Theme
AI Resources
liteparse
liteparse is a local document parser from LlamaIndex for PDFs, DOCX, XLSX, PPTX, and images, with Markdown, JSON, and text output plus richer layout data for PDF workflows.
Its current runtimes span Rust, Node, Python, and browser WASM, with document-complexity detection, OCR choices, bounding boxes, and page screenshots for harder PDFs. Use this as a first read, not a recommendation. Open the original project before trusting details like terms, limits, privacy, cost, setup, or safety.
What it is
A local multi-format document parser
liteparse handles PDFs, common Office formats, and images locally, returning Markdown, JSON, or text that can feed retrieval, agents, and other downstream workflows.
Why it stands out
Local parsing with agent-friendly extras
It combines local operation with complexity detection, richer PDF structure, bounding boxes, OCR choices, and page screenshots, while exposing Rust, Node, Python, and browser WASM paths.
Availability
Repository and docs
The tool is publicly available on GitHub with linked documentation and examples for readers who want to inspect supported formats, OCR options, and parsing output behavior.
Why it matters
What makes it useful
Local parsing can decide whether retrieval or agent context is usable before a model answers. liteparse gives readers one extraction layer to compare across everyday documents, with lighter paths for straightforward files and richer PDF structure, OCR, and screenshots when needed.
What to know
Where it fits
This project fits in the ecosystem layer rather than the benchmark or assistant layer. It is more relevant to readers comparing parsing tools, OCR choices, and document-ingestion workflows than to readers looking for a finished end-user AI app.
Notable points
What stands out
The current project extends beyond PDF-only extraction: it adds Office files and images, several output formats and runtimes, and complexity detection that helps readers judge when a lightweight local path is enough.
Before using
What to review
Which format, output, runtime, OCR path, and parsing mode match the intended documents.
How the parser handles tables, images, scanned PDFs, and structured layout cues in practice.
Office-family conversion requires LibreOffice, while the browser WASM and language bindings have their own setup and format boundaries.
Whether the chosen OCR and downstream workflow stay local or send document text, images, or screenshots to another service.
Reader fit
Who may find it relevant
Readers building agent, retrieval, or ingestion workflows across PDFs, Office files, and images.
Builders who want a lighter local parser with several runtimes, layout data, OCR, and screenshot support.
Less relevant for readers focused only on chat interfaces or model releases.
Editorial note
Why LifeHubber lists it
LifeHubber lists liteparse because it combines local document extraction with multiple formats, runtimes, bounding boxes, OCR choices, and page screenshots in a small tool. Readers can compare whether that local control is enough for their real documents before choosing a heavier hosted parser.
Source links
Source materials
Reader note
Before relying on this entry
LifeHubber lists entries to help readers inspect AI projects, not to endorse them or prove they are safe, suitable, accurate, maintained, or right for a specific use. We do not verify every entry in depth. Before relying on anything listed, review the original materials, terms, privacy practices, limits, and risks that matter for your situation.
More in Ecosystem
Keep browsing this category
Explore more AI ecosystem resources.
LEANN
StarTrail-org/LEANN
A local vector index for semantic search and personal RAG that reduces stored embeddings through selective recomputation, with Python, CLI, and MCP routes.
FreeToken
FlashML-org/FreeToken
A local serving engine for running large mixture-of-experts language models across NVIDIA GPU memory, system memory, and CPU compute, with a local API, terminal interface, and coding-agent launch paths.
OpenAI Privacy Filter
openai/privacy-filter
A privacy-filtering model and local toolkit for detecting and masking personally identifiable information in text, positioned around high-throughput sanitization workflows.
For project maintainers
Listed here? You can use the badge.
If you maintain a project with a current LifeHubber listing, you may add the optional “Listed on LifeHubber AI Resources” badge to its README, docs, or website. No introduction or permission request is needed.
