Operations substrate for AI agents that use real software: 311 sites/tools, logged-in browsers, desktop apps, local tools, MCP, policy, evidence, AgentEnvelope v2, and self-repair.

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.

AI-powered code healing and self-repair system for Ruby applications

The AI that remembers you. Forever. — A living digital entity built in Rust. 68 crates. Self-writing genome. Persistent memory. Constitutional governance. Drop a TOML file, Hydra learns.

macOS-only YouTube audio downloader converting to lossless WAV/PCM. Simple Tkinter GUI and flexible CLI using yt-dlp and ffmpeg. Includes self-repair and maintenance tools.

Continuity-Aware Self-Repair algorithm engine, benchmark, and demo for AI short-drama pipelines

Research pilot (dormant): does one simple repair decision space work across math & output-constraint domains?

A Claude Code skill that turns a mission into a self-maintaining, self-repairing agent harness.

Fault Tolerance via Generative Neural Cellular Automata

CodeForge — AI Code Agent with Self-Repair. Full-stack FastAPI + Next.js app with multi-agent orchestration, sandboxed code execution, and LLM routing.

Mechanistic Interpretability as a Control System: Dissociations, Data Attribution, and Autonomous Self-Repair in Language Models

~72 runnable engineering guides on agent runtimes, self-custody, and local-first systems — each with the problem, the design decisions, and a demo you can run.