Paul de Grijp

Passionate about building software products | Engineering Leader | Remote-first | @weaviate_io

[Bob van Luijt @bobvanluijt]

Back in the day, our version of a "free tier" was simply: "Go use the open-source version."

While that open-source version now gets hit millions of times per month (which, FWIW, is incredible 🤯), Weaviate has evolved into so much more than just a database

🧵👇

[Paul de Grijp @pauldegrijp]

Just back from Greece with our rockstar Weaviate Engineering & Product team 💚 One week, fully locked in 🔥
We aligned on our roadmap, had a real debate about the coding agents transformation, and ran a hackathon where we shipped a TON of great new features, all building on Weaviate 🚀

This team is unreal. Remote-first works, but put them in one room for a week and you see magic!

[Bob van Luijt @bobvanluijt]

🔥 The Weaviate team is on absolute fire this month, shipping one major update after another!

🗣️ Today, I am incredibly excited to roll out a feature requested by MANY of our community members

🚀 We have just launched a 𝗙𝗥𝗘𝗘 𝗙𝗢𝗥𝗘𝗩𝗘𝗥 𝗧𝗜𝗘𝗥 on Weaviate Cloud!

[Bob van Luijt @bobvanluijt]

🚢 Toot! The team is shipping again!

We’re seeing a massive wave of developers & agents building advanced AI memory capabilities on top of Weaviate. To make that even easier, we just launched Engram, a dedicated memory service built right on our database.

[Weaviate AI Database @weaviate_io]

Most agent memory systems are just glorified context windows.

And this is exactly why production agents fail at scale.

We've been working on this for months, and it's finally here: 𝗘𝗻𝗴𝗿𝗮𝗺 𝗶𝘀 𝗻𝗼𝘄 𝗚𝗔.

If you've been building agentic applications, you know the problem. Agents that should get smarter over time stay flat instead. They forget user preferences, re-solve the same problems repeatedly, and waste tokens on work that can't be reused. Long context windows help, but cramming them full degrades accuracy, inflates costs, and increases latency.

𝗘𝗻𝗴𝗿𝗮𝗺 𝘀𝗼𝗹𝘃𝗲𝘀 𝘁𝗵𝗶𝘀.

It's a managed memory service built on Weaviate that 𝘢𝘤𝘵𝘪𝘷𝘦𝘭𝘺 𝘮𝘢𝘪𝘯𝘵𝘢𝘪𝘯𝘴 memory instead of just storing it. Asynchronous pipelines extract relevant information from raw data, reconcile it with existing memories (handling deduplication, preference changes, time-evolving facts), and persist clean, structured memory state ready for retrieval.

𝗞𝗲𝘆 𝗰𝗮𝗽𝗮𝗯𝗶𝗹𝗶𝘁𝗶𝗲𝘀:

𝗙𝗶𝗿𝗲-𝗮𝗻𝗱-𝗳𝗼𝗿𝗴𝗲𝘁 𝗔𝗣𝗜 → Add raw data and continue working. Pipelines run asynchronously in the background with durable execution.

𝗧𝗼𝗽𝗶𝗰𝘀 𝗮𝘀 𝗺𝗲𝗺𝗼𝗿𝘆 𝗺𝗮𝗴𝗻𝗲𝘁𝘀 → Natural language descriptions that pull matching information from raw data. You control what's worth remembering.

𝗦𝗰𝗼𝗽𝗲𝘀 𝗳𝗼𝗿 𝗶𝘀𝗼𝗹𝗮𝘁𝗶𝗼𝗻 → Project-wide, user-scoped, or property-scoped memories with hard and soft isolation enforced at the platform level.

𝗖𝗼𝗺𝗽𝗼𝘀𝗮𝗯𝗹𝗲 𝗽𝗶𝗽𝗲𝗹𝗶𝗻𝗲𝘀 → Extract, transform, buffer, and commit steps that manage memories dynamically based on data type and preferences.

𝗕𝘂𝗶𝗹𝘁 𝗼𝗻 𝗪𝗲𝗮𝘃𝗶𝗮𝘁𝗲 → Memory retrieval inherits Weaviate's vector + keyword + metadata search on the same production stack you already trust, using native multi-tenancy to isolate instances.

Whether you're building chatbots that remember user preferences, agents that learn from experience, or multi-agent systems that need shared context, Engram gives you memory as infrastructure.

As a promotional offer, we’re giving $75 in credits for your first three months of Engram! Sign up before July 15th to claim it.

Read the blog: https://t.co/24koipQIjO

Get started: https://t.co/v9fMGMNCej

[Weaviate AI Database @weaviate_io]

A few weeks ago, @philipvollet, @victorialslocum and @aestheticedwar1 joined the 𝗕𝗶𝗴 𝗕𝗲𝗿𝗹𝗶𝗻 𝗛𝗮𝗰𝗸 with a mission: build an epic project with Weaviate, and win the top prize.

They only had 36 hours start to finish, and the concept was ambitious - combine trend-dectection on Twitter with persona-based AI content generation.

𝗧𝗵𝗲 𝘁𝗲𝗰𝗵 𝘀𝘁𝗮𝗰𝗸:
• Weaviate for storing and semantically searching Twitter data
• Gemini models for content generation
• Tavily for additional context retrieval
• A custom scoring model built with Pioneer to rank trends

The system monitors Twitter to identify emerging trends using semantic clustering. When it finds something relevant, it analyzes your writing style and previous content to build a persona model. Then it generates new posts about those trends - but in 𝘺𝘰𝘶𝘳 voice, not generic AI-speak.

The question is: did their sleep-deprived hackathon project manage to take home the 10k top prize?

Watch our new video to find out 👀
https://t.co/Uy1CeQT1TU

[Etienne Dilocker @etiennedi]

💯

The ability to mix structured and semantic information in a single query/prompt is what makes Weaviates Query agent so powerful.

This is not 2023 style vector search, this is 2026 agentic retrieval.

[Etienne Dilocker @etiennedi]

Small Change, Big Impact: Day 1/5: PQ Speed-up 📈⚙️

Product Quantization just got ~60% faster on average between v1.34.7 and v1.34.8.

How? Why? It uses an optmization technique that's probably as old as coding itself. More in 🧵⬇️

[Weaviate AI Database @weaviate_io]

Big update from the Weaviate Cloud team!

We’ve rolled out a 𝗻𝗲𝘄 𝗽𝗿𝗶𝗰𝗶𝗻𝗴 𝗺𝗼𝗱𝗲𝗹 to make it easier to understand what you’re paying for and ensure pricing scales with how you actually use the platform - no matter if you're testing ideas or running production workloads:

Here's what's new:
- New names: Serverless Cloud → 𝗦𝗵𝗮𝗿𝗲𝗱 𝗖𝗹𝗼𝘂𝗱, Enterprise Cloud → 𝗗𝗲𝗱𝗶𝗰𝗮𝘁𝗲𝗱 𝗖𝗹𝗼𝘂𝗱
- New pricing dimensions: 𝘃𝗲𝗰𝘁𝗼𝗿 𝗱𝗶𝗺𝗲𝗻𝘀𝗶𝗼𝗻𝘀, 𝘀𝘁𝗼𝗿𝗮𝗴𝗲, 𝗯𝗮𝗰𝗸𝘂𝗽𝘀
- New plans: 𝗙𝗹𝗲𝘅, 𝗣𝗹𝘂𝘀, and 𝗣𝗿𝗲𝗺𝗶𝘂𝗺
- Real-time cost visibility with a new pricing calculator

The result: transparent, predictable pricing that scales with your actual usage 💚

🔬 Read the full breakdown in our launch blog: https://t.co/v4vB2RhrfE
🔖 See the details on our pricing page: https://t.co/EIm0pUyC1A

[Victoria Slocum @victorialslocum]

Stop trying to find internal company info like this..

This no-code AI solution takes 5 minutes to build.

Sometimes it pays to work smarter, not harder - I built this company knowledge Q&A system with zero coding, using @stackai's Platform.

These customizable, no-code solutions provide huge benefit to companies wanting to set up AI workflows without needing developer resources - or teams who are looking to leverage AI in minutes, not weeks.

Check it this webinar to learn more! https://t.co/qIyKgAplja

Awesome company, awesome product - using @weaviate_io's vector database under the hood 💚

[Bob van Luijt @bobvanluijt]

🚢 Big Shipping News: 𝗜𝗻𝘁𝗿𝗼𝗱𝘂𝗰𝗶𝗻𝗴 𝘁𝗵𝗲 𝗤𝘂𝗲𝗿𝘆 𝗔𝗴𝗲𝗻𝘁!
🙌 Today is a major milestone for Weaviate—we’re officially launching the first of our three Weaviate Agents, starting with the 𝗤𝘂𝗲𝗿𝘆 𝗔𝗴𝗲𝗻𝘁!
👉 Read the release blog: https://t.co/T8PZImp4XC

𝗔 𝗕𝗶𝘁 𝗼𝗳 𝗛𝗶𝘀𝘁𝗼𝗿𝘆
When RAG (Retrieval-Augmented Generation) first started making waves, we immediately asked ourselves: What if RAG could go back into the database? This led us to develop the concept of 𝙂𝙚𝙣𝙚𝙧𝙖𝙩𝙞𝙫𝙚 𝙁𝙚𝙚𝙙𝙗𝙖𝙘𝙠 𝙇𝙤𝙤𝙥𝙨—a way to improve retrieval and generation continuously. As the idea evolved and agents took off, we refined our approach and terminology, making agentic AI a core part of the Weaviate ecosystem.

👉 Read more here: https://t.co/zhXnRzkhSX

𝗤𝘂𝗲𝗿𝘆𝗶𝗻𝗴 𝗗𝗮𝘁𝗮𝗯𝗮𝘀𝗲𝘀 𝘄𝗶𝘁𝗵 𝗙𝘂𝗻𝗰𝘁𝗶𝗼𝗻 𝗖𝗮𝗹𝗹𝗶𝗻𝗴
Out of this, the publication 𝙌𝙪𝙚𝙧𝙮 𝘿𝙖𝙩𝙖𝙗𝙖𝙨𝙚𝙨 𝙬𝙞𝙩𝙝 𝙁𝙪𝙣𝙘𝙩𝙞𝙤𝙣 𝘾𝙖𝙡𝙡𝙞𝙣𝙜 was born. The Weaviate Labs team conducted extensive research to explore how we could build truly database-centric agents—agents that don’t just retrieve data but actively enhance and evolve database management. This represents a major leap forward, blending AI-driven automation with traditional database operations in a way that’s never been done before.

👉 Read the research paper: https://t.co/xw3eJpdS5K

𝗪𝗵𝗮𝘁’𝘀 𝗡𝗲𝘅𝘁❓
At Weaviate, we truly believe this is a huge step forward in building AI-native database technology. By merging traditional database operations with AI-powered agents, we're redefining what's possible in database management. And this is just the beginning.

𝗧𝗿𝘆 𝗜𝘁 𝗢𝘂𝘁 𝗳𝗼𝗿 𝗙𝗿𝗲𝗲❗
The Query Agent is now 𝗳𝗿𝗲𝗲 𝘁𝗼 𝘁𝗿𝘆 𝗼𝗻 𝗪𝗲𝗮𝘃𝗶𝗮𝘁𝗲 𝗖𝗹𝗼𝘂𝗱. Check out the documentation and our press release for more details. We can’t wait to see what you build! 🚀

👉 Documentation: https://t.co/XrAxPY7yM6
👉 Press release: https://t.co/cawFd7Gp0b

💚 to the whole Weaviate team, you all rock!
#️⃣ #Weaviate #AI #VectorSearch #RAG #AgenticAI

PS:
Soon even more agentic releases!

[Bob van Luijt @bobvanluijt]

🔥 The Weaviate team is on fire!
🤯 The month is almost over, but look at this laundry list of things shipped!
🚢 𝗪𝗲𝗮𝘃𝗶𝗮𝘁𝗲 𝗘𝗺𝗯𝗲𝗱𝗱𝗶𝗻𝗴𝘀 𝗶𝘀 𝗻𝗼𝘄 𝗚𝗔 𝗶𝗻 𝗪𝗲𝗮𝘃𝗶𝗮𝘁𝗲 𝗖𝗹𝗼𝘂𝗱, featuring @SnowflakeDB's Arctic Embed 2.0
🚢 Dedicated Enterprise Deployment on 𝗠𝗶𝗰𝗿𝗼𝘀𝗼𝗳𝘁 𝗔𝘇𝘂𝗿𝗲
🚢 𝟵𝟰% 𝗳𝗮𝘀𝘁𝗲𝗿 𝗸𝗲𝘆𝘄𝗼𝗿𝗱 𝘀𝗲𝗮𝗿𝗰𝗵 with BlockMax WAND
🚢 𝗙𝘂𝗹𝗹 𝗥𝗕𝗔𝗖 𝘀𝘂𝗽𝗽𝗼𝗿𝘁 is now available as an enterprise feature
🚢 𝗠𝘂𝗹𝘁𝗶-𝘃𝗲𝗰𝘁𝗼𝗿 𝗲𝗺𝗯𝗲𝗱𝗱𝗶𝗻𝗴𝘀 now enable both queries and objects to be represented by multiple vectors (ColBERT-style "late interaction")
🚢 @nvidia integrations make it easier to build AI applications with embedding, search, and RAG
🚢 Async Replication enables 𝗮𝘂𝘁𝗼𝗺𝗮𝘁𝗶𝗰 𝗰𝗼𝗻𝘀𝗶𝘀𝘁𝗲𝗻𝗰𝘆 𝗺𝗮𝗶𝗻𝘁𝗲𝗻𝗮𝗻𝗰𝗲 across a distributed deployment
🧑‍🔬 𝗤𝘂𝗲𝗿𝘆𝗶𝗻𝗴 𝗗𝗮𝘁𝗮𝗯𝗮𝘀𝗲𝘀 𝘄𝗶𝘁𝗵 𝗙𝘂𝗻𝗰𝘁𝗶𝗼𝗻 𝗖𝗮𝗹𝗹𝗶𝗻𝗴 on Arxiv
📺 Three New podcasts
📚 Many new AI educational materials
💡 Stay up-to-date here: https://t.co/RPuMA0eGT9

[Paul de Grijp @pauldegrijp]

@TousEnsembleBe @weaviate_io Hi👋 The Weaviate Explorer Tool is currently in Early Access. Please DM me if you want me to add you to our Early Access program.

[Paul de Grijp @pauldegrijp]

Interesting perspective about the potential impact of AGI https://t.co/MojDAaNKH1

[Andrej Karpathy @karpathy]

The hottest new programming language is English

[Andrej Karpathy @karpathy]

Imo the productivity amplification here is so large that organizations should be thinking about it as a basic work tool, like a new kind of spreadsheets++, given out eagerly and by default.

[Bottlepay @bottlepay]

Tired of creating invoices for every transaction? Try LNURL. Bottlepay users can receive instant Lightning payments with the convenience of a static QR or address, just like on-chain. The best of both. Try it today, Bottlepay.

🤩 ⚡ 📱

#bitcoin #LightningNetwork #bottlepay

[Lyn Alden @LynAldenContact]

@coryswan From a recent draft I'm working on.

[Bottlepay @bottlepay]

Want one less thing to worry about? With the Bottlepay app you can schedule reoccurring buys. Monthly, weekly, daily, even hourly, Bottlepay has got you covered ✅ ⚡ 📱

#bitcoin #bottlepay