Show HN: ParseHawk – 100% Local Document AI with API, CLI, and Web UI

Category: devtools

Tags: document-ai, pdf-extraction, local-llm

Score: 6.3/10 (Innovation: 5, Technical: 7, Documentation: 7, Utility: 6)

ParseHawk is a local-first document AI tool that extracts structured JSON from PDFs, scans, and images using LLMs like NuExtract3, with a REST API, CLI, and web UI. Its interesting for developers needing private, on-premises document parsing without sending sensitive data to third-party services.

Target audience: backend devs

Repository: https://github.com/parsehawk/parsehawk · Python · Apache-2.0 · 8 stars

View on Hacker News