Stars
A syntax highter for diffs, clarifying which parts of lines have changed
🪨 why use many token when few token do trick — Claude Code skill that cuts 65% of tokens by talking like caveman
Your own personal AI assistant. Any OS. Any Platform. The lobster way. 🦞
High-performance AI coding agent CLI written in Rust with zero unsafe code
A community database for the problems on the erdosproblems.com site
MacOS Niri and Hyprland inspired tiling window manager that's developer signed and notorized (safe for managed enterprise environments). Aiming for parity and extra innovation.
vLLM Metal plugin powered by mlx-swift — high-performance LLM inference on Apple Silicon
LLM inference server with continuous batching & SSD caching for Apple Silicon — managed from the macOS menu bar
Exact speculative decoding on Apple Silicon, powered by MLX.
Browser Harness | Self-healing harness that enables LLMs to complete any task.
Tree-based speculative decoding for Apple Silicon (MLX). ~10-15% faster than DFlash on code, ~1.5x over autoregressive. First MLX port with custom Metal kernels for hybrid model support.
Lossless DFlash speculative decoding for MLX on Apple Silicon
Vim plugin for LLM-assisted code/text completion
DFlash: Block Diffusion for Flash Speculative Decoding
vMLX - JANGTQ Uber Compressed MLX Models - L2 Disk Cache (survives restart) + L1 Paged (super fast ttft) + Hybrid SSM Scheduler + Cont Batching + etc!
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.
MLX-VLM is a package for inference and fine-tuning of Vision Language Models (VLMs) on your Mac using MLX.
Improve viewing Markdown in Neovim
The fastest and the most accurate file search toolkit for AI agents, Neovim, Rust, C, and NodeJS
NextPlaid, ColGREP: Multi-vector search, from database to coding agents.
Open source preservation effort and rewrite of the iconic Civilization Game designed by Sid Meier and Bruce Shelley in year 1991
You know how you always have to write a wrapper around fetch to have sensible defaults, for every new project? This is that wrapper.
Detect npm supply chain attacks by comparing published packages against GitHub source. Built after the axios compromise (Mar 2026).
A curious book about OCaml: logic (types), algebra (values), computation (semantics), functions (lambda calculus), constraints, monads, algebraic effects, expression.
Tiny filesystem honeypot for macOS. Mounts fake secret files (.env, id_rsa, credentials.json) via WebDAV (no root) or NFS (root) — any access triggers an alert. Zero dependencies, pure Go stdlib.