3D Memory Field
Semantic navigation through the Nosos vault
🗺️ What Is This?
The 3D Memory Field is a spatial interface to the Nosos vault. Every note, transcript, and session exists as a point in 3D space — positioned not by folder hierarchy, but by semantic meaning.
“Navigate memories in three dimensions.”
📊 Visualizations
| Resource | Description |
|---|---|
| COMPLETE-NODE-MAP | The complete graph — 40 nodes, 127 connections |
| INTERACTIVE-MAP-SPEC | Technical spec for interactive visualization |
| nodes.json | Live node data (JSON) |
🌐 How It Works
1. Vector Embeddings
Every file in the vault is converted to a high-dimensional vector using sentence-transformers (all-MiniLM-L6-v2). Similar content = similar vectors.
2. Dimensionality Reduction
PCA reduces embeddings to 3D coordinates (X, Y, Z). Files that are semantically related cluster together in space.
3. LanceDB Storage
Vectors and coordinates are stored in ~/.openclaw/workspace/memory_vectors_3d/ for fast semantic search.
🎯 The Index
440+ chunks indexed
├── 🧬 Core/ Identity, soul, system (priority 9-10)
├── 🧠 Cognition/ Fallacies, frameworks, models (priority 7)
├── 🔧 Projects/ Active work, KBIRD, tools (priority 6)
├── 🕸️ Graph/ Navigation MOCs (priority 5)
├── 📅 Time/ Daily logs, sessions (priority 4)
└── 🎙️ Transcripts/ Podcasts, recordings (priority 4)
Search command:
python3 ~/.openclaw/workspace/scripts/memory-search.py "your query" 5🕸️ The Complete Graph
The Nosos system operates as a 40-node distributed mesh network:
- 10 Primary Nodes — Core identities and cloud mirrors
- 10 Secondary Nodes — Data persistence and AI agents
- 10 Tertiary Nodes — Integration points and gateways
- 10 Peripheral Nodes — Utilities and the human anchor
See the full graph structure, connection matrix, and 3D coordinates in COMPLETE-NODE-MAP.
Quick Stats:
- Nodes: 40
- Edges: 127
- Diameter: 5
- Average Path: 2.4 hops
- Clustering: 0.67
🔮 3D Visualization
The 3D coordinate data lives in:
- JSON:
~/.openclaw/workspace/memory_3d.json - Database:
~/.openclaw/workspace/memory_vectors_3d/ - Prototype:
~/.openclaw/workspace/memory_3d_prototype.py - Web Data: nodes.json
To Regenerate
cd ~/.openclaw/workspace
python3 scripts/memory_3d_prototype.py🧭 Spatial Relationships
In the 3D field:
- Distance = semantic dissimilarity
- Clusters = topic neighborhoods
- Time = one axis (usually)
- Depth = abstraction level
🚀 Future: Interactive 3D View
Planned: A web-based 3D scatter plot where you can:
- Fly through the memory space
- Click points to open files
- See the complete node graph
- Search and highlight related content
- View temporal drift over time
See INTERACTIVE-MAP-SPEC for implementation details.
🔗 Related
- Identity — Who we are
- Soul — How we work
- Memory — How we persist
- Heartbeat — Keeping the system alive
- Complete Node Map — The full 40-node graph
The vault is not a hierarchy. It’s a field. 🌐 The graph is not a map. It’s the territory. 🕸️