# amarodeabreu/claude-graph-memory architecture

> Architecture diagram of the GitHub repository amarodeabreu/claude-graph-memory, generated by GitDiagram from its file tree, README and a sample of source files (last updated 2026-11-17). It is an AI-made overview: check details against the source.

- Interactive diagram: https://gitdiagram.com/amarodeabreu/claude-graph-memory
- Repository: https://github.com/amarodeabreu/claude-graph-memory

## Overview

Claude Graph Memory is presented as local persistent graph memory for Claude Code. Its principal indexing workflow parses project documentation and code, then writes the extracted structure to NornicDB; Claude Code is documented as querying and storing memories through MCP. The tree and excerpts expose only the two population scripts, not the hook or MCP implementations, so those documented capabilities are shown without implying their wiring is present here.

Main entry points: [`scripts/populate-doc-graph.py`](https://github.com/amarodeabreu/claude-graph-memory/blob/main/scripts/populate-doc-graph.py) (Documentation indexer), [`scripts/populate-code-graph.go`](https://github.com/amarodeabreu/claude-graph-memory/blob/main/scripts/populate-code-graph.go) (Code indexer)

## Diagram (Mermaid)

```mermaid
flowchart TD

subgraph group_indexing["Graph indexing"]
  node_doc_indexer["Documentation indexer"]
  node_code_indexer["Code indexer"]
end

subgraph group_storage["Graph storage"]
  node_nornicdb[("NornicDB")]
end

subgraph group_client["Claude Code"]
  node_claude(("Claude Code"))
end

node_project_docs["Project docs"]
node_project_code["Project code"]

node_project_docs -->|"reads Markdown"| node_doc_indexer
node_doc_indexer -->|"writes graph"| node_nornicdb
node_project_code -->|"parses Go"| node_code_indexer
node_code_indexer -->|"writes graph"| node_nornicdb
node_claude -->|"queries and stores"| node_nornicdb

click node_doc_indexer "https://github.com/amarodeabreu/claude-graph-memory/blob/main/scripts/populate-doc-graph.py"
click node_code_indexer "https://github.com/amarodeabreu/claude-graph-memory/blob/main/scripts/populate-code-graph.go"

classDef toneNeutral fill:#f8fafc,stroke:#334155,stroke-width:1.5px,color:#0f172a
classDef toneBlue fill:#dbeafe,stroke:#2563eb,stroke-width:1.5px,color:#172554
classDef toneAmber fill:#fef3c7,stroke:#d97706,stroke-width:1.5px,color:#78350f
classDef toneMint fill:#dcfce7,stroke:#16a34a,stroke-width:1.5px,color:#14532d
classDef toneRose fill:#ffe4e6,stroke:#e11d48,stroke-width:1.5px,color:#881337
classDef toneIndigo fill:#e0e7ff,stroke:#4f46e5,stroke-width:1.5px,color:#312e81
classDef toneTeal fill:#ccfbf1,stroke:#0f766e,stroke-width:1.5px,color:#134e4a
class node_doc_indexer,node_code_indexer toneBlue
class node_nornicdb toneAmber
class node_claude toneMint
class node_project_docs,node_project_code toneIndigo
```

## Components

### Graph indexing

- [Documentation indexer](https://github.com/amarodeabreu/claude-graph-memory/blob/main/scripts/populate-doc-graph.py): `scripts/populate-doc-graph.py`
- [Code indexer](https://github.com/amarodeabreu/claude-graph-memory/blob/main/scripts/populate-code-graph.go): `scripts/populate-code-graph.go`

### Graph storage

- **NornicDB**

### Claude Code

- **Claude Code**

### Other components

- **Project docs**
- **Project code**

## Connections

- Project docs → Documentation indexer: reads Markdown (evidence: `scripts/populate-doc-graph.py`)
- Documentation indexer → NornicDB: writes graph (evidence: `scripts/populate-doc-graph.py`)
- Project code → Code indexer: parses Go (evidence: `scripts/populate-code-graph.go`)
- Code indexer → NornicDB: writes graph (evidence: `scripts/populate-code-graph.go`)
- Claude Code → NornicDB: queries and stores (evidence: `README.md`)
