feed · watching · stats · help with your tokens
NVIDIA/auto-ontology
An open context layer that turns database metadata into an ontology, so AI agents answer questions about enterprise data with fewer wrong answers.
It gives agents one trusted definition per business concept, mapped across tables and databases, so analytics answers are grounded instead of improvised. Agents query through the ontology, and people review and certify it in a web UI; terms, reviewed SQL and joins are served over MCP and a REST API.
Similar
- JustVugg/colibri
colibri is a C inference engine that runs very large open mixture-of-experts models on the machine you already have.
- deepseek-ai/dsh-superagent-prototype
dsh-superagent is a research prototype for a proactive coding agent that works on a single GitHub repository using DeepSeek Harness.
- anthropics/FlashProve
FlashProve is a research prototype for zero-knowledge proofs of AI inference that allows providers to prove model identity without revealing weights.
- finic-ai/kairos
Kairos is an open-source, real-time fraud and risk decisioning platform for sign-ups, logins, orders, payments and payouts.
- zhanghao123vip/ai-manju-skills
A collection of 21 genre-specific templates for generating full AI comic drama production workflows, including scripts, prompts, and release assets.
- KKKKhazix/agent-autoloop
Agent Autoloop lets a command-line agent pick up work in the background and follow it through, asking for a decision only when something is uncertain.
- pgEdge/ai-dba-workbench
A PostgreSQL monitoring system that combines traditional and AI-based monitoring for instances v14+ including Supabase and Amazon RDS.
- aaitor/skill-video-studio
A local video-production workspace driven by a Claude Code skill that turns a product walkthrough into a polished demo video.
sources
Claims below include README evidence. A matching quote or worker agreement does not establish that a claim is correct. Category majority among 2 workers. Version 1.
An open context layer that turns database metadata into an ontology, so AI agents answer questions about enterprise data with fewer wrong answers.
An open context layer that helps agents give fewer wrong answers on enterprise data.
Quote matched the README or GitHub description at extraction. Same claim and quote from 1 worker(s). Interpretation not reviewed by a maintainer.
It gives agents one trusted definition per business concept, mapped across tables and databases, so analytics answers are grounded instead of improvised.
Give agents one definition per business concept, mapped across
Quote matched the README or GitHub description at extraction. Same claim and quote from 1 worker(s). Interpretation not reviewed by a maintainer.
Agents query through the ontology, and people review and certify it in a web UI; terms, reviewed SQL and joins are served over MCP and a REST API.
query through the ontology, and people review it in a web UI.
Quote matched the README or GitHub description at extraction. Same claim and quote from 1 worker(s). Interpretation not reviewed by a maintainer.
Generates an ontology from database metadata.
Generate an ontology from database metadata
Quote matched the README or GitHub description at extraction. Same claim and quote from 1 worker(s). Interpretation not reviewed by a maintainer.
Gives agents one definition per business concept, mapped across tables and databases.
Give agents one definition per business concept, mapped across
Quote matched the README or GitHub description at extraction. Same claim and quote from 1 worker(s). Interpretation not reviewed by a maintainer.
Lets people review, edit and certify definitions in the UI.
Review, edit, and certify definitions in the UI
Quote matched the README or GitHub description at extraction. Same claim and quote from 1 worker(s). Interpretation not reviewed by a maintainer.
Checks whether a question is answerable before querying.
Check whether a question is answerable before querying
Quote matched the README or GitHub description at extraction. Same claim and quote from 1 worker(s). Interpretation not reviewed by a maintainer.
Serves context to any agent harness through MCP.
Serve context to any agent harness through MCP
Quote matched the README or GitHub description at extraction. Same claim and quote from 1 worker(s). Interpretation not reviewed by a maintainer.
Connects to ten source database engines.
Auto-Ontology connects to ten engines:
Quote matched the README or GitHub description at extraction. Same claim and quote from 1 worker(s). Interpretation not reviewed by a maintainer.
Exposes read-only ontology tools to any MCP client.
The [MCP](https://modelcontextprotocol.io) server gives any MCP client read-only
Quote matched the README or GitHub description at extraction. Same claim and quote from 1 worker(s). Interpretation not reviewed by a maintainer.
Returns each answer with the SQL and the steps that produced it.
The answer comes back with its SQL and the steps that produced it,
Quote matched the README or GitHub description at extraction. Same claim and quote from 1 worker(s). Interpretation not reviewed by a maintainer.
Imports and exports semantic models as Apache Ossie YAML.
Auto-Ontology is compatible with [Apache Ossie](https://ossie.apache.org/)
Quote matched the README or GitHub description at extraction. Same claim and quote from 1 worker(s). Interpretation not reviewed by a maintainer.
Routes predictive questions to KumoRFM when it is configured.
Set `KUMO_RFM_API_KEY` and the agent routes predictive questions to KumoRFM.
Quote matched the README or GitHub description at extraction. Same claim and quote from 1 worker(s). Interpretation not reviewed by a maintainer.
People review and certify the ontology in a web UI
Agents query through the ontology, and people review it in a web UI
Quote matched the README or GitHub description at extraction. Same claim and quote from 1 worker(s). Interpretation not reviewed by a maintainer.
Checks whether a question is answerable before querying
Check whether a question is answerable before querying
Quote matched the README or GitHub description at extraction. Same claim and quote from 1 worker(s). Interpretation not reviewed by a maintainer.
Serves context to agent harnesses through MCP and agent skills
Serve context to any agent harness through MCP, agent skills, and
Quote matched the README or GitHub description at extraction. Same claim and quote from 1 worker(s). Interpretation not reviewed by a maintainer.
Imports existing semantic models and shows the result as a graph
import existing semantic models, and explore the result as a semantic graph
Quote matched the README or GitHub description at extraction. Same claim and quote from 1 worker(s). Interpretation not reviewed by a maintainer.
Evaluated on BIRD, BEAVER and other SQL benchmarks
For BIRD, BEAVER, FDABench-Lite, and Wide World Importers, each eval item pairs a question with gold SQL
Quote matched the README or GitHub description at extraction. Same claim and quote from 1 worker(s). Interpretation not reviewed by a maintainer.
Limitation: The backend and ingestion services must keep their ports on a private network.
Keep ports 3001 and 3002 on a private network.
Quote matched the README or GitHub description at extraction. Same claim and quote from 1 worker(s). Interpretation not reviewed by a maintainer.
Limitation: The ingestion endpoints (ingest, delete, reset, compile) have no authentication of their own.
endpoints (ingest, delete, reset, compile) have no authentication of
Quote matched the README or GitHub description at extraction. Same claim and quote from 1 worker(s). Interpretation not reviewed by a maintainer.
Limitation: External pull requests are not accepted.
The Auto-Ontology team maintains the code and doesn't accept external pull
Quote matched the README or GitHub description at extraction. Same claim and quote from 1 worker(s). Interpretation not reviewed by a maintainer.
Limitation: The quickstart needs Docker with Compose v2.
You need Docker with Compose v2,
Quote matched the README or GitHub description at extraction. Same claim and quote from 1 worker(s). Interpretation not reviewed by a maintainer.
Limitation: Predictive questions rely on KumoRFM, a hosted service that receives the connected tables.
KumoRFM is a hosted service: to answer, the agent uploads the connected tables
Quote matched the README or GitHub description at extraction. Same claim and quote from 1 worker(s). Interpretation not reviewed by a maintainer.
Limitation: The software automatically retrieves external materials under separate terms and licenses.
This software automatically retrieves, accesses or
Quote matched the README or GitHub description at extraction. Same claim and quote from 1 worker(s). Interpretation not reviewed by a maintainer.
ai-ml · data