C++

Zero-cost abstractions for performance-critical systems — databases, game engines, and ML inference.

Projects built with C++

AI Engineering

llama.cpp

LLM inference in plain C/C++ — run capable models on everyday hardware.

llama.cpp made large language models runnable on a laptop CPU with no GPU, no framework, no cluster. The quantization formats it pioneered (GGUF) became the de facto standard for local inference.

Mar 10, 2023C++C

Developer Tools

DuckDB

An in-process SQL OLAP database — SQLite for analytics.

DuckDB brings columnar analytical queries into the process: no server, no setup, just fast SQL over Parquet and CSV files. It made the 'small data' analytics stack boring in the best way.

Jun 11, 2019C++