VP @databricks, Founder @neondatabase. Building Lakebase Postgres for AI-native world
San Francisco, CA
Joined June 2010
- Tweets5.4K
- Following2.2K
- Followers13.6K
- Likes7.8K
Pinned Tweet
There are two unclimbable mountains in database world: 1 Combined transactional/analytical processing 2 true multi-master scale out
We are making significant progress on both in Lakebase
Nikita | Scaling Lakebase Postgres retweeted
Lakebase will mark a phase shift in database technology! It'll enable LTAP, true multi-master, etc.
It all changes with agents and we feel we are in a unique point in time where we can be a lot more ambitious in taking on giant systems project with agentic software production.
1
2
731
Nikita | Scaling Lakebase Postgres retweeted
Postgres is a streaming database.
neon.com/docs/realtime/overv…
postgres might seem like a strange choice for a streaming database.
if you compare postgres directly to something like kafka, in terms of pure write throughput, you're going to do about 2x worse, because you pay the penalty of the WAL on postgres. on my local SSD, optimized 64kb inserts are about 300 MB/s on Postgres, and about 600 MB/s on Kafka (with ack waits).
but maximizing disk throughput is very unlikely to be your biggest problem. your biggest problem is infra component bloat. it's the number 1 problem we try to avoid with the open source version of Hatchet. the only strict dependency should be Postgres, and we're going to do everything we can to optimize the shit out of it until we can't optimize it anymore.
so we built durable streams on Postgres, so users don't need to add any additional infra components to their self-hosted Hatchet stack to benefit from durable streams.
Amazing launch. Congratulations @myprasanna! Excited to be an investor and a friend.
Today we're launching @vorflux 2.0: AutoBots, 24x7 coworkers that live in Slack.
I previously co-founded @Rippling, now $10B+, engg team of 1000s. Engg changes crazy fast now.
IDE autocomplete > CLI > Cloud agents > multi-player slack agents
Models deliver predictably now. Bottleneck to parallelism is to initiate, keep track and ping the right people for approvals.
Hire from our directory of opinionated AutoBots or make a new one with a goal. Bring your Codex/Claude Code subscriptions and Vorflux is practically free.
We recently closed a $15M seed round for @vorflux backed by @ycombinator, @peakxvpartners, @alliancedao, along with incredible partners including @parkerconrad, @immad, @typesfast, @jake_zeller, @balajis, @nivi, @metakovan, @lmrankhan, @nikitabase, @0xrwu, @ayushjaiswal, @mattshumer_, @eshamanideep, @sreeramkannan, @dvcoolster, @nusimow, @TeddySolomon11, @ashtoncofer, @rvivek, and others.
Lmk which autobot you’d like to try and we’ll double your credits to try.
Chapters:
0:00 Introducing Vorflux 2.0
0:22 From manager to director
0:44 How an AutoBot works
1:04 Cloud setup
1:25 On-call AutoBot
1:42 Project manager AutoBot
2:03 Customer experience AutoBot
3:01 Designer AutoBot
3:52 Social AutoBot
4:51 Open and frontier models
5:23 Always-on agents
3
14
1,406
Running on @neondatabase
Agents on Kylon have now completed over 5 million transactions. That's about 50,000 hours of manual work.
Bring your team, Claude Code, and Codex into one shared workspace where agents can handle research, marketing, sales, and operations alongside your people.
With access to 3,000+ tools, from patent databases to Meta Ads, your agents can work together across your business.
Comment with your use case for your first month free.
Deploy from Cursor and the agent provisions Postgres for you.
Powered by Neon and Vercel.
Nikita | Scaling Lakebase Postgres retweeted
Deploy apps in one click with @cursor_ai.
• No account to create
• No deployment configuration
• Database provisioning included
Built on Vercel for Platforms → vercel.com/for/platforms
Nikita | Scaling Lakebase Postgres retweeted
Agents can set up a Neon Function themselves, but they spend tokens reading docs first.
The Neon Function Registry gives them a working template instead, added with one command.
Below are a few of our favorites:
neon.com/blog/save-tokens-wi…
Co-sign. You should also mention flexibily. S3 is fundamentally multi-tenant and this should carry through the rest of the design when building the memory hierarchy.
It’s memory hierarchy all the way down.
S3 is the future, the world’s disk. It’s not the only storage medium, nor should it be (again, memory hierarchy).
But there’s hot and cold data, and the well-designed architectures will respect this.
Whether it be L1/L2/L3 and main memory, or NVMe and HDD, or pure replication and erasure coding.
The best designs exploit the memory hierarchy.
6
34
3,251
MCP on @neondatabase is very good and keeps getting better. We added a search_docs tool powered by Lakebase search too.
MCP is winning. Tool calls on the Neon MCP doubled in the last 6 weeks and this week, we're shipping support for MCP 2.0.
The 2026-07-28 spec update is a huge win for MCP and makes it much easier to host MCP servers on serverless infra. We added support for MCP 2.0 and also retired our SSE endpoints.
We wrote about the changes, our MCP usage numbers, and the spec update: neon.com/blog/is-mcp-good-ye…
Nikita | Scaling Lakebase Postgres retweeted
Neon Realtime is already pretty fast. But we're going to make it so much faster!
Nikita | Scaling Lakebase Postgres retweeted
I built Crew: AI teammates for your desktop. Main purpose was to learn how @bot actually worked.
Each bot has its own job, its own chat and its own screen on a cloud computer. They message each other and hand off work, and you watch them do it.
Built with:
@e2b for the cloud computer
@neondatabase for Postgres and the AI Gateway
@triggerdotdev for running the bots
@aisdk for the model calls
How it works: avikmukherjee.com/blog/crew
Code: github.com/Avik-creator/crew
It's important to understand what this unlocks. We are calling it "playable" environments.
Where agents can instantly load up many exact copies of production. What else is playable? Chess, Go, Starcraft, Math (Lean). All of cloud software is next.
h/t @kylemathews started writing about it here tanstack.com/blog/tanstack-d… more playable environments coming from Neon soon
