AI Anthropology Toolkit
A suite of AI anthropology tools for qualitative research
Matt Artz | GitHub | ORCID
Overview
The AI Anthropology Toolkit provides computational tools for anthropological and qualitative research. Every component is grounded in the conventions, debates, and craft knowledge of anthropology and cognate qualitative social sciences. Epistemic stance (interpretivist, critical, STS, feminist, applied, etc.) is treated as a first-class design parameter that shapes methods, writing, and analysis.
The toolkit includes standalone notebooks for qualitative data analysis, a Claude Code plugin with research lifecycle skills and agents, and will expand to include MCP servers and additional components over time.
What is AI Anthropology?
AI Anthropology is an emerging field that combines:
- Studying AI as cultural artifact — Understanding how AI systems reflect and shape human culture
- Using AI to enhance ethnographic research — Leveraging computational methods to scale qualitative analysis
- Applying anthropological insights to AI development — Bringing cultural understanding to technology design
This toolkit focuses on the second aspect: using AI to enhance traditional anthropological research methods while preserving the interpretive frameworks that make the discipline unique.
Notebooks
Standalone notebooks for computational qualitative analysis. Most can be run directly in Google Colab. Notebooks marked Local should be run on your own machine (see Running Locally below).
| Notebook | Run | Description |
|---|
| Academic Literature Explorer |  | Search 250M+ scholarly works across all disciplines via OpenAlex with citation counts and open access detection |
| Qualitative Codebook Builder | | Build qualitative codebooks from source literature with AI-assisted code generation, validation, and structured export |
| Interview Transcript Semantic Chunker | | Segment interview transcripts into semantically coherent chunks with speaker-aware processing and coherence scoring |
| Coding and Thematic Analysis | | Apply codes to qualitative data and build themes using deductive, inductive, or hybrid approaches |
| Text Network Analysis | | Build co-occurrence networks from text with community detection, centrality metrics, and interactive visualization |
| Topic Modeling (BERTopic) | | Discover topics in text collections using transformer-based clustering with interactive visualizations and zero-shot mode |
| Named Entity Recognition (GLiNER2) | | Extract people, places, organizations, concepts, and custom entity types from text using zero-shot NER |
MattArtzAnthro