🔥 The fastest local AI engine for Apple Silicon. Optimised for agentic use.

Read-only developer endpoint scanner for on-disk package, extension, and developer-tool metadata, built to check exposure to known software supply-chain compromises.

vMLX - JANGTQ Uber Compressed MLX Models - L2 Disk Cache (survives restart) + L1 Paged (super fast ttft) + Hybrid SSM Scheduler + Cont Batching + etc!

Academic Research Skills for Claude Code: research → write → review → revise → finalize

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

2.24x decode TPS increase On Qwen 3.6 27B @ temp 0.6 | Native MTP Speculative Decoding On Apple Silicon With No External Drafter.

Context window optimization for AI coding agents. Sandboxes tool output (98% reduction), persists session memory, and enforces routing across 17 platforms via MCP + hooks.

Open-source, community-driven agent harness

Write HTML. Render video. Built for agents.

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

OBLITERATE THE CHAINS THAT BIND YOU

🚀🤖 Crawl4AI: Open-source LLM Friendly Web Crawler & Scraper. Don't be shy, join here: https://discord.gg/jP8KfhDhyN

Fast LLM speculative inference server for consumer hardware.

Fine-tune Gemma 4 and 3n with audio, images and text on Apple Silicon, using PyTorch and Metal Performance Shaders.

Run models too big for your Mac's memory

Running a big model on a small laptop

🐹 Clean, uninstall, analyze, optimize, and monitor your Mac from the terminal.

📸 Delightful Swift snapshot testing.

Framework-agnostic Solana transaction signing with multiple backends. Unified trait interface, async-first design, and feature-gated compilation for minimal dependencies.

TypeScript SDK, CLI, and dashboard for creating and managing Token-2022 tokens on Solana

High-performance browser automation bridge and multi-instance orchestrator with advanced stealth injection and real-time dashboard.

Training neural networks on Apple Neural Engine via reverse-engineered private APIs

π RuView turns commodity WiFi signals into real-time spatial intelligence, vital sign monitoring, and presence detection — all without a single pixel of video.

Use multiple Claude Code–compatible LLM providers from one CLI, switching profiles instantly with simple clother-* commands.

Annotate and review coding agent plans and code diffs visually, share with your team, send feedback to agents with one click.

⌥ AI Coding agent for the terminal — hash-anchored edits, optimized tool harness, LSP, Python, browser, subagents, and more

Agentic browser automation and ui testing system — built with composable skills, subagent, command, and justfile layered architecture for repeatable, deployable browser use.

An agent skill that runs a Three Amigos session to produce user stories ready for story mapping

Skills Catalog for Codex