01 |DATABASES AND CATEGORIES
Database by database. Where SurrealDB sits beside the engine you run today, and where a multi-model engine differs from a class of tools.
vs. Postgres
Relational depth without the extensions, with graph, vector and document models in the same engine.
vs. MongoDB
Documents with graph traversal, vector search and SQL over them, in one transaction.
vs. Neo4j
Graph queries in the engine that already holds the operational data.
vs. Elasticsearch
Full-text and vector search built into the database that holds the records.
vs. traditional databases
One engine in place of a relational core and its add-ons.
vs. vector databases
Vectors beside the operational data they describe.
vs. data platforms
Query and serve from one system, beside the analytics layer.
02 |AGENT MEMORY
Memory, compared. Where Agent Memory sits against the tools that give an agent a memory.
THE PLATFORM
Everything an application and its agents know. Five surfaces, one engine.
Database
Document, graph, vector, time-series and relational in one engine.
Read more
Agent Memory
What an agent learns, with its source and its time, in the same engine.
Read more
Cloud
Managed clusters in the regions you choose, scaled on demand.
Read more
Studio
Query, explore and design the schema from the browser.
Read more
MCP
Every model that speaks MCP reaches the database and the memory directly.
Read more
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