We made Auto Ontology nice, and truly a graph.

For any machine with Docker: macOS, Linux or Windows. The gardend image is x86-64; on Apple Silicon, Docker Desktop runs it through emulation.

Auto Ontology started with Neo4j and ported to Postgres; we keep it inside something richer than Neo4j, and even richer than most RDF graphs.

The catalog was always a graph: databases contain schemas, schemas contain tables, tables contain columns, columns point at each other through foreign keys and joins, and a glossary term points at the columns that represent it and the SQL that computes it. What changed is where it is kept.

Where Auto Ontology began. Its catalog is a labeled property graph: nodes for databases, schemas, tables, columns, SQL statements and analyses; edges for contains, foreign key, join, union and has-sql.

Where NVIDIA moved it. The same graph became Postgres tables, and NVIDIA kept a golden file that captures every read of that graph, to check the port.

Where Nidra keeps it. The same graph, row for row, as RDF in gardend, the Sophia engine: a direct mapping of the 33 tables, where a row is a resource, a column is a property and a foreign key is a link. NVIDIA’s own golden captures pass identically against it: 1,068 reads. The glossary, the SQL attributes and the vector index are in the same graph; there is no Postgres.

gardend is an RDF graph store: Oxigraph inside, SPARQL 1.1, named graphs. It runs as one process per graph, local-first, and the graph lives in a folder you can copy. On top of the RDF it holds things most RDF stores do not:

Search over every entity by meaning and by words, in any language, with the model inside. No API.

Several people and agents can edit the same document at once (a CRDT).

A correction is recorded with who said it and when, and its lineage. A disagreement is two heads, not a lost update.

Claude or any agent reads and writes the same graph.

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.

The local edition is a download today. Hosted Nidra is coming soon. Join the waitlist.

The Nidra engine is open source under the Apache License 2.0; its source is on GitHub: sophia-labs/nidra.

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.

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.

Postgres, Snowflake, Databricks, DuckDB, MySQL, Trino, ClickHouse or SQLite. The ingestion service profiles every table and column and sweeps again every INGEST_INTERVAL_HOURS.

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.

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.

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.

Download the two files, load the gardend image, set a chat model and GARDEND_TOKEN in .env, and start the compose project. The download page has the checksums; Run it locally has every step.

builds the engine image on first run

docker compose -f compose.nidra.yaml up -d curl -s http://127.0.0.1:3001/api/health

Hosted Nidra

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.

Join the waitlist No cookies, no tracking. Only this address is kept.

Early access and questions: vera@sophia-labs.com