The data platform powering the AI era. Speed, scale, and cost-efficiency - without compromise. Get started today: https://xitter.cf/t.co/RpLdh0f8K3
Bay Area / Amsterdam
Joined January 2017
- Tweets5.1K
- Following65
- Followers20.9K
- Likes2.2K
Pinned Tweet
Welcome to ClickHouse, @andy_pavlo 👋
We're launching ClickHouse Labs, a new research group advancing foundational database technology, led by Andy as VP of Database Research.
Andy is an award-winning database researcher, professor at Carnegie Mellon University’s Computer Science Department and longtime leader of the CMU Database Research Group. At ClickHouse Labs, he'll build a team to take on the hardest problems in database systems, testing their work on real workloads and publishing it in the open, across both ClickHouse and PostgreSQL.
Read Andy’s blog: clickhouse.com/blog/andy-pav…
300 GB → 27 GB 📉
Infinitas Learning tracks grades and progress for 1.6 million learners on Postgres. When Postgres couldn't keep up with the analytics, they added ClickHouse Cloud. Ana Lacruz on what happened next 👇
Add fast analytics next to your Postgres, free with $300 in ClickHouse Cloud credits → clickhou.se/4s6Jct2
Watch Jerome and Ana's full customer story on running Postgres and ClickHouse together: clickhou.se/4yZuOoI
ClickHouse ran a filter query over 1 TB of in-memory data in 1.1 seconds on @nvidia Vera.
Using the standard binary, compute-heavy benchmarks also scaled nearly linearly across 176 CPU cores.
Read the results: clickhouse.com/blog/clickhou…
ClickHouse is building on NVIDIA Agent Knowledge Foundation.
We’re working with NVIDIA on using GPUs to accelerate data ingestion and analytical queries with cuDF. ClickHouse's SQL engine helps AI agents query enterprise data faster.
Learn more: blogs.nvidia.com/blog/enterp…
AI agents need to know your business to be useful.
At GTC Berlin, we’re adding NVIDIA Agent Knowledge Foundation to NVIDIA Agent Toolkit. It helps agents find relevant information, make predictions and help people decide what to do next.
OpenShell gives teams control over what agents can access and do.
Learn more: nvda.ws/4zJtVRh
Can ClickHouse act as your Iceberg catalog? In 26.10, experimentally, yes.
We'll show that, notebooks in the Web UI and SIMILAR TO on the release call, Thu 22 Oct at 4pm UK / 8am PT: c.house/2610ReleaseCall
Range joins that run instead of failing, LATERAL JOIN, and hash tables up to 2x smaller: 26.10 is a JOIN release.
See them on the release call, Thu 22 Oct at 4pm UK / 8am PT 🔗 c.house/2610ReleaseCall
Sonnet 5.5 on 201 analytics questions: a 68.7% pass rate, zero runs out of budget, a 13.7s median per answer and $10.39 for the whole run.
clickhou.se/4yYD7Bd
One agent run. Four kinds of data. Why four systems for one answer?
At @vercel Ship 2026, ClickHouse co-founder Yury Izrailevsky (@izrailevsky) explores data silos and how AI helps choose the data stack.
See how ClickHouse unifies your data. Start a free cloud trial in the comments. ⬇️
80–200 TB a day, in a single partition 📈
Jump Trading's logs are its record of every order and trade, and it has run them on ClickHouse for 7+ years. Arnaud Adant on why they chose it, at Open House San Francisco 2026 👇
Try ClickHouse on your own data, free with $300 in ClickHouse Cloud credits → clickhou.se/4s2Nhyc
Watch Arnaud's full talk on how Jump Trading uses ClickHouse with Iceberg: clickhou.se/3U0Qh1w
Finding an expensive query tells you what ran. Wait events tell you what it was stuck on.
Ask ClickHouse Agents: "What is my Postgres database waiting on, and what should I investigate next?"
Now in Query Insights for ClickHouse Managed Postgres: clickhouse.com/blog/postgres…
⚡ Meet ClickHouse’s experimental native TCP client for .NET. In a benchmark reading 1M rows, the HTTP client allocated 1.6 GB; TCP column reads allocated 6 MB. Both clients ship in ClickHouse.Driver.
clickhouse.com/blog/introduc…
Postgres's default huge_pages = 'try' falls back to 4KB pages silently. clickhou.se/4yiCO3b ClickHouse Managed Postgres uses 'on', and page tables stay at 0.5MB per connection instead of 31MB.
66 seconds → 2.5 seconds ⚡
@zoox searches its observability logs with ClickHouse. Vineet Ahirkar on the 27x speed-up they got from ClickHouse's new text indexes, at Open House San Francisco 2026 👇
Try the new text indexes on your own logs, free with $300 in ClickHouse Cloud credits → clickhou.se/4zscWCQ
Read about full-text search in ClickHouse, now generally available: clickhou.se/4ylstnd
Watch Vineet's full talk on observability at Zoox: youtube.com/watch?v=HLrJEJrs…
AI agents are putting new pressure on the data layer. They need fast, scalable infrastructure they can query efficiently.
Open ecosystems matter. And infrastructure has to keep pace with the way software is being built.
Full fireside chat with Aaron Katz (@ceo_clickhouse), Guillermo Rauch (@rauchg), Tristan Handy (@jthandy), and Lukas Biewald (@l2k) in the comments.
🔔 Managed ClickStack now supports tens of thousands of alerts, with built-in anomaly detection, a 24-hour preview to tune sensitivity, and better tools to find alerts and investigate why they fired.
clickhouse.com/blog/scaling-…
