Enpass commandline client

MinIO Object Storage Documentation

Parakeet implementation in C++ with ggml

Open Source Global Intelligence Platform - Real-Time OSINT Dashboard - A Palantir Alternative

Inspect and clean a USB-connected device from your terminal: storage, apps, media, and a live log viewer. No jailbreak, no root.

DFlash & TurboQuant in llama.cpp with up to 3x faster generation and 7.5x more KV cache in same VRAM

A fast Node.js package manager

Build desktop + mobile apps with Zig and web UI

🕷️ An adaptive Web Scraping framework that handles everything from a single request to a full-scale crawl!

WAHA - WhatsApp HTTP API (REST API) that you can configure in a click! 3 engines: WEBJS (browser based), NOWEB (websocket nodejs), GOWS (websocket go)

Structured Chain-of-Thought

Run LLMs with MLX

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

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

llama.cpp fork with additional SOTA quants and improved performance

MLX: An array framework for Apple silicon

A modern proof language

Bend2 - WIP

DFlash: Block Diffusion for Flash Speculative Decoding

Exact speculative decoding on Apple Silicon, powered by MLX.

KV cache compression via block-diagonal rotation. Beats TurboQuant: better PPL (6.91 vs 7.07), 28% faster decode, 5.3x faster prefill, 44x fewer params. Drop-in llama.cpp integration.

Lightpanda: the headless browser designed for AI and automation

The fastest macOS package manager. Written in Zig. 3ms warm installs.

Painless E2E Automation for Mobile and Web

A powerful MCP toolkit for coding, providing semantic retrieval and editing capabilities - the IDE for your agent

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

Zig code intelligence server and MCP toolset for AI agents. Fast tree, outline, symbol, search, read, edit, deps, snapshot, and remote GitHub repo queries.

llama.cpp fork with TQ3_1S/4S CUDA kernels — 3.5-bit WHT quantization achieving Q4s quality at 10% smaller size. Based on RaBitQ-inspired Walsh-Hadamard transform. Enables 27B models on 16GB GPUs w…