NobodyWho is an inference engine that lets you run LLMs locally and efficiently on any device.

Local PC app for everyone to use LLM locally 🫡

A persistent AI character that reads world news, builds memories with retrieval, and evolves an emotional state over time.

A cross-platform minimal(-ish) dependency SLM controlling program.

Examples of .apr format models

SLM-as-Cerebellum for LLM Policy Enforcement - biologically-inspired GO/NO-GO gating

🖥️ Explore CPU-SLM, a Rust-based SLM/LLM project that runs on CPU, offering efficient inference and chat with minimal dependencies.

A holiday project to better understand the inner workings of SLM/LLM.

Neurometric Runtime prototype — Manifest-driven Rust cluster manager with real SLM inference via HuggingFace Candle. Built as an Upwork proposal demo.

The Rust-native inference engine for Small Language Models (SLMs), Run efficient models locally with blazing fast speeds, instant startup times, and full Metal acceleration on Apple Silicon.