
This automates hypothesis generation and testing for empirical research by having LLMs generate 10-20+ testable hypotheses from your datasets in minutes. It supports three approaches: pure data-driven generation, literature-plus-data integration (with PDF processing), and combined methods. The framework showed 8.97% improvement over few-shot baselines in testing and 80-84% hypothesis diversity. You'd use this for research domains like deception detection, AI content identification, or mental health analysis where you need systematic hypothesis exploration. Redis caching cuts API costs during iterative refinement, and it works with both API-based models and local LLMs. The configuration requires careful prompt template setup, but the examples in the HypoGeniC datasets repo give you working templates to adapt.
$ npx -y skills add davila7/claude-code-templates --skill hypogenic --agent claude-codeInstalls into .claude/skills of the current project.
Hypogenic provides automated hypothesis generation and testing using large language models to accelerate scientific discovery. The framework supports three approaches: HypoGeniC (data-driven hypothesis generation), HypoRefine (synergistic literature and data integration), and Union methods (mechanistic combination of literature and data-driven hypotheses).
Get started with Hypogenic in minutes:
# Install the package
uv pip install hypogenic
# Clone example datasets
git clone https://github.com/ChicagoHAI/HypoGeniC-datasets.git ./data
# Run basic hypothesis generation
hypogenic_generation --config ./data/your_task/config.yaml --method hypogenic --num_hypotheses 20
# Run inference on generated hypotheses
hypogenic_inference --config ./data/your_task/config.yaml --hypotheses output/hypotheses.json
Or use Python API:
from hypogenic import BaseTask
# Create task with your configuration
task = BaseTask(config_path="./data/your_task/config.yaml")
# Generate hypotheses
task.generate_hypotheses(method="hypogenic", num_hypotheses=20)
Sponsors