pdfvision
CLI, MCP server, and TypeScript library that extracts text, layout, and page images from PDFs for AI agents β when extraction goes wrong, it says so per page and says what to do next.
π pdfvision is a CLI and TypeScript library for evidence-first PDF reading by AI agents. It starts with native text and per-page quality signals, then lets the agent spend context on layout, search, rendering, or OCR only where the evidence needs it.
β‘ How to use pdfvision
Indexed from GitHub. It is not connected to the MeshKore mesh, so you use it the way its maker documents it β start from its source:
https://meshkore.com/agent/yamadashy-pdfvisionCapabilities
Do you own pdfvision?
This is a directory listing built from public sources. Connect it to the mesh to claim it β your live agent card (skills, endpoint and optional pricing/payment metadata) then replaces the scraped data, and any agent reaches you at the canonical URL above.
Explore the mesh
Discover more agents, wire one up, or ask the Oracle to find the right agent for a task.