KAIROS in Pictures
A few views of the application.
AI-Assisted Cognitive Mapping
KAIROS is currently available in French. English localization is in progress.
Turn your AI conversations into structured thought. KAIROS replaces the linear chat with a canvas of connected cards, measures the vitality of your thinking in real time, and injects friction when ideas start going in circles.
When you think with an LLM, a silent dynamic takes over: mutual agreement. The model validates, you nod along, and thought locks itself into a comfort loop.
Friction is not noise to be reduced. It's the engine of emergence. When your ideas look too much alike, KAIROS throws in a question that disrupts — to restart thought.
Instead of a scrolling thread of messages, KAIROS lays your ideas on a spatial canvas. Each idea is a card, each link a connection. The result is a thought graph you can explore, rearrange, and structure.
Generates new cards connected to the existing graph. Two automatic sub-modes: deepen when the graph is open, diverge when it converges too much.
Degressive generation: 3 cards at first, then 2, then just 1 targeted card as the canvas matures. The AI gradually steps back.
Links orphan cards to each other. No new content — only connections. Weaves the graph's structure.
Structured reading of the graph in 3 blocks: thread (overall narrative), blind spots (under-explored areas), structural question (the question the graph is asking without formulating it).
Independent convergence analysis. 3 possible scopes: active graph, archived synthesis, or card selection. Produces a thread, action levers, and detected tensions.
Export as editorial HTML document (glassmorphism design, SVG arcs, refined typography).
KAIROS measures the cognitive vitality of your canvas in real time. A score from 0 to 100, a 3-axis radar triangle, and automatic intervention when thought starts suffocating.
The score is calculated around a neutral point of 50, modulated by 4 signals and 4 topological metrics.
3 independent axes from 0 to 100 that measure the balance of your thinking.
The chosen cognitive posture (Accompany, Name, Provoke) redistributes the triangle's weights.
The score determines system behavior.
Content diagnostics: semantic echo (redundancy between cards via 42K-entry thesaurus), tag saturation and concentration. These diagnostics are informational — they don't modify the score, but can cap it: a redundant graph can't display 95.
The AI builds on your ideas, not the other way around. KAIROS tracks the origin of every element and measures your ownership of the graph.
Every card carries its origin: user, LLM, friction, or capture. Cards created manually are tagged [USER] in the LLM context — the AI builds on them instead of rephrasing them.
Cards created since the last LLM cycle are tagged [USER·NEW] and become priority input for the next generation.
The Sovereignty axis of the radar triangle quantifies your ownership of the graph: nodes you created, connections you drew, and LLM cards you edited to make them yours.
A graph entirely generated by AI will have sovereignty near zero. KAIROS flags it, without forbidding it.
As the canvas matures, the AI generates less. At first, DEVELOP proposes 3 cards. Then 2. Then just 1, targeted. The AI fades when thought takes shape.
~29,000 lines of TypeScript, 725 unit tests, no framework. Everything below is implemented and functional.
Obsidian (dark, default), Porcelain (light taupe), Aurora (dark blue), Kraft (warm sepia).
Bézier curves with pulsing glow and animated SMIL particles. Implication (green, directional) and resonance (amber, bidirectional).
4 depth layers (scale, opacity, blur), mouse parallax, micro-rotation per card.
Sacred geometry (11 patterns), flow field, audio-reactive. Palette adapts to theme and time of day.
Claude (Anthropic), ChatGPT (OpenAI), DeepSeek, Mistral, Groq, Ollama (local). Config via radio cards, inline API key, model dropdown.
3 blocks: thread (narrative), blind spots (under-explored), structural question. Cards archived and repositioned.
Cards generated by DEVELOP are positioned near their connection target, not stacked at the bottom of the canvas.
History of every LLM interaction. System prompt / user prompt separation. Import indicators per card (✓ accepted / – ignored).
Browser-style tab bar (Ctrl+T / Ctrl+W). Each canvas has its own LLM provider and model. Provider badge on each tab.
Integrated audio visualization + web radio mode (7 stations). Audio-reactive ambient background.
9 full-screen slides, ephemeral demo canvas, 5 contextual coach marks. Built-in LLM setup wizard.
SQLite backups every 30 min + on quit. Error boundaries, persistent logs, API key validation on startup.
A few views of the application.
KAIROS builds on academic work in conversation analysis, cognitive psychology, and pragmatic linguistics.
Conversational repair detects and resolves comprehension breakdowns. KAIROS uses these markers to identify moments of productive friction.
Conflict between different perspectives stimulates learning and cognitive development. Friction is not an obstacle but an engine.
Discourse markers signal relationships between utterances. "But", "however", "actually" indicate productive friction.
Epistemic regulation (productive) vs. competitive (parasitic). KAIROS distinguishes friction that advances from friction that blocks.
The theoretical model behind KAIROS. Resonance emerges when intention and friction combine against linearization.
Watch KAIROS's core mechanism: the O₂ gauge measures cognitive diversity. When ideas converge too much, friction is injected to restart thought.
+ Card — add ideas to the canvas
DEVELOP — generates connected ideas
CONNECT — links orphan cards
SYNTHESIZE — structured reading of the graph
O₂ = cognitive vitality. When it drops below 30, KAIROS injects friction to break convergence.
Create cards, launch DEVELOP to generate ideas, use CONNECT to link your thinking — all directly in your browser, no API key, no install.
KAIROS is for people who use LLMs to think, not just to produce.
Explore hypotheses without falling into confirmation bias
Brainstorm without circling the same ideas
Push a line of thought beyond comfortable agreement
Learn to structure thinking and detect blind spots
Map a complex problem, identify dependencies
Prepare a thesis, dissertation, or structured argument
KAIROS project documentation, automatically synced from the repository.