SurrealDB

Who held power in Rome in any given year? Our latest Cookbook demo maps about 9,200 events in SurrealDB Agent Memory, showing who ruled and controlled each place. Each new ruler supersedes the last without erasing them. Start exploring. 👉 sdb.li/47HzIuM

Ready to change a live schema with confidence? Learn how schema works in SurrealDB, tighten constraints, and ship changes with SurrealKit: fast sync in development, staged rollouts with a rollback path in production. Start the course. 👉 sdb.li/4iGQTml

From startups to global enterprises, developers use SurrealDB to power AI agents, knowledge graphs, and real-time systems. Discover who's building with our multi-model database and explore their stories. 👉 sdb.li/4jwxcMP

Today at 4 PM BST: Developer Office Hours on Discord. Host Drew Ridley will walkthrough recent changelog updates and what they mean for your projects. Join us and ask your questions live. 👉 sdb.li/4yAmP0q

First up in the SurrealDB Agent Memory Cookbook: Calgary 1912-1913 explorer. Walk the streets, speak to residents, and report on how the town changed. Every answer comes from directory records held in Agent Memory. Start exploring. 👉 sdb.li/4zM4ZIV

Building agent memory? Start with the right ingredients: every fact with its source, permissions that stick, and corrections that keep history. The SurrealDB Agent Memory Cookbook offers practical end-to-end guides. Pick a recipe. 👉 sdb.li/4k3M8nY

Can your AI agent tell what changed, when, and why? ICYMI: last week we launched SurrealDB Agent Memory to give your AI agents persistent state that keeps this history. Our benchmark results show strict accuracy, not just the mean. See why that matters in production.👉 sdb.li/4yl79hG

Launch week wasn’t long enough. So next week, we ship even more. SurrealDB 4, SurrealFS, SurrealDB Earth, and more. Simplicity or scale? Transactions or speed? Yes. Stop choosing.

Agent memory benchmarks are baked. We have just launched SurrealDB Agent Memory, and published every number behind its score: 77.2% on BEAM at 1M, 57.1% counting only full marks. Every strict score on this chart sits 20+ points below its headline. surrealdb.com/blog/agent-m...

Attending AI Engineer New York? Find us at booth 45, 12–14 Oct. Meet Tobie Morgan Hitchcock, @jaimemh.bsky.social, and the rest of the team. Learn why teams in financial services are rethinking where their agents keep state: memory, relationships, and access control in one engine. 👉 sdb.li/4yBsNyp

Speed or durability? In-memory or persistent? Simplicity or scale? Memory or accuracy? Transactions or speed? SQL or SurrealQL? Yes. Stop choosing. sdb.li/4hMwcVX 12-16 October. See you next week.

Finding content creators on Later's influencer marketing platform used to mean manual filtering. Now it runs on a context-aware knowledge graph on SurrealDB, blending semantic search, graph traversal, and vector search. Learn how. 👉 sdb.li/4wyyqfK

Developer Office Hours is back this Thursday at 4 PM BST on Discord. Join host Drew Ridley for a walkthrough of recent changelog updates, SurrealKit, and the Terraform provider for SurrealDB, plus live Q&A. See you there. 👉 sdb.li/4hJV6Em

Looking to build AI apps that remember, retrieve, and reason, and take them to production? The Encore integration adds backend infrastructure around our database, which stores context across documents, graph relationships, and vectors. Learn more. 👉 sdb.li/4yBEK7W

AI engineering is increasingly about more than calling an LLM API. For developers who want to learn it by building, our new SurrealDB University course covers RAG, agent memory, context layer architecture, and more. Get the course breakdown. 👉 sdb.li/4hCz329

Where does an AI agent’s state live once the process that created it is gone? We’re partnering with Antimetal, Auth0, and Amazon Web Services (AWS) during AI Engineer New York week for an evening of conversations and live demos answering that. Join us on Oct 12. 👉 sdb.li/4rN49ZJ

Where does your AI agent's memory actually live? @martinschaer.bsky.social puts it in a filesystem built on SurrealDB, with fused full-text and vector search, and RBAC in one clause. Learn how. 👉 sdb.li/46Qi4Vg

PolyAI's customers needed voice AI assistants that could answer from their own knowledge bases inside Agent Studio, without migrating sensitive content into a vendor's ecosystem. Learn how the SurrealDB integration made that possible. 👉 sdb.li/4sa4zJ5

A folder of meeting notes is a graph pretending to be documents. @martinschaer.bsky.social extracts it into SurrealDB using CocoIndex, then builds a text-to-SurrealQL agent that generates its prompt live from the schema, ensuring it never drifts. Learn how. 👉 sdb.li/4hEEjma

Meet Aeon's Surreal Renaissance, an interactive story where you're the main character. Discover SurrealDB's multi-model power through hands-on exploration. Begin your journey today. 👉 sdb.li/3Khkft6

We’re partnering with Mastra during SF Tech Week for an evening of demos and conversations that will answer the question of what shared memory means for AI agents. Join Tobie Morgan Hitchcock and Mastra’s Head of Research, Aamish Ahmad Beg, on Oct 5. Register. 👉 sdb.li/4AbwDAh

Developer Office Hours is back today at 4 PM BST on Discord. Have questions about the database or need practical guidance on projects you're working on? Chiru Boggavarapu and Drew Ridley are ready for them. Come ask them live. 👉 sdb.li/4rrExl0

Cobrainer runs graph, vector, full-text, and memory for its AI agent on one engine. Learn more about how it built a skills-intelligence platform with Graph RAG and agent memory. 👉 sdb.li/3R2eeE0

Our event, co-hosted with @docker.com, tackled agent access without losing control. Thanks to Per Ploug Krogslund (Docker), Martin Schaer, Jonathan Aiken (Pivot), and everyone who joined. Catch up on Martin's session on defining permissions at the data layer. 👉 www.youtube.com/watch?v=U-0Y...

A new claim lands. Does it echo past fraud, and is the claimant tied to a known ring? @martinschaer.bsky.social answers both with HNSW vector recall and graph traversal in one SurrealDB query, no ETL. Learn more. 👉 sdb.li/4jaSqBQ

Using @azure.microsoft.com? SurrealDB Cloud, our managed multi-model database service, is now available on Azure. Get private connectivity, lower latency, better data residency, simpler security, plus simplify procurement with Azure Marketplace. Get the details. 👉 sdb.li/4dF2Ztc

What does shared memory actually mean for AI agents? Want to find out? We're partnering with Mastra during SF Tech Week for an evening of live demos and conversations on this very topic. Join us on Oct 5. 👉 sdb.li/4AbwDAh

From startups to global enterprises, developers use our multi-model database to build AI agents, knowledge graphs, and real-time systems. Take a closer look at how they’re building with it. 👉 sdb.li/4jwxcMP

How do you migrate a production schema without breaking it? Our new SurrealDB University course covers schema internals plus SurrealKit's staged, reversible rollouts and fast sync for development. Get the course breakdown. 👉 sdb.li/4iiwuEy

Developer Office Hours is back today. Join Drew Ridley for a discussion and Q&A on SurrealGuard, which provides static analysis and type inference for SurrealQL. See you at 4 PM BST on Discord. 👉 sdb.li/4xg2Cwc

Curious what you can build with our multi-model database? SurrealDB Labs has tools, tutorials, demos, and community resources. Dive in and start building today. 👉 sdb.li/4vYwpc8

Conversation memory, workflow snapshots, evaluation scores, observability spans, and vector search. Most Mastra apps juggle four systems for that. SurrealDB can now serve as a storage backend for Mastra, handling that. Learn more. 👉 sdb.li/4yqtoDc

What does it take to build coherent agent memory? Join our CEO and Co-founder, Tobie Morgan Hitchcock, online on Sept 8 to find out. Register now to save your spot. 👉 sdb.li/4xDKSMi

SurrealDB Cloud is live in Frankfurt, Germany. It's our second European region for teams building with our multi-model database. The same benefits as our other regions apply: lower latency for AI agents and real-time apps. Learn more. 👉 sdb.li/4cVj8dO

Agent access is broken. Our London event, co-hosted with @docker.com, is where we'll tackle the problem together. Join Tobie Morgan Hitchcock, Per Krogslund (Docker), and guest speaker Jon Aiken (Pivot) to learn how. Register now. 👉 sdb.li/4xdzxCA

Spreadsheets or a flat CMDB table show assets, not what’s at risk if one gets compromised. @martinschaer.bsky.social models assets and their relationships as a graph in SurrealDB, so blast radius and incident reconstruction are one query away. Learn how. 👉 sdb.li/3SDFklV

Our SurrealDB Cloud region in São Paulo, Brazil is now live. If you're building with our multi-model database, you can benefit from lower latency for AI agents and real-time apps, plus satisfy data-residency requirements. Learn more. 👉 sdb.li/3SGSrm7

Untangling questions like who ultimately owns a fund can be hard for financial institutions, usually solved with recursive CTEs and reporting jobs. @martinschaer.bsky.social has another way, modelling it as a graph, the full chain in one query. Learn how. 👉 sdb.li/4qwqw59

Our London event, co-hosted with @docker.com, is Sept 17. How do you give an agent access to files, APIs, and data without losing control? Join Tobie Morgan Hitchcock, Per Ploug Krogslund (Docker), and guest speaker Jonathan Aiken (Pivot) to find out. 👉 sdb.li/4xdzxCA

Every production agent needs two graphs: the execution graph, what an agent does, and the context graph, what it knows. Tobie Morgan Hitchcock discusses why teams need to graph-engineer an agent's memory as well as the agent. 👉 sdb.li/4gGd1MF

Every agent reads from the same shared memory. So what stops one from surfacing another customer's data? Nothing, unless access control lives in the database. Join our CEO and Co-founder, Tobie Morgan Hitchcock, to learn how to enforce it. Register now. 👉 sdb.li/4qnWaBr