GABRIEL (OpenAI, 2026)

github.com/openai/gabriel
Active415updated 1 month ago
Jupyter Notebook
Apache-2.0

Generalized Attribute Based Ratings Information Extraction Library; official OpenAI toolkit that turns messy qualitative corpora into analysis-ready datasets for social scientists and data scientists, measuring quantitative attributes in text, images, or audio using the GPT API. See the [official blog post](https://openai.com/index/scaling-social-science-research/) and [NBER working paper](http://www.nber.org/papers/w34834) (413+ stars, Apache 2.0)

Sourced from

  • GitHubgithub.com/openai/gabriel
  • Awesome AI for Sciencegithub.com/openai/gabriel

Related resources

Curated collection of 23,000+ agent skills for empirical research across 8 social science disciplines, enabling reproducible social science research with AI agents (Stanford REAP & CoPaper.AI, 1.1K+ stars, 2026)

Active3.4K1 week ago
Stata
NOASSERTION

Curated collection of 23,000+ agent skills for empirical research across 8 social science disciplines, enabling reproducible social science research with AI agents (Stanford REAP & CoPaper.AI, 3K+ stars, 2026)

Active3K1 month ago
Stata
NOASSERTION

Modern LLM-native agent simulation platform for social science research and experimental design, providing a flexible framework for creating and managing intelligent agents in simulated environments (Tsinghua FIB Lab, 984+ stars, 2025)

Active1.2K5 days ago
Python
Apache-2.0

Design, conduct and analyze results of AI-powered surveys and experiments. Simulate social science and market research with large numbers of AI agents and LLMs (460+ stars, 2024)

Active4843 weeks ago
Python
MIT