Founder and COO @SurrealDB
London, England
Joined July 2021
- Tweets1.1K
- Following859
- Followers1.2K
- Likes3.1K
Pinned Tweet
The 3-day @SurrealDB x @LangChain hackathon kicked off last night at SurrealDB’s London HQ.
Very much looking forward to seeing what everyone creates by the end of the weekend. 🚀
Jaime Morgan Hitchcock retweeted
Catch-up: in-memory engine 1.0 at 28.3x (21.5M reads/s), persistent engine 1.0 at 7.95x (6.8M reads/s), Agent Memory 77.2% BEAM, CLI 1.0, plus v3.2.6 with KV export, Rome and Night Owls memory demos, Startup Programme open. Next week: SurrealDB 4, SurrealDB Earth, SurrealDS, and more. Still shipping.
Jaime Morgan Hitchcock retweeted
Great time at Cloudflare Connect. Thank you @dok2001 and the whole Cloudflare team for having us.
We have been building something very special on @Cloudflare. It goes live next week 🌍
Jaime Morgan Hitchcock retweeted
Great to catch up with @samlambert at @Cloudflare Connect 🧡 Agents are going to put a lot of pressure on databases, and @planetscale is clearly thinking hard about it. Looking forward to seeing what Neki becomes.
Jaime Morgan Hitchcock 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. 👉 sdb.li/4BgWxmx
Jaime Morgan Hitchcock retweeted
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/4zqTxCi
Jaime Morgan Hitchcock retweeted
Just a reminder, there's another release from @SurrealDB this week.
Jaime Morgan Hitchcock retweeted
Weekly Changelog
- New in-memory storage engine, 1.0: 28.3x the point reads of RocksDB, both in memory. 21.5M reads a second
- New persistent storage engine, 1.0: 7.95x the point reads of RocksDB with synchronous durability. 6.8M reads a second. Encryption at rest on by default
- SurrealDB Agent Memory: 77.2% on BEAM at 1M tokens, 57.1% counting only full marks. Every number published
- SurrealDB CLI 1.0: one launcher for the database, Agent Memory, Cloud, extensions, and the language server
- SurrealDB Studio: support for accountless access and Agent Memory context management
- New LangGraph.js docs for Agent Memory
- SurrealDB v3.3.4
Launch week wasn’t 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.
Jaime Morgan Hitchcock retweeted
Great day at the @FirstMarkCap CEO Summit. Top sessions from @harleyf, @profound, @clay, and @glencoates.
Thank you, as always, @FirstMarkCap.
Jaime Morgan Hitchcock retweeted
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-mem…
Jaime Morgan Hitchcock retweeted
Best out there (it’s not particularly close) AND fully multi-model, you really can say YES to everything @SurrealDB 🚀🚀
SurrealDB Agent Memory is live.
Every fact keeps its source, history, and permissions.
BEAM: 77.2% headline. 57.1% strict (fully correct only).
Same strict count on every vendor with public per-question files.
Judges named. 700 answers published.
surrealdb.com/agent-memory/b…
Jaime Morgan Hitchcock retweeted
SurrealDB Agent Memory is live.
Every fact keeps its source, history, and permissions.
BEAM: 77.2% headline. 57.1% strict (fully correct only).
Same strict count on every vendor with public per-question files.
Judges named. 700 answers published.
surrealdb.com/agent-memory/b…
Jaime Morgan Hitchcock retweeted
In the real world, you don't get to tell your agent what kind of question it's about to be asked. A benchmark shouldn't either.
So ours doesn't. 77.2% on BEAM at 1M, 57.1% strict, every number with its judge.
Jaime Morgan Hitchcock retweeted
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.
We are replacing RocksDB.
26.8x the creates. 7.95x the reads. 6.10x the updates.
Every commit flushed to disk. One machine. One command.
Do not take my word for it. Run it yourself.
surrealdb.com/blog/we-are-re…
Jaime Morgan Hitchcock retweeted
We are replacing RocksDB.
Our new persistent storage engine is out today, open source under Apache 2.0.
With every commit flushed to disk: reads 7.95x faster, updates 6.10x faster, creates 26.8x faster.
Read the post: surrealdb.com/blog/we-are-re…
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
