Cloudflare
SurrealDB 4 and SurrealDB Earth. What every agent gets.
- Scales to zero instantly.
- Remembers in one query.
- Fully transactional. Still ACID.
- Speaks Postgres and MySQL.
- Cold starts on Earth in ~300ms.
- Instance creation time ~500ms.
- Starts on its first query on SurrealDB Earth.
- One engine. Serverless, Cloud or self-hosted.
- Scales to as many agents and users as you need.
HOW IT FITS TOGETHER
A database for every agent.Memory on top.One connected view of everything your application and agents know.
WHAT SETS IT APART
What makes it different
One database.Every data model.
SurrealQL unifies SQL, knowledge graphs, vector and full-text search, temporal and key-value queries in one language - on one database, backed by object storage.
- explore the databaseBetter context.Less overhead.
Retrieve more relevant context with fewer calls - helping improve accuracy, reduce latency and avoid wasting LLM tokens on unnecessary data.
- explore the databaseOne retrieval query.Fewer system hops.
Search, graph traversal, filtering and permissions in one retrieval query, so the context stack has fewer systems to cross.
- explore the databaseAccess control.Built into the data layer.
Define permissions at the role, record and field level, so every user, service or agent only sees and changes exactly what it should.
- explore the databaseUSE CASES
What teams build on one engine. With the data model each workload needs.
GraphRAG
Retrieval that combines graph traversal with vector search for grounded, connected context.
Agent Memory
Persistent, queryable memory for agents - relationships, semantics, and recency in one store.
Knowledge graphs
Model entities and relationships natively - query structure and meaning together.
Temporal facts
Facts that supersede one another with the history kept, so an agent knows what changed and when.
Digital twins
Assets, dependencies, telemetry and the agents that reason over them, in one transactional engine.
Real-time applications
Live queries and change streams, so every client sees a write as it commits.
One SurrealQL query searches vectors, walks the graph, filters documents and ranks full text, and commits it all in one ACID transaction.
Your questions,answered
SurrealDB is a database for every agent. Relational, document, graph, vector and time-series data are native primitives you can query together in one ACID transaction, through SurrealQL or through Postgres and MySQL clients. On SurrealDB Earth, each database starts on its first query and scales to zero immediately when the query ends. Authentication, row-level permissions and live queries are built in.
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
Start with the database, or start with Agent Memory. Both run on one engine. The database is a free account away. Agent Memory is a context in Studio away.
