EVENTS
Upcoming events
Stream #38: A closer look at SurrealDB 4
SurrealDB 4 is here: the database and memory for every agent. It’s a big one. A faster engine, more than 240 fixes no 3.x release contains, and Postgres and MySQL compatibility, so the tools you already use can connect. Alongside it comes SurrealDB Earth, our new serverless offering on Cloudflare, which gives every user, customer or agent a database of its own that starts on its first query. And SurrealDS, for the deployments that need to grow. Join us live on Wed 18 Nov to dig into all of it. Tobie Morgan Hitchcock (co-founder and CEO) and Stu Schwartz (Head of Engineering) take a closer look at what’s new in SurrealDB 4 and why it matters. Then Chiru (Agentic Systems Engineer) puts it to work, building an online store platform where every shop gets its own database on SurrealDB Earth. The last part is yours, so bring your questions!
Register to join
Agents in Production: Multi-Agent Systems
Agents in Production is back in London, and this time we're teaming up with Mastra. What changes when it stops being one agent? Shared state between agents, who each one is acting as, and what stops them treading on each other. The move from a single assistant to a fleet is where most of the hard problems start. Expect honest talks from teams running multi-agent systems, live demos, plus food, drinks, and plenty of time for networking.
Save your seat
Beyond CRUD: The Data Layer for Agentic AI
A SurrealDB Hyderabad community meetup on moving beyond CRUD to an agentic, multi-model data foundation - data, relationships and retrieval for AI. Talks, live demos and networking at EPAM Hyderabad on Saturday 6 December 2026.
Save your seatSERIES
Programmes we run all year. In person, online and on demand.
Agents in Production
Our meetup series for the engineers who are actually shipping agents, in London, New York and San Francisco.
Webinars
Hour-long technical sessions with live demos and Q&A, live and on demand. Every one is recorded.
Livestreams
Release premieres, AMAs and build-alongs with the SurrealDB team, live on YouTube, LinkedIn and X.
ON DEMAND
Catch up on anything you missed. Webinars, meetup talks and livestreams.
Benchmarking agent memory: BEAM, observational memory and why the scores lie
Aamish Ahmad Beg, Mastra. Recorded at Shared Memory, San Francisco.
Watch now
When your agent stops reading and starts asserting
Jon Aiken, Pivot. Recorded at Trust, Access & Control, London.
Watch now
We gave AI a shell. What could possibly go wrong?
Per Krogslund, Docker. Recorded at Trust, Access & Control, London.
Watch now
Even a jailbroken LLM can't exceed its database permissions
Martin Schaer, SurrealDB. Recorded at Trust, Access & Control, London.
Watch now
Temporal knowledge graphs as agent memory
Watch now
Text-to-SurQL: Prompt engineering for agentic retrieval
Watch now
Access control for multi-agent systems
Watch now
Agent accuracy in production
Most agents have a memory now. Far fewer are accurate - able to answer correctly, stay right as things change, and show where each fact came from. Agent accuracy is the gap between a memory layer that simply exists and one you'd trust in production.
Watch now
SurrealDB Stream #37: Building a living knowledge layer for your agents
Everyone shows the clever query side of AI agents: vector search, GraphRAG, memory. Almost nobody shows the part that decides whether your agent is actually any good - how the data gets in, and how you keep it fresh. Re-embed everything on a schedule and your agent's knowledge is stale the moment the job finishes. On Thursday 30 July, Tobie Morgan Hitchcock sits down with Linghua Jin from CocoIndex and SurrealDB's Martin Schaer to walk through how a living knowledge layer for AI agents actually comes together. CocoIndex ingests your documents incrementally - recomputing only what changed - straight into SurrealDB, where the documents, an entity graph and the vectors all live in one store. Code-first and conversational: a walkthrough of a real, working pipeline and live queries. We'll cover: - Why stale, disconnected context is what really hurts agent accuracy - How incremental ingestion keeps your knowledge layer fresh, with no full rebuilds - How a folder of documents becomes chunks, embeddings and an entity graph in SurrealDB - Running vector search and graph traversal together in a single query - The edit-one-document moment: seeing only the delta re-embed Links: - Living knowledge layer blog: https://surrealdb.com/blog/a-living-knowledge-layer-for-your-agents-surrealdb-cocoindex
Watch nowGET INVOLVED
Be part of the next event. Speak, partner, host, or hear about every event first.
Speak at Agents in Production
Built something real with agents? Apply to give a talk at a night in your city.
Partner with us
Co-host a night, sponsor a hackathon or put your team on stage. Tell us what you have in mind.
Host a meetup
Run a SurrealDB meetup in your city. The team helps with speakers, swag and getting the word out.
Request a speaker
A SurrealDB engineer or founder for your stage, podcast or internal session.
Ambassador programme
Share what you build with SurrealDB, run sessions with us and get early access.
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
