Talk to us about Agent Memory
A context created in Studio gets you started straight away, on a free Sandbox plan with 3 million tokens. To talk through a design, a custom quote or an enterprise deployment, tell us what you are building and the memory problem you are solving. Prefer to speak to sales directly? Contact our sales team.
YOUR WORKSPACE
What a workspace comes with. Durable memory for your agents, on SurrealDB.
Knowledge graph
Entities matched by type and name as they arrive, so each one has one node.
Tri-temporal model
Supersession chains keep every version of a fact and when it held.
Hybrid retrieval
Seven signals fused into one ranking, each recorded on the trace.
Shared memory across agents
Scope enforced by Agent Memory on every read and write, not left to the caller.
Between conversations
Elaboration and consolidation run in the background, between conversations.
MCP server and SDKs
Seven MCP tools, Python and TypeScript SDKs, and adapters for agent frameworks.
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
Managed clusters in the regions you choose, scaled on demand.
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