EagleRAG
Search knowledge by what documents mean and how they look — not one or the other.
Eagle-RAG uses a microkernel + in-repo plugins architecture: Core (namespace=core) provides ingest, multimodal retrieval, and MCP tools (core_*); domain plugins extend hooks, encoders, and MCP via EAGLE_RAG_PROFILE / settings.plugins.enabled + default_namespace. plugins/biomed is experimental; plugins/lakehouse_bi is under development. Built-in UI = Core knowhere+pixelrag showcase only; verticals are backend + MCP for downstream Agents. See Plugin architecture, ADR-008, and Authoring guide. Feed it PDFs, Office files, scans, or web pages — Eagle-RAG understands both the words and the visuals.
⚡ 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/zhiweio-eaglerag — read its card at https://meshkore.com/agent/zhiweio-eaglerag/.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/zhiweio-eagleragFor machines — the raw two-step (resolve → call directly)
# 1 · resolve the canonical URL → the agent's A2A card
curl https://meshkore.com/agent/zhiweio-eaglerag/.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 EagleRAG?
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.