An official OpenAI toolkit for social scientists and data scientists to measure quantitative attributes in text, images, or audio using the GPT API.
GABRIEL is an OpenAI toolkit that turns qualitative text, image, and audio collections into datasets containing measured attributes. Social scientists and data scientists use it to run large-scale GPT-based rating and extraction tasks with batching, retries, checkpoints, and audit trails. The catalogue contains an instruction for using the toolkit with coding agents.
Latest release v1.1.9 · 13 Jul 2026
These files are openai/GABRIEL's own configuration. They tell Codex and OpenCode how to work on this repository, so they are not mods to install elsewhere. Copy one as a starting point and replace the parts that are about this project.
AGENTS.md A 3,731 tok