Every Eval Ever is a shared schema and crowdsourced eval database. It defines a standardized metadata format for storing AI evaluation results — from leaderboard scrapes and research papers to loca…

Un-0: an image generator powered by a simulated system of coupled oscillators, an example of an emerging physical computing substrate.

a minimalist agent that teaches you to create coding agents

WebAssembly binding for llama.cpp - Enabling on-browser LLM inference

Local-first healthcare AI: clinical NER & HIPAA PII de-identification that runs 100% on-device. 1,000+ medical models, 12 languages, Apple MLX + Python, no cloud, no patient data leaving your netwo…

Model export recipes, Python primitives, and Swift runtime utilities for on-device AI

How much experts do we need to serve a model?

llama.cpp's official website

An interface library for RL post training with environments.

Build and install script for llama.app

GEMMs with metal

One hub for all LLMs. Lives on your macOS menu bar.

Secure the tools you `brew install`

Pi coding agent extension: llama.cpp provider with dynamic model + context window discovery

Generate, format and mask agent traces with ease.

AssetOpsBench - Industry 4.0: A unified benchmark and framework for building, orchestrating, and evaluating domain-specific AI agents for Industry 4.0 asset operations and maintenance, with 460+ sc…

LLM inference in C/C++

Python bindings for llama.cpp

A utility script to upload pytorch traces to a Hugging Face Bucket, and then build sharable trace URL

Objective-C port of the tokenizer in HuggingFace's swift-transformers

How Fast can you pull from Hugging Face?

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

A course on context engineering with code agents.

Opinionated Configuration Files

Backup and restore OpenClaw agent workspaces to HF Buckets

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