HN Showcase
Back to browse
GitHub Repository

A fast, helpful, and open-source document parser

9,862 starsRust

LiteParse, a fast open-source document parser for AI agents

by freezed8·Mar 20, 2026·12 points·0 comments
Visit ProjectView on HN

AI Analysis

●●●BangerSolve My ProblemSlickCrowd Pleaser

Beats PyPDF and MarkItDown on accuracy without needing GPUs or cloud APIs.

Strengths
  • •Spatial text parsing with bounding boxes enables better document understanding for agents
  • •Zero GPU requirement means it runs on any machine, processing hundreds of pages in seconds
  • •One-line install as skill for 40+ AI agents including Claude Code and Cursor
Weaknesses
  • •Complex documents still need their cloud LlamaParse for dense tables and charts
  • •From run-llama means it's partly a funnel to their paid cloud product
Category
AI/ML
Target Audience

AI agent developers, RAG pipeline builders, document processing engineers

Similar To

LlamaParse · PyMuPDF · MarkItDown

Post Description

LiteParse is an open-source (Apache 2.0) document parser that provides high-quality spatial text parsing with bounding boxes. It does not depend on local or frontier VLMs.

Because it does not require GPUs, liteparse can be run on any machine, and process a few hundred pages of documents in seconds. It offers higher accuracy than similar tools like PyPDF, PyMuPDF, MarkItDown.

It supports a variety of file formats - PDFs, Office documents, images. It can be one-line installed as a skill for 40+ different AI agents, including Claude Code, Cursor, OpenClaw, Windsurf, and more.

Similar Projects