Liteparse

LiteParse is a local document parser that pulls text and layout data from PDFs, Office files, and images without sending anything to the cloud. It's built by the LlamaIndex team and runs through a CLI or Node API. The default OCR is Tesseract.js, which means zero setup but moderate accuracy. You can plug in a custom HTTP OCR server if you need better results. It handles batch processing, page ranges, bounding boxes, and can generate screenshots for visual layout tasks. If you're building agents that need to read documents or doing any kind of local ETL on unstructured files, this covers the basics without adding API costs or privacy concerns.

skills.sh installs: 4.2K
GitHub stars: 84
last updated: Aug 21, 2026

View on GitHub

Install

$ npx -y skills add run-llama/llamaparse-agent-skills --skill liteparse --agent claude-code

Installs into .claude/skills of the current project.

Files

Effective LiteParse

Extract text from documents locally with the lit CLI — a fast, model-free parser. This skill is about using it cheaply: each lit parse re-runs full extraction, and every line you dump into the conversation is paid for on every subsequent turn. The patterns below come from analyzing real agent traces where the same PDF was parsed up to 9 times and single image reads cost 140k+ characters of context. Don't repeat those mistakes.

The golden rule: parse ONCE to a file, then search the file

lit parse re-extracts the whole document every time you call it. Re-parsing per search is the #1 waste seen in traces. Parse a document exactly once, to a temp file, then run all your searches against that file:

# ONE TIME, per document. --no-ocr for born-digital PDFs (almost all reports) — much faster.
lit parse "/abs/path/doc.pdf" --format text --no-ocr -o /tmp/doc.txt && wc -l /tmp/doc.txt

Then search the file with cheap shell tools — never re-run lit parse to search again.