assistant-ui

Open Source React Library for AI Chat (YC W25)

[Andre Landgraf @andrelandgraf]

Congrats again to all the winners! Build Personal Agents Hack was a blast!

250 hackers · $280k in prizes · dying Wi-Fi · dozens of submissions · 3 winning teams · 2 side quests

Thanks everyone for joining and inspiring us with your amazing agent projects!

[Simon Farshid @simonfarshid]

Tonight I'm MCing a fireside chat with @MichaelArnaldi, creator of Effect, on the @coderabbitai rooftop in SF 🇺🇸

What should I ask him?

Luma: https://t.co/k57hYIOEdV

[assistant-ui @assistantui]

Save the date... This Sunday will be massive!

[Neon @neondatabase]

Build Personal Agents Hack · Sun, Oct 4 · San Francisco

Total prize pool: $279,500

+ $1,625 in credits for every hacker

RSVP: https://t.co/Gn0A0KmM4u

[KiNFiSH @KinfishT]

learn more

- Website and docs: https://t.co/uxP2afeEew
- Github: https://t.co/R1BvJUyNwf

[assistant-ui @assistantui]

you should check this out!!.

https://t.co/TwJkp3sFqJ

[KiNFiSH @KinfishT]

Introducing Jevia:

It’s something we built and use internally: an open-source, local-first adaptive and outcome-based model router for AI coding harnesses.

[assistant-ui @assistantui]

try it out ;)

[KiNFiSH @KinfishT]

Try Jevia:

Website and docs: https://t.co/uxP2afeEew
Source: https://t.co/R1BvJUyNwf

[assistant-ui @assistantui]

This will be epic. Can't miss.

[Michael @MicOgundare]

The Multiplayer Coding Hackathon with @coshellhq and @assistantui @freestyle_dev @Wefunder
Sat Oct 3, SF. Free.

Teams of 2 to 5 build in one shared drive, steering live agent sessions together.
Sign up at:
https://t.co/Xc9ONNKv3q

[assistant-ui @assistantui]

we want to see you there ;)

[Neon @neondatabase]

Oct 4, San Francisco

https://t.co/Gn0A0KmM4u

[assistant-ui @assistantui]

real worktrees. 87% less disk. nothing to configure. native COW ( copy on write ) sharing.

[KiNFiSH @KinfishT]

Introducing riftri (https://t.co/vsBwkNZo8y)

- 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.

[assistant-ui @assistantui]

@KinfishT those are bold numbers. and nothing to set up on the agent side. it just works.

[Hendrik Krack @HKrackDev]

“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.

[Thesys @thesysdev]

Building with @assistantui? OpenUI now has a dedicated integration.

Your agent can stream OpenUI Lang interfaces directly inside the conversation, from cards, tables, and charts to forms and choices that return structured input and continue the thread.

OpenUI generates the interface; assistant-ui provides the chat shell.

https://t.co/4G2kcwUBba

[Rabi Shanker Guha @rabi_guha]

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!

https://t.co/0S39W6O8xM

[Peter Petrash @petekp]

15 reasons why you should just use @assistantui

[Axel @AxelVincent_]

Here is the easiest way to implement your own harness for any vertical; it's so easy it feels like cheating :
- Typescript backend with https://t.co/TRibF2oTlZ from @mastra
- Typescript frontend with https://t.co/6ssYom7Cp7 from @assistantui

[Simon Farshid @simonfarshid]

crossed a mil in weekly downloads!!! come join us, we’re hiring!

[Simon Farshid @simonfarshid]

lfg

[tokens& @tokensandai]

most AI apps still don't use the full multimodal stack.

vision, audio, real-time processing. all largely untapped

we got you access to the latest @GoogleDeepMind models. if you've been wanting to build multimodal agents, this one's for you

🏆 $45K+ in prizes (up to $25K in credits alone)
📅 saturday march 28 · san francisco

apply below 👇

[Simon Farshid @simonfarshid]

modelpedia -- an open source catalog of all models across providers

[Simon Farshid @simonfarshid]

Today, we are launching the redesigned assistant cloud Dashboard, with improved analytics and thread management