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
vs. MongoDB
vs. Neo4j
vs. Elasticsearch
vs. traditional databases
vs. vector databases
vs. data platforms
02 |AGENT MEMORY
Memory, compared. Where Agent Memory sits against memory middleware, agent databases and vector databases.
vs. memory middleware
One engine in place of a vector store, a graph store and a row store held together in application code.
vs. agent databases
A multi-store architecture removed rather than internalised, with provenance on every fact.
Memory against vector databases
Embeddings beside the records they describe, in one engine and one transaction.
THE PLATFORM
Everything an application and its agents know. Five surfaces, one engine.
Database
Document, graph, vector, time-series and relational in one engine.
Agent Memory
What an agent learns, with its source and its time, in the same engine.
Cloud
Dedicated clusters by region, or serverless on SurrealDB Earth.
Studio
Query, explore and design the schema from the browser.
MCP
Every model that speaks MCP reaches the database and the memory directly.
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.
VP of Engineering, Later
GET STARTED