We are replacing RocksDB with SurrealKV 1.0
SurrealKV 1.0 is open source today: 7.95× faster point reads than RocksDB with synchronous durability, and the command to run the benchmark yourself.
SurrealDB Blog6 min read
SurrealDB
33 stories
Our commitment to open source: show the code, run the numbers
SurrealKV and SurrealMX are open source under Apache 2.0, and every benchmark we publish comes with the command to run it.
SurrealDB Blog5 min read
Introducing SurrealMX: SurrealDB’s new in-memory storage engine
SurrealMX is SurrealDB’s high-performance in-memory storage engine, built for ultra-low latency, high concurrency, and millions of operations per second.
SurrealDB Blog6 min read
Introducing Encore × SurrealDB
SurrealDB and Encore make it easier to build production-ready AI applications with durable memory. The integration combines SurrealDB’s vector search, graph relationships and structured data with Encore’s APIs and infrastructure, giving developers a simpler way to build, test and deploy…
SurrealDB Blog3 min read
Introducing our new University course: “SurrealDB for AI Engineers”
Learn AI engineering hands-on with SurrealDB, from vector search and RAG to hybrid retrieval, agent memory, Text-to-SurrealQL, and context-layer architecture.
SurrealDB Blog3 min read
SurrealDB Cloud is now available on Microsoft Azure
SurrealDB Cloud now runs on Microsoft Azure, so teams standardised on Azure can deploy inside the cloud they have already approved.
SurrealDB Blog2 min read
Multi-hop graph traversal inside SurrealDB
Move breadth-first search into SurrealDB: recursive traversal with a depth range, predicates pushed into every hop, and what EXPLAIN says about edge indexes.
SurrealDB Blog13 min read
Why does my vector search return nothing when I add a filter?
A filter applied after an HNSW walk can only remove rows, so a selective one comes back empty. Three measured SurrealDB fixes, plus the schema that avoids them.
SurrealDB Blog18 min read
Announcing the Mastra integration for SurrealDB and Agent Memory
One package gives Mastra agents a single database for conversations, workflow state, observability and vectors, plus managed memory that extracts and semantically recalls facts.
SurrealDB Blog4 min read
SurrealDB Cloud is now available in Frankfurt, Germany
SurrealDB Cloud now runs in Frankfurt, Germany: lower latency across continental Europe, German and EU data residency, and a shorter round trip for agents.
SurrealDB Blog2 min read
SurrealDB Cloud is now available in São Paulo, Brazil
SurrealDB Cloud now runs in São Paulo: in-region latency for Latin America, Brazilian data residency, and faster agent workloads.
SurrealDB Blog2 min read
Building a filesystem-based agent memory on SurrealDB
Give an AI agent persistent memory as a filesystem in SurrealDB: computed file paths, fused full-text and vector search, and RBAC in a single PERMISSIONS clause
SurrealDB Blog17 min read
How Cobrainer built graph-based agent memory on one engine
Cobrainer runs graph-based agent memory and a Rust-native agentic graph RAG on SurrealDB, replacing a separate vector store and search engine.
SurrealDB Blog5 min read
SurrealDB University's newest course on schemas
SurrealDB University's newest course teaches you about schema internals and migrations.
SurrealDB Blog7 min read
Graph engineering is missing a graph
Graph engineering stops at the diagram. The harder half is the context graph underneath: whether relations, vectors and memory share one consistency boundary.
SurrealDB Blog20 min read
Announcing the Swift SDK for SurrealDB
The first alpha of the official Swift SDK for SurrealDB is here, with async/await, type-safe models, live queries, and Swift Package Manager support.
SurrealDB Blog3 min read
Testing known time in Agent Memory on a 2,200-year corpus
How to use asOf in Agent Memory to allow gating of spoilers to ensure that spoiler-filled memory, even if already ingested, does not show up if it should not.
SurrealDB Blog8 min read
Introducing SurrealDB Studio and what it means for you
Introducing SurrealDB Studio: the new app for working with your SurrealDB instances and Spectron contexts, and the most powerful way to interact with your data.
SurrealDB Blog8 min read
Showing 18 of 33 stories
Load more storiesAiByts Weekly Brief
Get the top AI news and tools straight to your inbox every week.
Weekly · AI news
Join 15,000+ AI enthusiasts