SEMANTIC FIELD
Collective Memory · Spatial Knowledge · Place-Anchored Mind

Load a 3D scan of any place. Converse with an AI on a Solari flip-board. Group words by color, draw edges between ideas, and send them into space as annotated nodes — building a shared memory palace one session at a time.

Place Meaning Memory Edge Artifact
Launch App → Read Tutorial ↓
↓ scroll to explore
What is Semantic Field
A collective memory palace

The hippocampus doesn't just store memories — it builds spatial maps. Every memory palace tradition from Simonides to Giordano Bruno exploited this: anchor ideas to places, and the brain retrieves them like a route. Semantic Field makes this literal. Load any real 3D scan, converse with an AI, group the words that matter, connect them with edges, and place them in space — anchored to the geometry that already lives in your body.

Solari Lobby
Type into the flip-board input. The AI responds in three flipping lines. Words and phrases auto-land on your canvas.
3D Scene
Load real .PLY point clouds. Orbit, pan, zoom. Place annotation nodes directly on objects at their 3D coordinates.
Color Canvas
Words and phrases land here. Group them by color — no meaning required. Add meaning later via double-click.
Edges
Connect nodes with labeled edges in 3D space. Draw a triad, a square, a constellation — the graph is yours to shape.
Meaning Layers
Each node holds up to 6 meaning layers — literal, cultural, contested, speculative. Attest, contest, co-evolve with AI.
GitHub Sync
Save a world.json file. Commit it to a shared repo. Collaborators pull and load — merges are non-destructive, per-node.
Step-by-step guide
How to use it

Start with a question. End with a memory palace. Here's the path.

Step 01 / 06
The Solari Lobby

The entry point. Type any question, concept, or provocation into the input field below the board. Hit Enter or SEND. The AI responds on the flip-board — letters scrambling into place like an airport departures sign. Response words and recognized phrases drop automatically onto your canvas.

  • Multi-word phrases that belong together arrive as a single italic chip on the canvas
  • Click any word on the board directly to add it to the canvas manually
  • The board remembers conversation history — build on previous exchanges
  • Try asking it to define a place, a feeling, a tension, or a contradiction
  • Hit Enter Scene → when you're ready to move into 3D space
SEMANTIC FIELD — LOBBY
M
E
A
N
I
N
G
I
S
N
E
G
O
T
I
A
T
E
D
N
O
T
F
I
X
E
D
·
E
V
O
L
V
I
N
G
B
E
G
I
N
A
N
Y
W
H
E
R
E
What does this space mean to you?
SEND
↑ Click any word on the board to add it to your palette
Step 02 / 06
Load your Point Cloud

Drop a .ply file onto the app or use the file button. Exported from Lixel Color Studio, Polycam, RealityCapture, or any photogrammetry tool. The parser handles both ASCII and binary PLY.

  • Lixel exports are usually Z-up — auto-corrected on load
  • Polycam and Gaussian splat files use spherical harmonic coefficients for color — handled automatically
  • Use the pts slider in the toolbar to tune point density vs. crispness
  • Double-click the canvas to reset the view at any time
  • Up to 1 million points rendered live in the browser
SCENE VIEW · PLY LOADED
⟳ Orbit ⊕ Place ◌ Erase pts ▬▬●───
↑ Real point cloud with ground plane · orbit / zoom / pan
Step 03 / 06
Place Semantic Nodes

Switch to ⊕ Place Node mode and click anywhere in the scene to drop an annotation node at that 3D position. A modal opens immediately for you to name it and begin annotating.

  • In Place mode, click any point in the scene — a node appears at that 3D world coordinate
  • Switch back to Orbit mode and drag the ring of any node to reposition it precisely
  • Nodes scale with depth — closer nodes appear larger, distant ones fade
  • Right-click any node to delete it
  • Use + Node in the toolbar to add a node at the scene center
3D SCENE · ANNOTATION NODES
THE ARCHIVE THRESHOLD FLOW drag to move
↑ Nodes depth-scale with distance · drag ring to reposition
Step 04 / 06
Annotate Meaning Layers

Click any node to open the Meaning Editor. Each object holds up to 6 named layers — Literal, Cultural, Contested, Speculative, Poetic, Technical. Layer through them like tuning a radio. Let the AI co-evolve any layer.

  • Click a layer tab to switch to it — write freely in the text area
  • Type in the Co-evolve with AI box to prompt the AI to refine that specific layer
  • Attest meanings: Affirm ✓ · Contest ✕ · Expand + · Ambiguous ~
  • Attach words from your palette directly into a layer
  • Add up to 6 layers per object — each layer is independently versioned
Concept
The Archive
◉ Literal
◉ Cultural
◌ Contested
◌ Speculative
◌ Poetic
◌ Technical
A physical repository of knowledge — dust, decay, and the slow accumulation of things deemed worth preserving. The archive is never neutral; its selection is always a political act.
Attest:
✓ Affirm 5
✕ Contest 2
+ Expand 3
~ Ambiguous 1
Expand the contested dimension — who decides?
Evolve
3 contributors · 7 revisions Crystallize Node →
↑ 6 named layers · attestation · AI co-evolution · crystallize to graph
Step 05 / 06
Canvas, Edges & Sync

Words from the board land on the Canvas panel. Group them by color — no meaning required. Add meaning later via double-click. In the scene, use ⌁ Connect mode to draw edges between nodes. Save a world.json and commit it to a shared GitHub repo to sync with collaborators.

  • Click a token to select it (white outline), then click a color swatch to assign a group
  • Multi-word phrases from the AI arrive as a single italic chip — they're recognized units
  • Double-click any token to add an optional meaning label — visible in the 3D scene on hover
  • ⌁ Connect mode: click node A → click node B → optionally type a relation label
  • Right-click any edge to remove it
  • ⟳ Sync → Save world.json, commit, push. Collaborators pull and Load to receive your update
  • Loads merge non-destructively — newer revision wins, new nodes and edges are additive
Canvas
select → color
threshold
collapse
memory palace
collective memory
archive
dissolve
◈ SEND TO SCENE
World Sync
1 Save world.json
2 git add world.json
git commit -m "..."
git push
3 Collaborator: git pull
4 Load world.json in app
Merges non-destructively.
↑ Color groups · phrase chips · git-based world sync
Step 06 / 06
Clean with Erase Mode

Raw scans always have noise — floating points, background clutter, scan artifacts. Switch to Erase mode and paint over any points to remove them. Each stroke is one undo step.

  • Click ◌ Erase in the toolbar — a circular brush cursor appears
  • Paint over noisy or unwanted points to hide them
  • Adjust the brush slider for fine or broad strokes
  • Hit ↩ Undo to restore the last stroke's points exactly
  • Erased points are non-destructive — hidden, not deleted — until you export
ERASE MODE ACTIVE
brush
⟳ Orbit ⊕ Place ◌ Erase brush ──●── ↩ Undo
↑ Paint to erase · brush size control · undo per stroke
Reference
Controls & Shortcuts
Action Input Notes
Orbit sceneLeft dragHorizontal + limited vertical — can't go below ground
Pan sceneRight drag or Alt + dragMoves the orbit pivot point
ZoomScroll wheelExponential — works at any scale
Reset viewDouble-click canvasReturns to full-scene overview
Move a nodeDrag the ringSlides on camera-aligned plane in 3D
Open annotation editorClick the ringShort click = open, drag = move
Delete a nodeRight-click nodeRemoves node and all its edges
Draw an edge⌁ Connect → click A → click BOptional relation label on confirm
Delete an edgeRight-click edge lineImmediate, no confirm
Add word to canvasClick word on boardOr automatically from AI responses
Group canvas tokenClick token → click color swatch6 color groups, no type required
Label a tokenDouble-click tokenOptional meaning — shown on hover in scene
Send canvas to scene◈ Send to SceneCommits canvas as a new graph node
Save world⟳ Sync → Save world.jsonAPI keys never written to file
Load / merge world⟳ Sync → Load world.jsonNon-destructive merge — newer revision wins
Erase points◌ Erase mode → paintScreen-space brush — hides, doesn't delete
Undo erase↩ Undo buttonOne undo per stroke, stackable
Color & Type
Grouping Without Commitment

The canvas uses color groups as the primary organizing tool — assign any word to a color without needing to name what the color means. Groups can be labeled later, or left as pure visual clusters. When you send a canvas to the scene, the dominant group maps loosely to one of five underlying node types — a scaffold you can override at any time.

Event
Something that happened. A moment with before and after. Ruptures, transitions, occurrences in time.
Concept / Lens
An interpretive frame. Ideas, categories, ways of seeing. The tools we bring to things rather than the things themselves.
Process
How something unfolds. Cycles, transformations, flows, feedback loops — duration as the primary quality.
Relation
A connection between things. Dependencies, analogies, tensions, affinities. Better expressed as an edge than a node.
Artifact
A document, object, image, or medium. Things that carry meaning across time — containers, not just contents.

Types are a lightweight scaffold — useful for export and querying, but never a gate. Start with color. Name it when it matters.

Workflow
The Loop

Semantic Field is designed for iterative return. Each session leaves a world.json that the next session — or next collaborator — picks up from.

01
Capture
Scan any space with Lixel, Polycam, RealityCapture, or any photogrammetry tool. Export as .ply.
02
Converse
Ask the Solari board questions about the space. Words and phrases land on the canvas automatically.
03
Group & Connect
Color-group canvas tokens. Send them into 3D space as nodes. Draw edges between related nodes.
04
Annotate
Click any node to open its meaning editor. Layer literal, cultural, contested, speculative readings. Co-evolve with AI.
05
Sync
Save world.json. Commit to a shared GitHub repo. Collaborators pull, load, and add their own layers.
Why spatial memory matters
The Hippocampus & the Map

Deep in the medial temporal lobe sits the hippocampus — a seahorse-shaped structure that is the brain's cartographer. It does not merely store memories; it builds cognitive maps. O'Keefe & Nadel's 1978 discovery of "place cells" — neurons that fire precisely when an animal occupies a specific location — established that the hippocampus is a genuine spatial computing engine, earning a Nobel Prize in 2014.1

The maps it builds are not limited to geography. The hippocampus encodes relational structure of any kind: the layout of ideas, the sequence of events, the connections between concepts. Memory palace techniques work precisely because they hijack this spatial machinery — anchoring abstract information to imagined places so the hippocampus can retrieve it like a route.

"The posterior hippocampi of taxi drivers were significantly larger relative to those of control subjects… volume correlated with the amount of time spent as a taxi driver."
— Maguire et al., PNAS 2000 2

This plasticity cuts both ways. A 2020 study found that habitual GPS use correlated with a steeper decline in hippocampal-dependent spatial memory over three years — and importantly, the decline was observed even in people who started with strong navigation ability, suggesting GPS use caused the drop rather than selecting for weaker navigators.3

Chronic stress compounds the problem. The hippocampus is densely packed with cortisol receptors. Sustained elevation of cortisol — a hallmark of urban crowding, noise, social precarity, and nature deprivation — suppresses adult neurogenesis in the dentate gyrus and causes dendritic atrophy.4 A study of 156,075 UK Biobank participants found that urban environments characterized by social deprivation, air pollution, and high density were associated with measurable brain volume differences along stress-response pathways.5 A separate analysis of ~1,000 adults found that those living in the most disadvantaged neighborhoods had hippocampal volumes equivalent to seven additional years of age-related atrophy.6

Note: these studies show correlation, not simple causation — genetic selection, socioeconomic confounds, and reverse causality are active areas of debate. The mechanism (chronic stress → cortisol → hippocampal atrophy) is well-established; the urban attribution requires care.

  • 1 O'Keefe & Nadel, The Hippocampus as a Cognitive Map, Oxford UP, 1978. Nobel Prize in Physiology or Medicine 2014.
  • 2 Maguire EA et al. "Navigation-related structural change in the hippocampi of taxi drivers." PNAS 97(8), 2000. doi:10.1073/pnas.070039597
  • 3 Dahmani L & Bohbot VD. "Habitual use of GPS negatively impacts spatial memory during self-guided navigation." Scientific Reports 10, 2020. doi:10.1038/s41598-020-62877-0
  • 4 Kim EJ et al. "Stress effects on the hippocampus: a critical review." Learn Mem 22(9), 2015. PMC4561403
  • 5 Sebert S et al. "Effects of urban living environments on mental health in adults." Nature Medicine 29, 2023. doi:10.1038/s41591-023-02365-w
  • 6 "Living in Disadvantaged Neighborhoods Linked to Brain Atrophy." Medscape, citing neighborhood ADI study, 2020.
~477 BCE
Simonides of Ceos survives a banquet hall collapse and identifies the crushed victims by reconstructing their seating arrangement from memory. He formalizes what he did as the method of loci — anchor each thing to be remembered to a place in a known building, then walk through it to recall in order.
~55 BCE
Cicero and the anonymous Rhetorica ad Herennium codify the technique for Roman orators. Senators memorize entire speeches without notes by walking imaginary architectures. The phrase "in the first place" is a linguistic fossil from this practice.
1582
Giordano Bruno publishes De Umbris Idearum — combining the classical method of loci with Hermetic cosmology and rotating zodiacal memory wheels. Bruno's ambition was total: a mnemonic system that encoded all knowledge as an architectural theater of the mind. He was burned at the stake in 1600. Historian Frances Yates recovered his work in The Art of Memory (1966).
1978
O'Keefe & Nadel publish The Hippocampus as a Cognitive Map, establishing that spatial memory has a physical substrate. The memory palace is not a metaphor — it is a description of how the brain actually works.
2000
Maguire et al. demonstrate that London taxi drivers grow their posterior hippocampus through years of active navigation. The brain is plastic in response to spatial practice — it expands to accommodate the map.
Now
XR + Gaussian splats make Bruno's memory theater literal. A photorealistic 3D scan of any space becomes a navigable knowledge structure — place cells fire in virtual environments just as they do in physical ones. Semantic annotations anchored to real geometry create spatially-indexed knowledge graphs shareable across any device. The map travels with the space.
The Map is Never the Territory

Alfred Korzybski's maxim — coined 1931 — is the permanent disclaimer on any knowledge system. No map is complete. Every annotation carries its author's blind spots, the period's assumptions, the language's limits. But sharing and refining maps between people with different vantage points is the closest collective process we have to becoming less wrong together. The semantic field is not truth — it is a convergence process.

On Cyphers

A cipher is a systematic substitution: replace each element of a message with a symbol from a chosen alphabet. Memory palaces work identically — replace each idea with a vivid image placed in a location. The code is spatial. Semantic Field extends this: each node is a cypher unit, its meaning layers the key, its attestations the checksum. A shared knowledge graph is a collectively-legible cipher for a shared world.

Yates FA. The Art of Memory. Routledge, 1966. Modern Library list of 100 Best Nonfiction Books.
Open Source
Single HTML file

The entire app — 3D point cloud engine, PLY parser, Solari board, color canvas, edge graph, meaning layers, and world sync — ships as one self-contained HTML file. No build step. No server. Drop it anywhere. Fork it freely.

Launch Semantic Field → View on GitHub ↗
Requires: modern browser · Claude.ai or Anthropic API key for AI features · .PLY file for 3D scene (demo scene included)