StackMap
Subscribe

auto-ontology vs EvoOntology

NVIDIA's ontology framework for agentic analytics: generate ontologies from metadata, ground agents in governed business meaning, validate generated SQL, and serve context via MCP, CLI and API. — versus — Renmin University's self-evolving ontology layer for data agents: builds a workload-grounded ontology over tables, files and databases, serves it via MCP, and evolves it from agent trajectories.

The curated verdict

Both build ontologies over tabular data that improve with workload; EvoOntology is research-grade, Auto Ontology ships MCP/CLI/API serving.

auto-ontologyEvoOntology
Stars14k1.3k
Forks1.2k107
LanguagePythonPython
LicenseApache-2.0MIT
Last activitytoday13 days ago
Topicsknowledge-graphs, datadata, knowledge-graphs
Curated connections46

auto-ontology — the curator's take

Reach for it when agents answer business questions across many sources with conflicting definitions — the ontology pins metric meaning, validates queries and returns the SQL with every answer, and certified corrections flow back in. Its own README says it: one clean source and a fixed question set don't need this; direct SQL or a semantic layer is enough.

EvoOntology — the curator's take

The research answer to stale semantic layers: instead of hand-maintained definitions, EvoOntology builds an ontology from your data and real workload, lets agents fetch only the semantics a step needs through MCP, and proposes targeted updates from execution trajectories, publishing a new version only when paired evaluation beats its parent. Claude Code and Codex plugins make it easy to try. It is two-week-old research code from a university lab: treat the evolution loop as an experiment, keep versions reviewable, and give it read-only credentials. If you want definitions humans own and govern, a curated semantic layer (ktx, neocarta) is the conservative choice.