Nidra
The semantic layer for your warehouse.
Connect a SQL warehouse and Nidra profiles its tables and columns, then compiles a semantic layer over them: a glossary of your business terms, what each column means, the joins that matter and named SQL for your metrics. Every customer gets an isolated knowledge graph that people and agents can read, correct and extend. Ask a question in plain language and you get the answer with the SQL behind it, and your Claude, Cursor or in-house agents can sign in to the same layer over MCP.
Hosted Nidra: Coming soon. The local edition is a download today. Hosted Nidra is coming soon.
Download the local edition · Join the waitlist
Download
The local edition
Nidra runs on your machine with Docker Compose. Two files: the engine source with its compose file, and the gardend image. Check them against their SHA-256 before you run them.
- nidra-local-20261103.tar.gz (11.6 MB): The engine source and compose.nidra.yaml: the semantic layer, the text-to-SQL agent, the ingestion service and the Chinook sample.
License: The Nidra engine, Apache License 2.0, built on NVIDIA Auto Ontology (Sophia Labs is not affiliated with NVIDIA).
SHA-256 61d92d241aef96f90e8dc446d58b5d773742de5a3d87f7339d0a3b03dced415b
- nidra-gardend-20261103.tar (71.7 MB): The gardend image (the Sophia engine with ONNX Runtime for its vector index), for docker load.
License: The Sophia engine (gardend) image, PolyForm Noncommercial 1.0.0; commercial use by arrangement with Sophia Labs. It includes ONNX Runtime (MIT).
SHA-256 b66d54d5b15cd68f92661381605ab1d00a1c819c1fe8bf03720c0f4d2609fc02
Both sums: SHA256SUMS-20261103.txt
Why a graph
Why the ontology lives in a graph
Auto Ontology keeps its catalog and its glossary as rows in Postgres. Nidra keeps the same records in gardend, the Sophia engine: the catalog, the glossary, the SQL attributes and the vector index are one RDF graph, and there is no Postgres.
It is the shape this data already has. Tables contain columns, columns join, a term points at the columns that represent it and at the SQL that computes it. In a graph those links are the data: you can follow them with SPARQL, and people and agents can read, correct and extend the same graph the agent answers from.
The agent
Ask in plain language, get the SQL
The agent is Auto Ontology’s text-to-SQL agent, kept as it is. It finds the terms and columns a question is about, writes SQL in your warehouse’s dialect, runs it, and repairs the query when it fails. You get the answer, the rows and the SQL behind them.
Its catalog reads go to the graph. Every one of them is graded against upstream’s own recorded answers for the same reads, so the agent sees the catalog it would have seen in Postgres.
What it does
What you get
A catalog of any SQL warehouse
Postgres, Snowflake, Databricks, DuckDB, MySQL, Trino, ClickHouse or SQLite. The ingestion service profiles every table and column and sweeps again every INGEST_INTERVAL_HOURS.
A glossary compiled from it
Business terms, what each column means, the joins that matter between tables, and SQL attributes: named SQL for your metrics, filed under the term they compute.
Answers with their SQL
POST /api/chat/completions streams the agent’s steps, then the answer, the rows and the SQL, so every number can be checked against your warehouse.
One graph for people and agents
The catalog and glossary are RDF in gardend: query them with SPARQL, or attach the engine to your own Sophia app and keep them in a graph of yours.
Run it locally
Run it on your machine today
Download the two files, load the gardend image, set a chat model in .env, and start the compose project. The download page has the checksums; Run it locally has every step.
docker compose -f compose.nidra.yaml build auto-ontology
docker compose -f compose.nidra.yaml up -d
curl -s http://127.0.0.1:3001/api/health
Hosted Nidra
Hosted Nidra is coming soon
A hosted semantic layer for your warehouse: a login, an isolated graph per customer, an MCP endpoint for your agents, backups and upgrades. Leave your email and we will tell you when it opens. We use this list for that and nothing else.
Early access and questions: vera@sophia-labs.com