Skip to content

NOUZStructured Memory for Obsidian and AI Agents

NOUZ helps agents find the right notes, links, and context in an Obsidian vault.

pip install nouz-mcp

What NOUZ Does

NOUZ turns an Obsidian vault into a local map of knowledge. Instead of a folder of files, the agent gets notes, links, levels, and nearby context. The structure stays under your control, while NOUZ helps keep the base organized and ready for precise agent work.

(children)[node]{parents}a short coordinate for a note: what it contains and where it belongs

Why It Matters

As a knowledge base grows, agents have a harder time choosing the right context: they read too many files, miss important links, mix drafts with conclusions, and rebuild material from scratch. NOUZ gives the agent precise actions over the base: read a note, inspect its place in the graph, follow links, suggest metadata, and find related material.

It does not replace thinking. It removes blind file wandering and leaves decisions where they belong: with the person using the system.

Less Wasted Context

The agent can request a specific part of the base: one note, its parents, children, nearby links, or candidate connections. Work shifts from repeated blind reading to a reusable local index.

No Auto-Rewrites

NOUZ surfaces possible metadata, links, duplicates, and drift signals. Nothing becomes part of the vault unless it is confirmed.

Hidden Connections

The semantic layer helps reveal intersections between notes, even when they use different words or live in different branches.

Memory for Agents

Through MCP, the agent gets practical tools: read a note, inspect its position, find neighbors, and suggest structure.

Three Modes

Start simple: Obsidian, YAML, and graph structure. Add semantics later, when the vault grows beyond manual links.

LUCA
Basic Graph

Obsidian vault structure: YAML metadata, parents, children, and note formulas. Works without embeddings or a complex config.

PRIZMA
Semantic Layer

Adds classification, related ideas, bridges between themes, core_mix, and drift signals. Useful when the vault outgrows manual linking.

SLOI
Level Discipline

A strict five-level structure: Core → Pattern → Module → Quant → Artifact. Useful for research bases and team knowledge where order matters.

Who It's For

Obsidian power users

The vault grew, the links live in your head

NOUZ helps expose structure, find disconnected notes, spot weak areas, and give the agent context without manually opening dozens of files.

Researchers and writers

Sources, hypotheses, and conclusions

Material from different domains can point to the same pattern in different language. NOUZ helps turn those intersections into a working research system.

AI Developers

Working memory for agents

The agent gets more than file access: it can see where a note sits, what it connects to, which material is nearby, and what to inspect next.

For Teams

The easiest way to try NOUZ is with Obsidian. If your knowledge base already lives in Notion, Confluence, Google Docs, or GitHub, you do not have to migrate it: the same approach can be connected through MCP connectors or custom adapters.

Semiotronika can help audit and set up agent-ready knowledge bases: duplicates, outdated pages, weak links, and disconnected sections. The workflow is explicit: the agent reads the base and suggests changes; a person reviews and applies them.

Knowledge Base Audit

A map of the current base: where structure has weakened, which topics are outdated, what duplicates exist, and where agents lack links.

Agent-ready setup

Obsidian, NOUZ, metadata rules, a local index, and a workflow where humans confirm important changes before they land.

Connectors and adapters

For team systems, NOUZ can act as a semantic layer beside the existing base without breaking Notion, Confluence, or another familiar tool.

Technical Foundation

The graph is built top-down. Each level has its role, and larger bases can add meta_root: a level-0 anchor that gathers domains into one system and stays out of semantic calculations.

LevelTypeWhat Goes HereSign Source
L1CoreKnowledge domain — a broad areaManual or etalon-based
L2PatternThematic frame for child modules and quantsManual or etalon-based
L3ModuleFunctional group, projectManual or etalon-based
L4QuantOne idea — a guide, research, postChild artifact type + content domain
L5ArtifactRaw material: logs, chats, configsContent-structure heuristic

Works With

Claude DesktopCursorOpenCodeClaude CodeClineContinueVS Code MCPAny stdio MCP client

Try It Quickly

bash
pip install nouz-mcp

Start with Obsidian: point NOUZ to your vault and connect it to an MCP client. LUCA works without embeddings; PRIZMA and SLOI need config.yaml and an embedding endpoint.

Example semantic mode:

yaml
mode: prizma

Environment variables:

bash
export OBSIDIAN_ROOT=/path/to/vault
export EMBED_API_URL=http://127.0.0.1:1234/v1

Run via MCP client:

json
{
  "mcpServers": {
    "nouz": {
      "command": "python",
      "args": ["-m", "nouz_mcp"],
      "env": {
        "OBSIDIAN_ROOT": "/path/to/vault"
      }
    }
  }
}

→ Quick Start

Research Context

NOUZ is a practical MCP server; the theory is optional. For readers interested in the research frame behind the project: Recursive Self-Organization as a Universal Principle.

{Semiotronika}
Telegram · Volnaya Sreda · Email