Renders large text blobs as dense PNG image pages via pxpipe, enabling vision models to read content at ~3x token efficiency with a single inline image block.
Compresses file reads, command output, search hits, and fetched web pages before entering agent context to reduce token usage, using deterministic transforms and a safety verifier.
Enables vision LLMs to read PDFs by automatically detecting text corruption and switching between text extraction and image rendering modes, while preserving reading order and filtering unnecessary images to prevent token overflow.
Enables intelligent document processing by extracting text, classifying document types, and generating structured summaries from PDFs and images using vision LLMs.
Provides AI agents with comprehensive document parsing capabilities including PDF text extraction, OCR, HTML-to-markdown conversion, table extraction, and summarization, optimized for agent workflows.