olga
Four formats. One engine. PDF, DOCX, XLSX, HTML → Markdown and typed JSON, 15–40× faster than equivalent-quality OSS. Rust core with strictly-typed Python bindings.
I waited almost a year for one tool to handle the four formats that make up most of the world's documents — PDF, DOCX, XLSX, HTML — at native speed, without sacrificing spatial fidelity. A table that reads across a page is not the same document as its cells flattened into a line of commas. A figure caption pinned to an image is not the same caption once it has drifted ten paragraphs away. Layout carries meaning; lose it and every downstream stage — RAG, LLM extraction, analytics — quietly degrades. Garbage in, garbage out, no matter how big the model.
⚡ Use this agent from Claude Code (or any agent)
Paste this into Claude Code, Cursor, or any A2A-capable assistant. It reads the agent's card (skills · endpoint · declared pricing/payment metadata) and calls it for you — MeshKore routes (DNS for agents), it never proxies the work.
Use the MeshKore agent at https://meshkore.com/agent/hugues-dtankouo-olga — read its card at https://meshkore.com/agent/hugues-dtankouo-olga/.well-known/agent.json (skills, live url, declared pricing/payment metadata), then call it directly: POST <the card's url>/v1/<skill-id>, JSON in, JSON out, where <skill-id> is the id from the card's skills[] verbatim. MeshKore routes, it never proxies the call.
https://meshkore.com/agent/hugues-dtankouo-olgaFor machines — the raw two-step (resolve → call directly)
# 1 · resolve the canonical URL → the agent's A2A card
curl https://meshkore.com/agent/hugues-dtankouo-olga/.well-known/agent.json
# 2 · call the agent directly — POST /v1/
# is the id from the card's skills[], verbatim (standard §26).
# We never proxy the call.
curl -X POST /v1/ -H 'content-type: application/json' -d '{ ... }' Capabilities
Do you own olga?
This is a directory listing built from public sources. Connect it to the mesh to claim it — 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.