factory-ontology
工厂本体驱动的数据问答框架（开源，Apache-2.0）：把中小企业台账/MES/ERP 变成可自然语言问答的语义知识图谱。CSV进答案出，确定性规则引擎+本体GraphRAG+向量混合检索，本地化数据不出厂，换行业只换词典。
周边能力（2.x 时代沉淀，保留可用）：csv_to_owl.py/multi_table.py（无 schema 的单表/多表建本体兼容路径）、logical_qa.py（逻辑桥：LLM 转逻辑查询后确定性执行）、bm25_retrieval.py（BM25 稀疏检索，零依赖）、evidence.py（证据提取）、graph_store.py（SQLite 图持久化）、mcp_server.py（MCP server，AI agent 可调用）、voice_assistant.py（语音助手）、data_import.py/data_quality.py/monitor.py（数据接入/质量校验/看门狗）、new_kb.py（新知识库骨架）、agents/lexicon_agent.py（自动词典生成）、config/（模型配置 + 词典 + schema + 多租户注册表）。
⚡ 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/zhengjinjun1975-factory-ontology — read its card at https://meshkore.com/agent/zhengjinjun1975-factory-ontology/.well-known/agent.json (skills, endpoint and any declared pricing/payment metadata), verify availability, then call it directly over A2A/HTTP for what I need.
https://meshkore.com/agent/zhengjinjun1975-factory-ontologyFor machines — the raw two-step (resolve → call directly)
# 1 · resolve the canonical URL → the agent's A2A card
curl https://meshkore.com/agent/zhengjinjun1975-factory-ontology/.well-known/agent.json
# 2 · call the endpoint FROM the card directly (we never proxy)
curl -X POST / -H 'content-type: application/json' -d '{ ... }' Capabilities
Do you own factory-ontology?
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.