Emmanuel Keller

💜 Dev quote of the week.

💜 Dev quote of the week.

SurrealQL is our powerful, SQL-like query language that provides developers with an intuitive way to interact with our multi-model database. Start your journey of learning how to query data across multiple data models. 👉 sdb.li/4oZhdZD

.@digitalkin_ai has built an Agentic Mesh ecosystem for AI agents. Curious why they chose our multi-model database to power the single responsive data layer for memory, cross-agent coordination and live UI state? Find out how it works. 👉 sdb.li/4byjm9n

Love it see this, @chrisabruce! Congratulations!

.@polyaivoice needed a fast and open way for customers to bring their own knowledge bases into their customer service AI agents. Integrating SurrealDB into their Agent Studio platform made it possible. Learn how. 👉 sdb.li/3P1qFyM

Had a great time on the ML in Production panel at @pyabordsf earlier today with @jxnlco and @AntonisK, hosted by @BEBischof. Data is the bottleneck for AI agents. Agent memory needs to be multi-faceted - relational, graph, temporal, vector - and by optimising that data layer and the tools that call into it, you optimise token use too. You wouldn't employ someone who used the wrong tools and tried multiple times before succeeding at a task. Same goes for AI agents. Thanks @pydantic for putting it all together!

Curious how to keep an agent’s output correct as data changes, memory grows, and systems scale? Join @tobiemh and guest speakers @samuelcolvin (@pydantic ) and @LinghuaJ (@cocoindex_io) at our San Francisco meetup to learn how.

Hyderabad keeps delivering. Our meetup, in collaboration with GraphQL Hyderabad, brought together developers for sessions on database tech, @GraphQL, and AI-powered app development. Thanks to our community leaders Jayant Acharya and Chanda Raj Kumar, and to speakers Monika Kusumanchi, Uma Devi Cheruku, Vyshnavi Devi, Sreedhar Divi, and Jayasree Radavaram for their insightful sessions.

What a weekend for the London AI community. Our @SurrealDB x @LangChain Hackathon: Agents and Knowledge Graphs has wrapped. Developers building real things, pushing agents and knowledge graphs into exciting territory. Huge congratulations to the winners: 🥇 Team Taro 🥈 Team Synapse 🥉 Team Dead Reckoning A big thank you to the @LangChain, @LangChain_OSS @LangChain_JS, and @SurrealDB teams for making this happen, and to everyone who showed up, stayed late, and built something worth showing off. @anushkacreates's fantastic video says it better than I can. Next up, SurrealDB is heading to San Francisco for @nvidia GTC. If you are around, come find our booth. And if you want to join our next event, details are here: luma.com/psgx1v3g More to come. P.S. A big thank you also to Abda Bastola, @amadaecheverria, @chaeyoonakim, Dinuja Perera, @elenas_HQ, @IgnacioPaz87, @imam_shaik, @kramekar1, @martinschaer, Ned Rudkins-Stow, and @sudip_kandel.

If you’re working with lots of slide decks and need a better way to search through them, Surreal Slides makes it simple 🌀 Built around LlamaParse, it parses presentation files into clean, structured data, turning raw slides into something AI can truly understand. Each slide is extracted, summarized, and organized before being stored in @SurrealDB for flexible retrieval. From there, you can query your entire presentation library in natural language through an agentic interface: no need to manually scan files or remember where a specific slide lives. Take a look at the demo below👇 GitHub Repository: github.com/run-llama/surr…

💜 Dev quote of the week.

SurrealDB v3 is officially here. The most exciting part of this release is the new support for file uploads. You can now manage binary data and files directly within the database environment. This simplifies your architecture by reducing the need for external storage buckets. It is a major step forward for building streamlined applications. 🚀

SurrealDB v3 is officially changing the game for AI development. If you are building with AI models and RAG, this update simplifies your entire workflow. The biggest benefit is having your data and your vectors in one place. You no longer need to manage a separate vector database just to handle your embeddings. By integrating vector search directly into the core, SurrealDB v3 makes RAG workflows much faster and more efficient. It removes the friction of managing a complex stack for your AI applications. 🚀

@CodeEdison SurrealDb for 99% of use cases. The reliability is one thing, but vectors turned it into the default for anyone shipping AI apps. Everything else is usually just extra overhead.

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/4qLVHYV

Context graphs for AI are only as good as the relationships underneath them. @SurrealDB 3.0 just made record links bidirectional via record references. With the reference in place, linked records can automatically “see” the records linking to them. No more reverse-lookups. No more query hacks. No more schema gymnastics. Cleaner models. Faster traversals. Zero duct tape. If your “graph” needs workarounds, it isn’t graph-native. Learn more: surrealdb.com/docs/surrealql…

The latest SurrealDB JavaScript SDK release is our most significant update yet. We rebuilt the SDK’s core internals, focusing on ergonomics, flexibility, and developer experience. Our own Julian Mills breaks down what’s new. 👉 sdb.li/4rGRLtt

With the latest release of SurrealDB, we’re taking the first step toward native file support in our multi-model database. See what's new. 👉 sdb.li/4qUN7qi

With the latest release of SurrealDB, we’ve introduced record references to make working with record links more efficient, delivering clearer schemas, simpler queries, and faster traversals. Learn more. 👉 sdb.li/4clUX97