William Strunk Jr.'s Elements of Style (1918) in markdown format for AI agents

Run a fleet of persistent, identity-bound AI agents across harnesses (Claude Code first, more coming). Declarative fleet.yaml, tmux consoles, systemd/launchd supervision, spawn & oversee subagents,…

Lightweight Go proxy that exposes GitHub Copilot as OpenAI and Anthropic compatible API endpoints

Local AI, native to your Mac. Chat, serve, monitor, and connect MLX models from one macOS app.

Config-driven AI pipeline for triaging and implementing code in the issue board

What are the principles we can use to build LLM-powered software that is actually good enough to put in the hands of production customers?

A fast, single-binary C database that gives AI agents durable, searchable long-term memory — with a Claude Code integration.

Your personal AI agent platform — self-hosted, BYO Claude/Codex subscription

DeepSeek 4 Flash and PRO local inference engine for Metal, CUDA and ROCm

The world's premier FSDK server operating system.

LeafWiki - Self-hosted wiki. Single Go binary, SQLite, Markdown on disk. No external database required.

Any model. Any hardware. Zero compromise. Built with @ziglang / @openxla / MLIR / @bazelbuild

Easy isolated self-hosted GitHub Actions runners (VM-preferred: Tart/libvirt, Docker fallback with hard limits)

Bootable UEFI live ISO for Dakota — offline installation via tuna-installer

Build metadata for building the COSMIC desktop stack using BuildStream

Scripts I had to develop to make Refracta work on Debian 13 with KDE Plasma to pack a running operating system into an identical ISO capable of spawning the next machine

Agentic Software Engineering (ASE)

A set of tools for working with domain models

Collective intelligence runtime for AI agents. Knowledge graph + persistent memory.

Desktop and web interface for OpenCode AI agent

Zero-dep agent workflows with structured approval gates and adversarial review.

Agent-agnostic file-system coordination layer for multi-LLM-agent collaboration (Codex / Claude Code / Cursor / generic).

Katra — Cognitive Memory as a Service for AI Agents. Open-source cognitive memory infrastructure with MCP protocol support.

A persistent, file-based memory layer for coding agents — give Claude Code, Codex & others a project brain (durable decisions, requirements, constraints) via a zero-dependency CLI.

Herd: open-source meta-harness for agent fleets

Bluefin QA pipeline — Argo Workflows, KubeVirt, behave/dogtail GNOME smoke tests

Your personal chief of staff in Claude Code (or Codex) — markdown memory + skills, clone and go. Optional Obsidian vault.

Get your repo ready for AI.