Start

START Project Documentation Hub

Welcome to the comprehensive documentation for the START (Scalable, Tailored Active-inference Research & Training) project - an advanced AI-powered system for creating personalized Active Inference and Free Energy Principle curricula.

๐Ÿš€ What is START?

START is a complete educational content generation pipeline that combines:

๐Ÿ“š Documentation Structure

Core Guides

๐Ÿ› ๏ธ Setup & Development

๐Ÿ”„ System Architecture

๐Ÿงช Methods and Publication

๐Ÿ”— External Integrations

Specialized Documentation

๐Ÿ“– User Guides

๐Ÿ”ง Configuration Reference

๐Ÿ“ฆ Data & Outputs

๐Ÿ“Š Visualizations

๐ŸŒ Translations

๐Ÿงญ Docs & Deployment

๐Ÿ“ Prompt Engineering

๐ŸŽฏ Quick Start Paths

For New Users

  1. Environment Setup - Get up and running
  2. Pipeline Overview - Understand the system
  3. Usage Guide (GitHub)

For Developers

  1. Environment Setup - Development environment
  2. API Docs (GitHub)
  3. Tests (GitHub)

For Researchers

  1. Pipeline Overview - Research capabilities
  2. Clone Management - Access research repositories
  3. Configuration Files - Customize research targets

๐ŸŒ External Resources

Active Inference Institute Ecosystem

Math & Programming Resources

In-Repo Entry Points

๐Ÿ“‹ System Capabilities

Research & Analysis

Content Generation

Visualization & Media

Multilingual Support

๐Ÿ”ง Configuration Overview

Research Configuration

# data/config/entities.yaml
entities:
  - name: "karl_friston"
    category: "scientist"
    priority: "high"

# data/config/domains.yaml
domains:
  - name: "biochemistry"
    category: "life_sciences"
    priority: "high"

Command-Line Interface

# From repository root; installed commands use the locked uv environment
uv sync --all-extras --dev

# Research high-priority entities
uv run start-curriculum --non-interactive --stages entity-research \
  --entity-priority high --json

# Generate domain-specific curricula
uv run start-curriculum --non-interactive --stages domain-research \
  --domains biochemistry --json

# Create multilingual content
uv run start-curriculum --non-interactive --stages translations \
  --languages Spanish French --json

# Inspect generated output contracts and deterministic offline fixtures
uv run start-validate-outputs --check
uv run start-regenerate-offline --output-dir /tmp/start-fixtures --json

๐Ÿ“Š Project Structure

START/
โ”œโ”€โ”€ src/                      # Core system implementation
โ”œโ”€โ”€ learning/                 # Curriculum creation scripts
โ”œโ”€โ”€ data/                     # Generated content and configuration
โ”œโ”€โ”€ docs/                     # Comprehensive documentation
โ”œโ”€โ”€ tests/                    # Test suite and validation
โ””โ”€โ”€ README.md                 # Project overview and quick start

๐Ÿ”„ Development Workflow

Standard Development Cycle

  1. Configure targets in data/config/ YAML files
  2. Run research using domain and entity scripts
  3. Generate curricula with comprehensive content creation
  4. Create visualizations for enhanced learning
  5. Translate content for multilingual accessibility

Quality Assurance

๐Ÿ“ž Getting Help

Documentation Resources

Community & Support


START represents a new paradigm in educational content creation, combining cutting-edge AI research capabilities with comprehensive pedagogical design to produce world-class Active Inference curricula tailored to any professional domain or individual learner.