
cd your-repo
nauro adopt --with-skills --with-subagentsRestart your agent, then invoke /nauro-adopt in Claude Code or $nauro-adopt in Codex. The skill reads project documentation and code, asks you about missing rationale, and seeds the project record without inventing decisions. The same onboarding command also installs the gated nauro-ship-task workflow and its planner, executor, reviewer, and tech-lead agents for both surfaces.
Run nauro status to verify MCP plus the installed skills and workflow agents. Run nauro doctor to check the project store itself. Re-running the onboarding command refreshes Nauro-owned workflow files and keeps recoverable backups of differing copies. It never migrates or changes third-party skills.
Nauro surfaces prior judgment for the agent to assess. Retrieval is advisory and never blocks a change. New or revised judgment is written only after your explicit approval. Local use needs no account. The local record is plain Markdown that you own. Cloud sync and remote MCP access are optional. Nauro sends no product analytics.
Adoption, setup, and incidental regeneration preserve an unmanaged AGENTS.md and warn. nauro sync is the sole explicit overwrite path. A # Manual section survives replacement.
Desktop app (macOS)
A free, read-only viewer over the project record: timeline, map, list, activity, docs. First launch sets up the CLI.
https://github.com/user-attachments/assets/e23d3d7f-2d5b-4ce4-be18-fcaff74e7973
Download for macOS (Apple silicon), signed and notarized.
Fit
If a small repo plus a reliable AGENTS.md or CLAUDE.md keeps agents oriented, Nauro may be more than you need.
Nauro is intended for longer-lived work where context can decay across sessions, tools, repositories, machines, or repeated handoffs.
Read the documentation for setup variants, concepts, command references, storage, and cloud access.
Development
uv sync --all-packages --all-extras
uv run pytest packages/nauro-core/tests/ -x -q
uv run pytest packages/nauro/tests/ -x -qReport bugs and request features in GitHub Issues.
Apache 2.0. Named for Peter Naur's Programming as Theory Building (1985).
This server cannot be installed
Maintenance
Resources
Unclaimed servers have limited discoverability.
Looking for Admin?
If you are the server author, to access and configure the admin panel.
Related MCP Servers
- Alicense-qualityDmaintenancePersistent decision memory and contradiction detection for AI coding agents. Enforces architectural consistency across sessions — the agent cannot code until it loads prior decisions. Human resolves conflicts on a dashboard or in chat.Last updated1MIT
- Flicense-qualityCmaintenanceEnables preserving, querying, and managing engineering decisions with reasoning and evidence through CLI, HTTP API, and MCP tools.Last updated16
- Flicense-qualityBmaintenanceLocal-first deterministic project memory for AI coding agents, with context packs, decisions, gates, risks, scoped claims and explicit checkpoints in project-owned files.Last updated
- AlicenseAqualityCmaintenanceSelf-hosted decision memory for AI coding agents. Captures decisions with the alternatives you rejected, and warns before an agent re-proposes a rejected approach.Last updated482Apache 2.0
Related MCP Connectors
The project brain for AI coding agents — memory, decisions, sprints, knowledge base via MCP.
Give your AI agent a persistent map of your project's structure, dependencies, and bugs.
Cross-agent artifact workspace with provenance across Claude Code, Codex, Cursor, LangGraph.
Latest Blog Posts
- Who's Calling? MCP Hosts Are an Identity Blind Spot (And the Spec Knows It)By Om-Shree-0709 on .mcpAgent IdentityOAuth 2.1
- Your AI Chatbot Just Exposed Your CEO's Salary to an InternBy Om-Shree-0709 on .Agent IdentityMCP SecurityOAuth Delegation
- Why MCP Servers Need Execution Sandboxing (And Why Your Current Stack Isn't Enough)By Om-Shree-0709 on .Agentic AiPrompt InjectionWebAssembly
MCP directory API
We provide all the information about MCP servers via our MCP API.
curl -X GET 'https://glama.ai/api/mcp/v1/servers/Nauro-AI/nauro'
If you have feedback or need assistance with the MCP directory API, please join our Discord server