ktx
Context layer so AI agents query your analytics databases accurately.
Auto Ontology es un proyecto de agentes de IA de código abierto de NVIDIA (NVIDIA/auto-ontology en GitHub). Tiene 12.131 estrellas en GitHub y 1.002 bifurcaciones, se publica bajo la licencia Apache-2.0 y se actualizó por última vez en GitHub el 12 de noviembre de 2026.
NVIDIA's context layer for agentic analytics — ontologies from enterprise metadata, served over MCP, CLI and API, Apache-2.0
Clone the repo, copy the example environment file, and fill in your NVIDIA API key and passwords.
Bring up the full stack with Docker Compose — frontend, backend, ingestion worker and Postgres.
Point it at your data source and let it ingest metadata into the ontology and catalog.
Query in natural language from the web UI, or serve the context to your agents over MCP, CLI or API.
Generates enterprise ontologies from metadata and connects existing semantic models into AI-ready knowledge graphs.
Gives agents trusted business meaning for metrics, entities and relationships — with provenance on every answer.
Checks generated SQL against certified definitions and lineage before it runs.
MCP server, CLI and API — any agent harness can consume the context layer.
Certified corrections and usage fold back into the ontology, so shared context improves with every question.
Clone the repo and copy the example environment file.
git clone https://github.com/NVIDIA/auto-ontology.git
cd auto-ontology
cp .env.example .envFill in DEFAULT_MODELS_API_KEY in .env with a key from build.nvidia.com, plus the passwords.
DEFAULT_MODELS_API_KEY=nvapi-...Bring the Docker Compose stack up and open the web UI.
docker compose upTwo more from the same shelf: ktx — Context layer so AI agents query your analytics, and Beam — Reflection's open 501B MoE model built for agentic. Browse every AI Agents tool in the catalogue to compare the category. Before running a model locally, check how much VRAM you need for local LLMs — model size has to match your hardware.
Agents answering business questions from data they do not understand — it builds a context layer (ontology) from enterprise metadata so answers are grounded and traceable.
Through MCP, CLI or API — the ontology is served to any agent harness.
Docker with Compose, uv, and an NVIDIA API key from build.nvidia.com.
Yes — Apache 2.0.
Not right now — the README states the project is currently not accepting external contributions.
Context layer so AI agents query your analytics databases accurately.
Beam — Reflection's open 501B MoE model built for agentic coding: 23B active parameters, a 1M-token context, Apache-2.0 weights, and Mirror, its open-source terminal harness
Mobile app automation and verification built for AI coding agents — CLI, MCP server, and Node API
The memory API that gives AI apps instant, lasting context.
Make your agents learn from experience with a dedicated context engine.
Production-ready agentic RAG behind a clean REST API.
Los demás proyectos de Agentes de IA con más estrellas del catálogo de LibreAI: la lista realista de alternativas si Auto Ontology no es lo que buscas.
A personal AI that really does things — on any OS, with your data staying yours.
Matt Pocock's engineering skills for coding agents — grill the spec first, then build it right, MIT
An agentic skills framework & software development methodology that works.
Agent harness optimization system with skills, memory and security for Claude Code, Codex and more
The agent that grows with you — a Python framework for adaptive AI agents.
Proyectos de Agentes de IA cercanos en el catálogo, los más próximos en estrellas a Auto Ontology: sigue explorando a ambos lados.
MCP server letting AI agents run 150+ cybersecurity tools for authorized pentesting and research.
Enterprise LLM app platform: GenAI workflows, RAG, agents, model management, evaluation, fine-tuning.
AI-powered reverse engineering assistant that bridges IDA Pro with language models through MCP.
Self-evolving memory OS for LLMs and agents: persistent graph memory, hybrid retrieval, skill reuse.
One portable, local-first memory layer for every AI agent - Markdown-native, user-owned and self-evolving.
Observability and evaluation for AI apps — see what your agents do.
Gratis y abierto: consigue el código fuente, dale una estrella al repositorio y empieza a crear.