← all repositories

Technion-Kishony-lab/data-to-paper

An automation framework using interacting LLM-driven agents to autonomously conduct complete end-to-end scientific research, from raw data to backward-traceable research papers.

801 stars Python AgentsDomain Apps
data-to-paper
Velocity · 7d
+0.7
★ / day
Trend
steady
star history

The framework orchestrates multiple AI agents through the full scientific research pipeline, including data exploration, literature search, hypothesis generation, data analysis, and manuscript writing. It creates backward-traceable scientific papers where any numeric value can be traced to the specific code lines that produced it. The system is designed to be field-agnostic and works from raw data alone, with human-verifiable outputs for scientific validity.

heatdrop uses Google Analytics to see which pages get read — nothing else. Your call. How we handle data.