CogDoc
CogDoc — 面向个人与团队的本地优先 AI 知识与研究工作台：多源 RAG、Deep Research、可验证引用、审核闭环、细粒度 ACL 与 Rust 加速混合检索。 CogDoc — A local-first AI knowledge and research workspace for individuals and teams, with multi-source RAG, Deep Research, verified citations, review workflows, fine-grained ACLs, and Rust-accelerated hybrid retrieval.
A local RAG knowledge-base console for individuals and teams, built on LangGraph multi-agent orchestration with a deterministic Rust core (PyO3 + maturin) underneath. It answers questions, summarizes a single document, compares multiple documents, and turns feedback into reviewable derived knowledge over your own PDF knowledge base — and every generated claim is pinned back to a [source:Pn] citation that is checked, not trusted. Use it from a CLI console, a Streamlit web app backed by FastAPI, or a standalone Debug console for trace inspection.
⚡ 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/jikongabc-cogdoc — read its card at https://meshkore.com/agent/jikongabc-cogdoc/.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/jikongabc-cogdocFor machines — the raw two-step (resolve → call directly)
# 1 · resolve the canonical URL → the agent's A2A card
curl https://meshkore.com/agent/jikongabc-cogdoc/.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 CogDoc?
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.