RUC open-sources EvoOntology, a self-evolving ontology layer for data agents via MCP
JeremyCMorgan · x · 2026-09-25
Renmin University's datalab released EvoOntology, billed as the first self-evolving ontology layer for data agents, bridging the agent-data gap over heterogeneous tables, files, and databases. Key points:
- MCP plugin: exposes a versioned ontology layer via MCP tools, plugging into Claude Code, Codex, and other agents
- Automatic construction: builds a tailored ontology layer directly from your data
- Continuous self-evolution: refines the ontology from agent execution traces, addressing how semantic layers go stale within weeks
Accompanied by a paper; 400 stars on GitHub with EN/CN docs.
More from coding & agent
- Runway MCP Lets Any AI Agent Generate Video Directly — tlakomy · 2026-09-25
- Hexis: open-source Postgres-native cognitive architecture giving LLMs memory and identity — GeretsOliver · 2026-09-25
- AgentArk, distilling multi-agent debate into a single LLM, accepted to NeurIPS 2026 — jindong_wang92 · 2026-09-25
- video-shotcraft author: Opus 5.5 makes a full code-generated video with music in one prompt — caolonghua · 2026-09-25
- Stability Matrix hang on Linux traced to 143 Windows fonts breaking Fontconfig — Signal_Care6558 · 2026-09-25
- Dev builds AI agent that calls 5 massage spas in parallel to compare prices and book slots — MarchCold7216 · 2026-09-25