AWS Textract

Tesseract OCR is software for performing offline optical character recognition on captured document regions. Its official documentation includes a user manual and source-code documentation.

OCR It is a Chrome and Firefox browser extension for extracting text from paginated document viewers, including scanned books, slide decks, PDFs, and embedded readers where text selection is unavailable. Users select a screen region, capture it with a hotkey, and append the locally generated OCR result to an ordered transcript; an automatic mode captures each page, advances the viewer, and stops when text repeats, paging fails, OCR fails, or a page limit is reached. OCR runs offline through a bundled Tesseract build without outbound requests, API calls, or image uploads. The extension crops, optionally enlarges, and converts the visible region to grayscale, queues OCR jobs serially, stores page text and verification thumbnails, flags consecutive duplicate pages, and exports the transcript as copied text or a TXT file with page separators. Page turning can use a picked screen point or keyboard event, including controls inside supported frames and shadow roots. It uses narrowly scoped browser permissions, relying on activeTab for single captures and requesting an additional site grant for automatic runs that persist across page loads or turn pages inside cross-origin iframes.

LiteParse is an open-source, standalone document parser from LlamaIndex focused on fast, local parsing of PDFs and other documents without proprietary LLM features or cloud dependencies. Its Rust-based pipeline converts Office files and images to PDF when needed, extracts native text with PDFium, optionally applies Tesseract or an HTTP OCR service, merges the results, and reconstructs spatial layout using text positions and bounding boxes. It can output Markdown, JSON, or layout-preserved plain text, generate page screenshots, detect documents that need OCR or heavier processing, and expose classified layout blocks such as headings, paragraphs, lists, tables, code, and figures; the JSON representation can include per-cell table coordinates and other opt-in PDF metadata. LiteParse is distributed through CLI, Rust, Python, Node.js/TypeScript, and browser WebAssembly packages, and is licensed under Apache 2.0.

TaxHacker is a self-hosted AI accounting application for freelancers, independent developers, and small businesses. It processes receipt photos, invoice PDFs, bank statements, and other documents with a configurable LLM, extracting dates, merchants, amounts, taxes, product names, and line items into a structured, Excel-like database. It can categorize transactions, split invoice items into separate transactions, and use custom fields with user-defined prompts; supported model backends include OpenAI, Google Gemini, Mistral, and local OpenAI-compatible endpoints such as Ollama, LM Studio, vLLM, and LocalAI. The application detects document currencies and converts transactions using historical exchange rates from the transaction date, including cryptocurrency support, and provides filtering, multi-project organization, import/export, and custom categories. The repository describes the project as being in early development and advises using it at one's own risk.