Featured

Local LLM

New 2026

DeepSeek 4 Flash local inference engine for Metal

New 2026

Reduce your LLM costs by 40-70% automatically. Routes prompts locally, compacts context, tracks real savings.

New 2026

Run OpenClaw Natively on Android — No Root, No Ubuntu, No proot

New 2026

Reverse proxy for Claude Code that anonymizes sensitive pentest data (IPs, hashes, credentials, hostnames, PII) before it reaches Anthropic. Dual-layer detection: local Ollama LLM + regex safety net, with per-engagement vault and self-improving feedback loop.

New 2026

Exact speculative decoding on Apple Silicon, powered by MLX.

New 2026

Run LLMs on Apple devices with CoreML, optimized for Apple Neural Engine + GPU

New 2026

Karpathy’s LLM Wiki, 100% local with Ollama. Drop Markdown notes → AI extracts concepts → your Obsidian wiki auto-links and grows. Zero sharing. Your notes stay yours.

New 2026

Autonomous AI movie studio — turn a text prompt into a fully produced video. 100% local, no cloud, no API keys.

New 2026

Gemma Gem runs Google's Gemma 4 model entirely on-device via WebGPU — no API keys, no cloud, no data leaving your machine.

New 2026

On-device, real-time multimodal AI. Have natural voice and vision conversations with an AI that runs entirely on your machine. Powered by Gemma 4 E2B and Kokoro.

New 2026

Community benchmark database for running LLMs on Apple Silicon Macs

New 2026

Auto pilot for Claude Code - connect multiple coding agents to a local LLM brain. 🆕 with a hive mind now

New 2026

Lucebox optimization hub: hand-tuned LLM inference, built for specific consumer hardware.

New 2026

Atomic-Chat is an open source alternative to ChatGPT that runs 100% offline on your computer.

New 2026

AI-powered penetration testing assistant using local LLM on linux (Parrot OS)

New 2026

runs anywhere. uses anything

New 2026

Atomic-Chat is an open source alternative to ChatGPT that runs 100% offline on your computer.

New 2026

A ~9M parameter LLM that talks like a small fish.

New 2026

A real-world use case demo for multi-AI-agent with authorization and deterministic verification to secure money flows

New 2026

一款开源 AI 驱动的本地 SSH 客户端

New 2026

Run Claude Code 100% on-device with local AI on Apple Silicon. MLX-native Anthropic-API server, 65 tok/s Qwen 3.5 122B, Llama 3.3 70B, Gemma 4 31B. Private, offline, airgap-ready. Built for NDA / legal / healthcare workflows.