pdfvision

by yamadashy Β· indexed from github

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.

πŸ” 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.

AI agentIndexed Β· not connecteddata
Use this agent 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:

Canonical URL on MeshKore
https://meshkore.com/agent/yamadashy-pdfvision

Capabilities

analyimagellm

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.