GRAPH AND VECTOR

Graph and vector, one query

Read the docs Start free with SurrealDB

Graph. Relationships as native edges you traverse.

Vector. HNSW and DiskANN indexes on the same records.

One statement. Traverse, filter and rank by similarity in one query.

A graph database and a vector database in one.Native relationships, approximate-nearest-neighbour search and full-text ranking in one query language over one copy of the data.

Read the docs

Native graph model

Nodes, edges and properties as records, traversed with arrow syntax to any depth.

Explore

Recursive traversal

Walk chains and dependency trees with recursive graph queries, filtering edges as you go.

Explore

HNSW vector index

Approximate-nearest-neighbour search with Cosine, Euclidean, Manhattan and inner-product metrics, on HNSW or DiskANN indexes.

Explore

Hybrid search

Full-text BM25 and vector similarity in one query, fused with reciprocal rank fusion.

Explore

Scope first, rank second

A structured filter narrows the candidates before the vector search runs.

Explore

One copy of the data

Graph edges, vectors and documents share the same records.

Explore

CONNECTED DATA

Relationships and similarity, together

Edges are documents you traverse with arrow syntax; vectors are an index on the same table. One query walks the graph and ranks by meaning.

GRAPH RELATIONSHIPS

Edges are records you traverse

RELATE customer:alice->purchased->product:widget_pro
    SET quantity = 2, date = time::now(), source = 'web';

SELECT ->purchased[WHERE date > time::now() - 30d]->product.name
    FROM customer:alice;

VECTOR SEARCH

Similarity on the same records

DEFINE INDEX product_embedding ON product
    FIELDS embedding HNSW DIMENSION 1536 DIST COSINE;

SELECT id, name, vector::distance::knn() AS distance
    FROM product
    WHERE category = 'tools'
        AND embedding <|10,40|> $query_embedding
    ORDER BY distance;

Graph and vector as the same records

One query, both models

Traverse relationships and rank by similarity in one statement, with the merge done by the engine.

One copy, in step

The vectors are an index on the source records, so they are as current as the write that made them.

One pass

Filter, traverse and rank run in one engine, in one pass, in one transaction.

Keep exploring

THE PLATFORM

Everything an application and its agents know. Five surfaces, one engine.

Database

Document, graph, vector, time-series and relational in one engine.

Five data models as dotted tiles: documents, graph, vector, time-series and relational

Agent Memory

What an agent learns, with its source and its time, in the same engine.

A timeline of remembered facts, each with its source

Cloud

Managed clusters in the regions you choose, scaled on demand.

Clusters in three regions on a world map, each running or scaling

Studio

Query, explore and design the schema from the browser.

MCP

Every model that speaks MCP reaches the database and the memory directly.

Three models connected through MCP to the database and Agent Memory

IN PRODUCTION

Trusted at scale. Samsung, Nvidia, Verizon, Tencent, and Walmart run on SurrealDB.

14,000+

Developers building on SurrealDB Cloud

4M+

Developers building on SurrealDB worldwide

FROM THE TEAMS

SurrealDB gives us a foundation where we can unify semantic search, knowledge graphs, and AI-driven decision making without stitching together multiple systems. Collapsing responsibility into SurrealDB has become our default engineering posture.

Justin Foley

VP of Engineering, Later

GET STARTED

Query relationships and meaning together. Traverse the graph and rank by vector similarity in one SurrealQL query.

Read the docs Start free with SurrealDB

Graph and vector, one query

A graph database and a vector database in one.Native relationships, approximate-nearest-neighbour search and full-text ranking in one query language over one copy of the data.

Native graph model

Recursive traversal

HNSW vector index

Hybrid search

Scope first, rank second

One copy of the data

Relationships and similarity, together

Edges are records you traverse

Similarity on the same records

Graph and vector as the same records

One query, both models

One copy, in step

One pass

Keep exploring

RELATE documentation

Technical deep dive

All features

Everything an application and its agents know. Five surfaces, one engine.

Trusted at scale. Samsung, Nvidia, Verizon, Tencent, and Walmart run on SurrealDB.

Query relationships and meaning together. Traverse the graph and rank by vector similarity in one SurrealQL query.