velocitybolt/open-extract

Structured Data Extractor for AI Agents. Search your documents or the web for specific data and get it back in JSON or Markdown in a single tool call.

47
/ 100
Emerging

Supports multi-document and multi-schema extraction across diverse file types without requiring vector databases or page specifications, with built-in caching for rapid reprocessing. Model-agnostic architecture that works with any LLM provider, integrating directly into agentic frameworks like LangGraph, AG2, and CrewAI. Accepts user-defined schemas as key-value pairs describing extraction targets, returning results in JSON or Markdown formats suitable for downstream agent workflows.

185 stars.

No Package No Dependents
Maintenance 6 / 25
Adoption 10 / 25
Maturity 16 / 25
Community 15 / 25

How are scores calculated?

Stars

185

Forks

21

Language

Python

License

MIT

Last pushed

Jan 05, 2026

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/rag/velocitybolt/open-extract"

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