Growth @ SurrealDB
London, England
Joined April 2011
- Tweets178
- Following364
- Followers119
- Likes1.9K
The cat's out of the bag.
SurrealDB 4 and @SurrealDB Earth are out today.
When we started SurrealDB, I wanted one database that could hold every shape of data and query it all together.
Now every agent, user and app can have a database of its own.
Ignacio Paz retweeted
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. 馃憠 sdb.li/4BgWxmx
Ignacio Paz retweeted
Just a reminder, there's another release from @SurrealDB this week.
Ignacio Paz retweeted
Launch week wasn鈥檛 long enough.
28.3x the point reads of RocksDB, in memory.
7.95x on disk, with synchronous durability.
77.2% on BEAM at 1M tokens. 57.1% strict.
Next week: @SurrealDB 4, SurrealFS, SurrealDB Earth, and more.
Agent Memory is here. This is one of the biggest launches in SurrealDB's history.
It turns conversations and documents into a shared brain of entities, relationships, and facts, tracking where information came from and how it changes over time. It's built on top of SurrealDB, which supports graphs, vectors, and documents in one database - there's no need to stitch together multiple systems. The result: better accuracy, performance, and token efficiency.
We've also invested heavily in benchmarking, achieving 77.2% on BEAM. There are great alternatives like Mem0, Honcho, and Cognee, but we're taking a different approach.
Memory or accuracy? Yes.
SurrealDB Agent Memory: memory for AI agents, every fact with its source.
77.2% on BEAM, the 1M-token memory benchmark. 57.1% strict, every rubric item met in full. No other vendor we checked publishes that.
Learn more: sdb.li/4zqTxCi
Stop choosing.
Ignacio Paz retweeted
Speed or durability? Yes.
We're replacing RocksDB.
New persistent storage engine: reads 8.0x and updates 6.1x faster than RocksDB. Reads 73.7x faster than SlateDB (on disk, not object storage).
Run it yourself.
Stop choosing.
sdb.li/3VE7i24
Ignacio Paz retweeted
In-memory or persistent? Yes.
Our new in-memory storage engine: 28.3x faster than RocksDB and 17.5x faster than LMDB for reads, both in memory. Lock-free. Embedded, in the browser or on a server.
Run it yourself.
Stop choosing.
sdb.li/4zqT3Mt
Something's coming...
Speed or durability?
In-memory or persistent?
Simplicity or scale?
Memory or accuracy?
Transactions or speed?
SQL or SurrealQL?
Yes.
Stop choosing.
sdb.li/4eicEGr
12-16 October. See you next week.
Ignacio Paz retweeted
Weekly Ship Log
- SurrealDB Cloud on Microsoft Azure
- Mastra template: Company Brain with SurrealDB
- Beekeeper Studio integration and new Database clients docs section
- SurrealDB docs skill for coding agents
- SurrealKit Beta.3
- Agent Memory in Studio
- Embedded SurrealDB (in-memory) on the Swift SDK
Ignacio Paz retweeted
More ways to build. More ways to scale. 馃殌
Exciting to see @SurrealDB bring SurrealDB Cloud to Microsoft Azure, opening up new possibilities for teams building in the cloud鈽侊笍
Using @Azure? 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. 馃憠 sdb.li/4yJz9fx
Ignacio Paz retweeted
This morning with startup program leaders at Granola, Dust, Stripe, Clay, Fin, SurrealDB, HYPE, and MongoDB.
馃嚞馃嚙鉂わ笍馃敟
Ignacio Paz retweeted
Using @Azure? 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. 馃憠 sdb.li/4yJz9fx
Ignacio Paz retweeted
Weekly Ship Log
- SurrealDB v3.1.6
- SurrealDB Cloud in S茫o Paulo
- SurrealDB Cloud in Frankfurt
- Mastra integration for SurrealDB and Agent Memory
- Hermes integration with SurrealDB file system, database, and Agent Memory docs
- Agent Memory JavaScript SDK on npm as @surrealdb/memory
- Docs search in SurrealDB MCP
Ignacio Paz retweeted
Our SurrealDB Cloud region in S茫o 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. 馃憠 sdb.li/4qQEHSC
Ignacio Paz retweeted
Weekly Ship Log
- SurrealDB file system, a virtual file system for AI agents, with Hermes, Pydantic, OpenAI and Anthropic
- Claude SDK and JetBrains Air integrations for Agent Memory
- SurrealKit v1 beta, our schema migration tooling
- New "Schema internals and migrations" course on SurrealDB University
- Docker Sandbox (SBX) integration
- TanStack DB integration, local-first collections
- Agent Memory integration with Mastra v1
- Docs MCP, docs search now served from the Fabric API
Ignacio Paz retweeted
Meet SurrealDB Studio, our new app for working with your SurrealDB instances and Spectron contexts. It takes over from Surrealist as the official app. Learn why we built it, and what it has to offer. 馃憠 sdb.li/4gl5a77
Ignacio Paz retweeted
A data warehouse tells you what is true, not how things connect. Surreal Sync now ingests Snowflake tables into SurrealDB, where facts join the relationships, vectors, and agent memory already living in one engine.
Learn more. 馃憠 sdb.li/4wbn4On
