dylanhogg/llmgraph

Create knowledge graphs with LLMs

60
/ 100
Established

Extracts related entities and relationships from Wikipedia pages using LLM prompts, supporting 15+ entity types (movies, books, concepts, people, etc.) with customizable prompts. Outputs graphs in multiple formats—GraphML, GEXF, and interactive HTML via pyvis—while tracking token usage for cost estimation. Integrates with any LiteLLM-supported provider (OpenAI, Ollama, etc.) and includes caching for iterative graph expansion.

503 stars and 617 monthly downloads. Available on PyPI.

Maintenance 6 / 25
Adoption 16 / 25
Maturity 25 / 25
Community 13 / 25

How are scores calculated?

Stars

503

Forks

31

Language

Jupyter Notebook

License

MIT

Last pushed

Oct 11, 2025

Monthly downloads

617

Commits (30d)

0

Dependencies

15

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/llm-tools/dylanhogg/llmgraph"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.