#99th of 21 in RAG and searchFor data and documents, data analysis

auto-ontology

Ontology layer that grounds text-to-SQL agents in certified business definitions

Stars
13.7k
License
Apache-2.0
Last commit
Nov 2026
Language
Python
Stars, last 28 weeks+12,907
2 May 2026: 764 stars9 May 2026: 764 stars16 May 2026: 764 stars23 May 2026: 765 stars30 May 2026: 765 stars6 Jun 2026: 765 stars13 Jun 2026: 765 stars20 Jun 2026: 765 stars27 Jun 2026: 766 stars4 Jul 2026: 767 stars11 Jul 2026: 767 stars18 Jul 2026: 767 stars25 Jul 2026: 767 stars1 Aug 2026: 768 stars8 Aug 2026: 769 stars15 Aug 2026: 769 stars22 Aug 2026: 769 stars29 Aug 2026: 770 stars5 Sept 2026: 770 stars12 Sept 2026: 771 stars19 Sept 2026: 771 stars26 Sept 2026: 771 stars3 Oct 2026: 772 stars10 Oct 2026: 785 stars17 Oct 2026: 795 stars24 Oct 2026: 869 stars31 Oct 2026: 1,442 stars7 Nov 2026: 10,622 stars14 Nov 2026: 13,671 stars

764 on 2 May 202613,671 on 14 Nov 2026

From GitHub's daily star counts.

Checked on GitHub.

Overview

Generates an ontology of terms, SQL attributes and relationships from database metadata, stores it in Postgres with pgvector, and uses it to answer natural-language questions with SQL and provenance. It ships a Next.js web UI, FastAPI backend and ingestion services, plus an MCP server, REST API and agent skills. Inference defaults to NVIDIA NIM endpoints; self-hosted or OpenAI-compatible endpoints can be set per model role.

Who it is for: Teams building text-to-SQL agents over enterprise databases

Strengths

  • Connects to ten engines including Postgres, Snowflake, Databricks, ClickHouse, DuckDB and SQLite
  • Each answer returns its SQL and steps; check_answerable flags questions the data cannot cover
  • Read-only MCP server and streaming REST API work with Cursor and Claude Desktop
  • Imports and exports semantic models as Apache Ossie YAML

Weaknesses

  • Ingestion service has no authentication; ports 3001 and 3002 must stay private
  • Defaults need an NVIDIA API key unless each model role points elsewhere
  • Project is not accepting external contributions
  • Quickstart needs a second repo (auto-ontology-eval) and uv to seed the sample database

What it needs

  • Python, NVIDIA NIM (Nemotron), OpenAI-compatible endpoints, self-hosted NIM
  • Needs PostgreSQL 17 with pgvector, NVIDIA NIM endpoint or OpenAI-compatible LLM, Docker Compose or Kubernetes (Helm), HashiCorp Vault (optional)
  • Docker
  • env example file

Also in RAG and search

See all 21
Also in RAG and search
RankProjectScore
1xerjElasticsearch-compatible search server that auto-indexes folders for coding agents Live demo ↗ (opens in a new tab)19.2k stars+11,240 (+141%) in 30 daysApache-2.087 out of 100
2sonicLightweight schema-less search index that returns object IDs, written in Rust Live demo ↗ (opens in a new tab)21.4k starsMPL-2.082 out of 100
3xbergRust document extraction engine with OCR, tables and 15 language bindings Live demo ↗ (opens in a new tab)9.6k starsMIT80 out of 100
#4qmdLocal hybrid search over markdown notes and docs, with CLI and MCP server31.2k starsMIT78 out of 100
#5llm-appYAML-configured RAG server that keeps a vector database synced with a document folder58.7k starsMIT77 out of 100