Most retrieval-augmented systems stop at search. But agents and copilots need structured, persistent memory to reason, adapt, and evolve over time.
In this session, we’ll show how to turn SurrealDB into a long-term memory layer for your LLM apps, combining graph and vector data to power richer context and better decisions.
In this online workshop, you’ll learn how to:
- Store persistent memories with graph-linked facts
- Perform similarity search and structured reasoning in one query
- Use vector embeddings and graph hops inside SurrealDB
We’ll walk through practical patterns and show how SurrealDB collapses graph, vector, and relational data into a single memory substrate for next-gen AI.
Agenda
- Welcome & introductions – 10 minutes
- Building Memory with Graphs + Vectors in SurrealDB – 40 minutes
- Q&A – 10 minutes
👉 New to SurrealDB? Get started here.
🗣️ Speaker opportunities - submit your talk! Working on an interesting project that you would like to share with the community? Submit here.
New to SurrealDB?
SurrealDB is a scalable multi-model database that allows users and developers to focus on building their applications rather than architecting and managing their infrastructure. SurrealDB allows users to use schema-less and schema-full data patterns effortlessly, with the ability to operate like a relational database with SQL (albeit without the JOINs), but with the same advanced functionality as the best NoSQL document and graph databases. SurrealDB was designed to enable users to build modern real-time applications effortlessly - with the ability to query right from Chrome, Edge, or Safari, removing the need for complicated database backends and APIs - with advanced row-by-row security and access permissions handled right within the database itself.