Portable Kong skills and Konnect MCP configuration for agents — contributor source for packaged Konnect, Gateway, DataKit, and declarative-tool skills distributed via marketplace catalogs and plugi…

grow what you know

Train a tiny Transformer from scratch on your iMessage history, entirely on your Mac.

Code based orchestration for any coding agent.

📚 Web app for browsing, reading and downloading eBooks stored in a Calibre database

Build product integrations with AI.

Desktop app to manage markdown knowledge bases

Give your coding agent the power to write and run agent evals.

Scripts for agents, shared between my repositories.

Official CLI for the OpenAI API

DeepSeek 4 Flash local inference engine for Metal

Headless CLI client for stateful Agent Client Protocol (ACP) sessions

Orchestrate sandboxed coding agents in TypeScript with sandcastle.run()

Build your own AI SRE agents. The open source toolkit for the AI era.

Skills for Real Engineers. Straight from my .agents directory.

Open-Source Frontier Voice AI

ClawSweeper scans all issues and PRs and suggest what we can close, and why. It runs every PR / Issue once a week.

⚡ Native MLX Swift LLM inference server for Apple Silicon. OpenAI-compatible API, SSD streaming for 100B+ MoE models, TurboQuant KV cache compression, MACOS + iOS iPhone app.

LLM inference server with continuous batching & SSD caching for Apple Silicon — managed from the macOS menu bar

Visualize, collaborate, and evolve the software architecture with always actual and live diagrams from your code

Keep Codex running forever

One brain, many harnesses. Portable .agent/ folder (memory + skills + protocols) that plugs into Claude Code, Cursor, Windsurf, OpenCode, OpenClaw, Hermes, or DIY Python — and keeps its knowledge w…

A lightweight, powerful framework for multi-agent workflows

A Claude Code skill that turns any codebase into a beautiful, interactive single-page HTML course for non-technical vibe coders.

Garry's Opinionated OpenClaw/Hermes Agent Brain

A single CLAUDE.md file to improve Claude Code behavior, derived from Andrej Karpathy's observations on LLM coding pitfalls.