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.

Local-first personal AI. Runs on your machine, remembers your work, helps research & workflows. Optional P2P. Alpha.

Free-first, model-adaptive coding agent runtime that makes local small LLMs work reliably with harness, checkpointing, verification, cache-aware context, and free-model fallback.

Structured planning, bounded memory, TDD, and Git guardrails for local coding models in Pi Code (I don't know TypeScript at all; this is mostly a local-model experiment, with occasional help from Claude Code)

A self-hosted AI document knowledge platform, private and on-premise RAG.

A Desktop Agent that can work on any OpenAI compatible API endpoint including local LLMs too.

LLM-as-a-Judge framework for profiling local model capabilities across domains — toward automated model team composition

Open-source interoperability layer for Coding Agents & LLMs

A simple agent helps you summary your daily email.