PyHGF: A neural network library for predictive coding

Deep active inference agents using Monte-Carlo methods

PyTorch library for Active Fine-Tuning

Official Implementation for the paper "SR-AIF: Solving Sparse-Reward Robotic Tasks from Pixels with Active Inference and World Models"

A sovereign cognitive architecture with IIT 4.0 integrated information, residual-stream affective steering (CAA), Global Workspace Theory, active inference, and 72 consciousness modules — running locally on Apple Silicon.

Implementation/simulation of active neural generative coding (ANGC) for training neurobiologically-plausible active inference agent models.

Manuscript source: Self-orthogonalizing attractor neural networks emerging from the free energy principle

MLSS-2026 Melbourne Bert's lectures

[NeurIPS 2021] World modelling and action learning using a contrastive formulation of the active inference framework, for reaching visual goal states

Cognitive science research workspace — Active Inference, Bayesian modeling, ant behavior, and computational neuroscience

PID-like control implemented as active inference with linear generative models

Active Inference & Category Theory

Homing Piegon is an inference framework implementing Variational Message Passing. It can be used to implement an Active Inference agent that performs planning using a Tree Search algorithm that can been seen as a form of Bayesian Model Expansion.

Deep Active Inference (Deep AIF) Agents

DIE — is an Artificial Life project aimed at reproducing emergence of distributed intelligence under environmental pressures using learning cellular automata models.

Active inference agent and corresponding environment in Unity used in the study "A deep active inference model of the rubber-hand illusion"