Build smarter knowledge graphs for data-rich applications
SurrealDB is a Rust multi-model database and context layer for AI agents: documents, graphs, vectors, time-series, and relations are native in one ACID engine, no stitched stores. Query with SurrealQL, connect via MCP, WebSocket, and SDKs, with GraphQL generated from your schema. Built-in auth, permissions, HTTP APIs, and live queries reduce separate backend glue. Runs embedded, at the edge, or as a highly-scalable cluster in the cloud. Same engine, everywhere.
SurrealDB supports native graph traversal, vector similarity search, and full-text indexing. Hybrid RAG combines vector cosine similarity with BM25 full-text scoring in a single weighted query, and graph-based re-ranking allows semantic results to be contextualized by relationship importance.
SurrealDB includes built-in authentication, row-level security, and record-level access methods defined in SurrealQL. Enterprise plans offer audit logging, FIPS-compliant cryptography, SSO, and compliance certifications (SOC 2 Type 2, ISO 27001, GDPR, CCPA, Cyber Essentials Plus).
SurrealDB provides live queries that push changes matching predicates to connected clients in real-time, enabling reactive state management without polling. Supports multi-node distributed live queries for scalable real-time applications.
SurrealDB unifies document storage, graph relationships, vector embeddings, time-series data, full-text search, and relational queries in one multi-model engine with one query language (SurrealQL), eliminating the need to manage separate systems and their integration glue code.
SurrealDB serves as the context layer for AI agents, combining documents, graphs, vectors, and time-series in one ACID transaction. Agents can retrieve complete context in a single query without stitching multiple databases together, enabling reliable reasoning over consistent data.