The open-source infrastructure for Artificial General Intelligence.
This wiki is your guide to the Hyperon stack — the canonical, continuously-updated reference connecting the big-picture ideas to the papers and working code behind them, with a clear on-ramp for newcomers and depth for experts. Start with a tutorial, go as deep as you like, and never lose the thread from concept to implementation.
Hyperon is a composable, neurosymbolic platform for integrating diverse machine cognitive processes — from symbolic reasoning and probabilistic inference to neural learning and evolutionary search. These collaborate through a principle called cognitive synergy, so the system can tackle problems none of them could solve alone. The result is not a static toolbox but a common cognitive medium in which learning, reasoning, attention, motivation, and program synthesis enter into recurrent, auditable loops. Read the full vision & architecture → About Hyperon
Every topic links to both, side by side — students begin with the tutorial; experts go straight to the deep dive. Neither is gated behind the other.