C

Run GLM-5.2 (744B MoE) on a 25GB-RAM consumer machine — pure C, zero deps, experts streamed from disk. Tiny engine, immense model. 🐦

UNIX-like reverse engineering framework and command-line toolset

DeepSeek 4 Flash local inference engine for Metal and CUDA

The systemd System and Service Manager

🔥 A cross-platform build utility based on Lua

A lightweight MQTT broker for IoT and publish-subscribe messaging

An open-source antivirus engine for detecting malware and threats

The programming language for agents

Run the full 2.78-trillion-parameter Kimi K3 model, DeepSeek V4.1 Flash or GLM-5.3-Flash beyond available RAM by streaming activated weights directly from NVMe. A dependency-free, embeddable C inference engine.

Random version of microemacs with my private modificatons