Minimize surprise. Maximize evidence.
Welcome to the open-source curriculum infrastructure for Active Inference education. This repository hosts 17 complete courses spanning Kindergarten to PhD, powered by a modular Python publishing engine.
Maintained by Dr. Daniel Ari Friedman (@docxology) at the Active Inference Institute.
All courses share a unified 8-topic spine grounded in the Free Energy Principle, revisited at increasing levels of mathematical and conceptual formalism.
| Topic Spine | Systems → Agents → Perception → Cognition → Action → Learning → Communication → Planning |
|---|
| Course | Audience | Focus |
|---|---|---|
| Elementary | Grades K-5 | Stories, play, and drawing |
| Family | Verified Families | Parent-child co-learning activities |
| Middle School | Grades 6-8 | Scratch programming & logic |
| High School | Grades 9-12 | Python basics & guided labs |
| College 101 | Undergraduates | Full notation & standard simulations |
| Advanced 401 | Graduate/PhD | Research seminars & formal proofs |
| Track | Focus | Lab Style |
|---|---|---|
| Philosophy | Argumentation & Ontology | Thought Experiments |
| Cognitive Science | Neuroscience & Psychology | Case Studies |
| Mathematics | Formal Derivations | Proofs & Exercises |
| Computer Science | Implementation & Algorithms | Python active_inference Lib |
- Embodied Cognition (Somatic practice)
- Organizations (BioFirm framework)
- Robotics (ROS2 & Hardware)
- Crochet (Fiber arts & morphological computation)
- Inventions (Creative engineering)
- Metallurgy (Materials science)
- Python 3.11+
- uv (recommended)
git clone https://github.com/ActiveInferenceInstitute/courses.git
cd courses/software
uv sync# Render the Philosophy track to Text and Markdown
uv run python scripts/generate_all_outputs.py --course ai-philosophy --formats txt,md
# Preview the full publishing pipeline
uv run python ../publish.py --dry-runSee the Quick Start Guide for full details.
This repository is powered by a custom Python rendering engine (software/) that orchestrates the transformation of Markdown source files into 6 output formats.
graph TD
Source["📚 Source Content<br/>(Markdown)"] --> Engine["⚙️ Publishing Engine<br/>(Python 3.11+)"]
Engine --> PDF["📄 PDF<br/>(WeasyPrint)"]
Engine --> HTML["🌐 HTML<br/>(Interactive)"]
Engine --> DOCX["📝 DOCX<br/>(Word)"]
Engine --> MP3["🎧 MP3<br/>(gTTS)"]
Engine --> TXT["TXT"]
Engine --> MD["MD"]
style Source fill:#fef3c7,stroke:#d97706
style Engine fill:#dbeafe,stroke:#2563eb
style PDF fill:#d1fae5,stroke:#059669
- Architecture Guide: Deep dive into the 5-layer system design.
- CLI Reference: Documentation for all 22 CLI scripts.
- Module API: Reference for the Python source modules.
We maintain AGENTS.md files at every directory level to provide context-aware guidelines for AI agents.
- Repository Guidelines
- Real Methods Only: We strictly enforce a "no mocks" policy in testing.
We maintain a structured archive of ~2,600 video transcripts from the Active Inference Institute's YouTube channel, organized into 38 playlists including:
- Livestreams & Paper Discussions (1,000+ videos)
- GuestStreams (900+ videos)
- Textbook Cohorts (Parr et al. 2022)
- Applied Active Inference Symposia
See YouTube Documentation for the transcription and translation pipelines.
We welcome contributions to both the curriculum and the software engine!
- Read CONTRIBUTING.md.
- Ensure you have
uvinstalled. - Follow the Content Authoring guidelines.
We maintain a robust suite of 1,021+ tests ensuring curriculum integrity and software stability.
cd software
uv run pytest tests/This work is licensed under CC BY 4.0. © 2026 Active Inference Institute.
Generated by the Active Inference Institute Publishing Pipeline. Last updated: 2026-02-15.