Cognir — Documentation

Getting Started ←|

Overview<br>Quickstart<br>Architecture<br>Core Concepts

Document Processing

Importing Documents →<br>Text Extraction<br>AI Concept Extraction<br>Reader & Annotation

Note Editor

Overview →<br>Multi-Page System<br>Rich Formatting<br>Annotation Mode<br>Reading Mode

Knowledge Graph

Zettelkasten System →<br>3D Visualization<br>Node Types<br>Filters & Navigation<br>Editing Nodes

Export & Output

Compilation & Export →<br>Export Formats

Configuration

API Key Management<br>AI Providers<br>Data Storage<br>Themes & Preferences<br>Backup & Import

Reference

Keyboard Shortcuts<br>Troubleshooting<br>Glossary

Getting Started / Overview

Cognir Platform Overview

Cognir is a local-first, AI-augmented knowledge work environment designed for deep engagement with complex textual material. It provides an integrated pipeline for document ingestion, semantic concept extraction, active annotation, multi-page note composition, three-dimensional knowledge graph construction, and structured output compilation.

The platform operates entirely within the browser. No data is transmitted to external servers except direct API calls to the configured AI provider. All persistent state — documents, annotations, notes, and knowledge graphs — is stored in IndexedDB with a localStorage fallback.

Platform Philosophy

Cognir is built on the principle that every idea that matters should cost you a thought . Passive storage creates an illusion of knowledge; active annotation forces cognitive compression, which is the mechanism of genuine understanding.

Core Capabilities

CapabilityDescription<br>Document IngestionPDF, DOCX, TXT, and Markdown file parsing with multi-file support<br>Semantic ExtractionAI-driven concept, thesis, and argument extraction from source material<br>Active AnnotationSelect any text element and attach structured thoughts with Zettelkasten integration<br>Multi-Page EditorRich text composition with formatting, math symbols, image insertion, and page management<br>3D Knowledge GraphForce-directed three-dimensional visualization of atomic ideas and their connections<br>Structured ExportCompile knowledge into paragraphs, bullets, reports, or concise formats<br>Local-First StorageAll data persists in-browser via IndexedDB; zero server-side storage

Quickstart

This section provides a minimal path to first value. Users can be operational within two minutes of initial load.

Step 1: Configure an API Key

Cognir requires an API key from a supported AI provider to perform semantic extraction and knowledge graph synthesis. The platform ships with a shared default Groq key for immediate evaluation, but users are strongly encouraged to provision their own key for production use.

Click the Settings button (☰) in the top-right corner of the landing page.

Paste your API key into the input field. The system will auto-detect the provider based on key prefix.

Click Save Key . The key is stored exclusively in your browser's IndexedDB.

Step 2: Import a Document or Start a Note

From the landing page, users have two entry points:

Load Document — Upload a PDF, DOCX, TXT, or Markdown file. The system will extract text, perform AI-driven concept extraction, and present an annotated reader view.

Try Cognir — Opens the multi-page note editor directly with a pre-built starter document demonstrating the annotation and graph workflow.

Step 3: Annotate and Build

Once in the reader or note editor, select any text to trigger the annotation popup. Write your reaction or analysis. After accumulating annotations, click Graph to generate the 3D knowledge map. Finally, click Compile Output to export your synthesized knowledge.

Tip

For first-time users, the platform loads a pre-built starter document called "The Cognir Method" with three pre-annotated passages and a pre-computed 3D knowledge graph. This allows immediate exploration of the full workflow without any AI API calls.

Architecture

Cognir is a single-page application delivered as a self-contained HTML file. It requires no build step, no server, and no installation. The architecture is intentionally minimal to reduce attack surface and maximize portability.

Runtime Dependencies

LibraryVersionPurpose<br>PDF.js3.11.174Client-side PDF text extraction with coordinate-aware parsing<br>Mammoth.js1.6.0DOCX to plain text conversion<br>Three.jsr128WebGL-based 3D knowledge graph rendering<br>Google Fonts—Inter (UI), Lora (prose), JetBrains Mono (code)

Data Flow

─────────────┐ ┌──────────────┐ ┌─────────────┐ ┌──────────────┐<br>│ File Input │────▶│ Text Extract│────▶│ AI Extract │────▶│ Concept │<br>│ (PDF/DOCX/ │ │ (pdf.js / │ │ (Provider │ │ Model │<br>│ TXT / MD) │ │ mammoth) │ │ API call) │ │ (JSON) │<br>└─────────────┘ ──────────────┘ └─────────────┘ └──────────────┘<br>┌─────────────┐ ┌──────────────┐ ┌─────────────┐ ┌──────────────┐<br>│ Export │────│ Zettelkasten│◀────│ Annotation │◀────│ Reader / │<br>│ (TXT) │ │ Graph (3D) │ │ System │ │ Note Editor │<br>└─────────────┘ └──────────────┘ └─────────────┘ └──────────────┘

Storage Architecture

All...