Generative UI and In-App Agents with assistant-ui

Oct 4, San Francisco luma.com/build-agents

It's hack time! Join and build your own personal agent! Full day hackathon hosted by the agent stack w/ food trucks, credits for hackers, six-figure prizes, after-party, and of course, plenty of time to hack 🤖 Join @neondatabase, @mastra, @ExaAILabs, @usekernel, @assistantui, @executorsh, @flydotio, and @agentmail for Build Personal Agents Hack! luma.com/build-agents

Introducing riftri (riftri.dev) - real Git worktrees ( native COW ) that don't each cost you a full checkout. Spin up 10 worktrees for parallel agents or branches, and the unchanged files are shared at the filesystem level instead of copied.

still no @abhiaiyer

This was pretty incredible to be part of. Thanks everyone who helped yesterday. We really couldn't have done it without you.

OSS projects are the backbone of the industry, and we've previously committed over $1M cash to support them. Now, we're committing $10M to help protect the projects that do so much. Keep an eye on our live commitment tracker: coderabbit.ai/oss#live-oss-c…

“AI coding gives everyone 80% of the result for 10% of the effort. That 80% is no longer your edge. It’s the commodity. The remaining 20% - taste, judgment, edge cases, review - is where all the alpha lives.” Truth be spoken: The best engineers don't work less. In fact, we’re all suffering from AI psychosis right now, but we also ship 10x more. Really enjoyed my conversation with @simonfarshid, Founder & CEO of @assistantui, on our latest convo of  @coderabbitai 's The Merge.

OpenUI now renders within @assistantui Your agent can now generate interfaces or take structured input via real forms - all inside the most loved Agent UI framework. @KashyapVisharad cooked with this one! assistant-ui.com/docs/tools/…

I'm exploring what's next =) Building @synthesiscoca w/ @ammirsm is one of the most meaningful experiences of my life — from contributing to @DSPyOSS to @ycombinator S24, raising from amazing folks, pivoting, and publishing a the largest eval of AI on evidence synthesis. Now I'm looking for somewhere where I can leverage all my zones of genius to make an impact. I've made products used by 200M+ people Built OSS with almost 100M downloads And raised millions of dollars My creative antennae are attuned to finding "why doesn't that exist yet?" opportunities and executing on them before others. I'm technical enough to go deep on what’s being built & previously built products zero to one — but also genuinely good with people; communicating clearly, building trust, and understanding users. This is where I thrive. My skills are a rare mix right now & they're in demand more than ever before. I can't wait to get to work at a larger scale. I'm especially excited to work more with founders and agents, from GTM to research. If you're building something ambitious and think we should talk, my DMs are open! Here's what I've made lately:

hi! please meet givemeanode.com! it's a new autoresearch product from the san francisco compute company. try asking it to "download insert-model-here off huggingface and optimize it 4x and don't stop until it's done." let it run for days. you know those massive grab bag of black magic tricks others do? we want to let you do that too, for cheap. lets let anyone train models. it's backed by a big, fair queue that makes sure nobody can just buy out the whole thing, so there's always space for experiments. struggling to get gpus? try here <3 it's not just a business promise, it's how the product works! it doesn't require you to sign some big long reserved contract for years, where you're betting your balance sheet on your gpu bill, because it's backed by the liquidity of sfcompute. it's built for ridiculous redundancy & reliability. jobs can die and restart from the same point & the scheduler keeps headroom for you. even the platform itself going down does not stop your agent, because we've built ticketing straight into the mcp that lets your agent recover from outages. we've taken the thing offline, started it up again, and agent-supervised training runs just keep on going. it's got platform-native support for grant programs, meaning you can buy capacity, and sponsor other accounts. it's got s3 compatible storage, hugging face integrations, scratch disks & persistent volumes, clock locking, ncu support, metrics, logs, traces, checkpointing, and a whole grab bag of other stuff. but you shouldn't worry about that. let your agent sweat those details. we'd love for you to try it, DM me for some GPU credits if you'd like!

I think Claude Max usage limits got quadrupled? I seem to get roughly $1200 of fable/week (previously $300/week)

How we helped @assistantui turn landing-page visitors into installs. 20% of playground users found a working POC and downloaded the code. Here's how 👇

Moving for work? One of the hardest parts is figuring out which visa you even qualify for. We built a free tool that tells you in ~30 seconds. Drop in your location, get some options, with timing, cost, and links to official sources. No login. Try it @ gullie.io/visa-checker

July has been suspiciously productive for me

Vision is more token efficient than text input! Why? …

everyone’s sharing their chance to join cursor. here is mine!

box

At HumanLayer, we’re on a mission to solve the AI slop code problem. In 2025 we open-sourced our Research, Plan, Implement framework, now deployed inside fortune 500s like Block and Uber - places where shipping slop is just not an option And that was just the beginning. Today, we’re opening access to HumanLayer - an Agentic IDE, collaboration platform, and building blocks for your software factory. HumanLayer enables engineers solving hard problems in complex codebases to: > move 2-3x faster across the entire SDLC (not just coding) > maintain rigorous standards for system architecture and program design Hundreds of engineers at companies of all sizes are already using HumanLayer to ship fast without sacrificing quality. I'm excited to invite you to try humanlayer today at humanlayer.com, and I'm even more excited to see what you build. @0xblacklight and I are deeply grateful to our team, our customers who give us so much incredible energy and feedback, our investors who have always been in our corner, and our friends and family who have supported us along this crazy journey if you're a staff or principal engineer trying to make AI coding work at scale for your team, we'd love to hear from you as @swyx likes to say - let's make this the year of no more slop