#cjk

An MCP server that gives your AI agent agentic RAG over your PDFs, one file or a whole folder: hybrid semantic + keyword search, selective page reads, tables, images, OCR, chart data, and multi-column/CJK layouts. The agent decides when to search; pdf-mcp does the retrieval.

Opinionated paranoid text spacing in JavaScript, with on-device AI semantic judgment

Python library that measures the width of strings in a terminal

Make CommonMark more friendly for Japanese/Chinese/Korean (CommonMark next specification draft)—plugins & patched packages

Canonicalize and neutralize adversarial Unicode — homoglyph/bidi/zalgo/invisibles — before it reaches your classifiers, indexes, and identifiers