Give every agent
its own database

Q: Can I use SurrealDB without Agent Memory for AI agents?

Yes. SurrealDB gives each agent a database for graph traversal, vector search and real-time subscriptions, and on SurrealDB Earth each one starts on its first query. Agent Memory adds structured memory on top, and can be added later.

Q: Can each agent have its own database?

Yes. On SurrealDB Earth each agent or user can have its own database on Cloudflare's network. Each database is its own instance, with its own storage and commit log. It starts with the first query, cold starts in ~300ms and scales to zero instantly when idle, and you pay for the data it stores.

Q: Can an agent use a Postgres or MySQL client?

Yes. SurrealDB 4 speaks the Postgres and MySQL wire protocols, so an agent can write the SQL it already knows through the clients it already uses, and most queries run unchanged.

Q: What frameworks does SurrealDB integrate with?

SurrealDB integrates with LangChain, LlamaIndex and any MCP-compatible client through the MCP server. Official SDKs cover Python, JavaScript, Rust, Go, Java, .NET and PHP.

Start free with SurrealDB Explore Agent Memory Explore SurrealDB Earth

One per agent. On SurrealDB Earth each agent or user can have its own database, which starts on its first query and scales to zero when idle.

Speaks Postgres and MySQL. Agents write the SQL they already know, and Postgres and MySQL clients connect as they are.

Remembers in one query. Vector, graph, document and full-text come back together, and Agent Memory keeps each fact with its source.

01 |THE PROBLEM

The context wall. Every seam between systems is where context leaks.

Context leakage

Relationships, history and metadata fragment as data moves between systems.

Partial writes

Without one transaction, memory updates in one system while state fails in another.

Compounding latency

Every hop between systems is a round trip, and they add up under load.

Operational overhead

Five systems means five failure modes, five monitors and five sets of credentials.

02 |MEMORY

Remembers in one query. Graph, vector, filters and time in one round trip.

1-- Context engineering: combine graph, vector, and temporal data
2LET $user = user:jaime;
3LET $query_vec = fn::embed("What products does this user like?");
4
5SELECT
6	->purchased->product AS purchase_history,
7	->reviewed->product[WHERE vector::similarity::cosine(embedding, $query_vec) > 0.8] AS relevant_products,
8	->preferences[WHERE valid_at <= time::now()] AS current_preferences
9FROM ONLY $user;

03 |MULTI-AGENT

Coordination through shared memory. One knowledge graph, under ACID guarantees.

Memory

Shared memory

Agents that share a Context read and write one Agent Memory graph, so what one agent learns is there for the others.

Explore Agent Memory

Writes

Serialised writes

Concurrent writes from many agents commit in order, with no lost updates.

How transactions work

Events

Event-driven handoffs

Live queries and events wake downstream agents when relevant data changes.

Explore real-time

Permissions

Unified permissions

RBAC and record-level permissions apply to every agent the same way.

Explore permissions

04 |THE STACK

Database and Agent Memory. One stack, one transaction, one policy.

Structured context

Documents, graphs, vectors, time-series and relational data in one engine.

Persistent memory

Knowledge graphs, entity extraction and temporal facts, kept with their source.

Hybrid retrieval

Vector similarity, graph traversal and structured filters in a single query.

Serverless on Earth

Serverless databases on Cloudflare's network, as many as your agents and users need, scaling to zero when idle; you pay for the data it stores.

Your questions,answered

How does this differ from RAG?

RAG retrieves chunks of text by vector similarity. SurrealDB and Agent Memory supply structured context, with graphs, documents, vectors, temporal facts and memory in one transactional system. RAG is one retrieval pattern within it.

Can I use SurrealDB without Agent Memory for AI agents?

Can each agent have its own database?

Can an agent use a Postgres or MySQL client?

What frameworks does SurrealDB integrate with?

THE PLATFORM

Everything an application and its agents know. Five surfaces, one engine.

Database

Document, graph, vector, time-series and relational in one engine.

Five data models as dotted tiles: documents, graph, vector, time-series and relational

Agent Memory

What an agent learns, with its source and its time, in the same engine.

A timeline of remembered facts, each with its source

Cloud

Dedicated clusters by region, or serverless on SurrealDB Earth.

Clusters in three regions on a world map, each running or scaling

Studio

Query, explore and design the schema from the browser.

MCP

Every model that speaks MCP reaches the database and the memory directly.

Three models connected through MCP to the database and Agent Memory

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

Give every agent its own database. A database that starts on its first query on SurrealDB Earth, with Postgres and MySQL clients and memory in one query.

Start free with SurrealDB Start in Studio