The free AI already on your Mac. CLI tool, OpenAI-compatible server, and interactive chat — all on-device via Apple Intelligence. No API keys, no cloud, no downloads.

为纯文本模型"看图“设计更好的视觉工具箱和技能，支持多图理解，图片问答，前端UI还原、GUI 自动化等，并可选无缝接入多个主流agent，直接识别粘贴图片｜ A vision toolkit and skill designed for text-only llms — image Q&A, long-screenshot OCR, frontend UI restoration, and …

Two-node DGX Spark/ASUS GX10 DeepSeek V4 Flash DSpark NVFP4 port for vLLM 0.25, with live dashboard and reproducible deployment.

DeepSeek-v4-Flash 0731 recipe for 2x DGX Sparks

keys- 1M context: Inkling-Small-NVFP4 + DSpark + NVFP4 KV on SGLang, sm_121a-optimized on Two DGX Sparks — one-shot agent-executable recipe, all GB10 patches + bench numbers

Qualified vLLM TP2 + DSpark K7 recipe for official DeepSeek V4 Flash 0731 on two DGX Sparks

DeepSeek V4 Flash DSpark 1M NVFP4 KV recipe for 2x DGX Spark

Real-time text-to-speech with Qwen3-TTS

SGLang is a high-performance serving framework for large language models and multimodal models.

Head-to-head tool-eval-bench comparison: Laguna-XS-2.1-Q8_0 vs Qwen3.6-35B-A3B-UD-Q8_K_XL

MiMo-V2.5 Omni · TP=3 on 3x DGX Spark · NVFP4 4-bit KV cache → ~3.5x more 1M-context KV pool (3.06M→10.59M tokens) vs FP8

High-performance interactive system monitor for NVIDIA DGX systems — GPU, CPU, memory, disk, network in a beautiful TUI

vLLM, llama.cpp, fine-tuning, etc all on bare metal with the DGX Spark

Democratizing Reinforcement Learning for LLMs

A vector index built on TurboQuant, written in Rust with Python bindings

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

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

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

The best-benchmarked open-source AI memory system. And it's free.

FULL Augment Code, Claude Code, Cluely, CodeBuddy, Comet, Cursor, Devin AI, Junie, Kiro, Leap.new, Lovable, Manus, NotionAI, Orchids.app, Perplexity, Poke, Qoder, Replit, Same.dev, Trae, Traycer AI…

[This fork supports TV accessories] Broadlink RM Mini and Pro plugin for homebridge: https://github.com/nfarina/homebridge

40+ tips for getting the most out of Claude Code, from basics to advanced - includes a custom status line script and Claude Code running itself in a container. Also includes the dx plugin: skills f…

A community-maintained Homebridge plugin for controlling Tuya devices locally over LAN, with an optional Tuya Cloud fallback for whatever the LAN can't reach. Includes new features, fixes, and upda…

Homebridge plugin for Midea devices

Grafana Monitoring Dashboard for Tesla Solar and Powerwall Systems

User-friendly AI Interface (Supports Ollama, OpenAI API, ...)

Get up and running with Kimi-K2.6, GLM-5.2, MiniMax, DeepSeek, gpt-oss, Qwen, Gemma and other models.