
Launch post: urun.sh/blog/introducing-sen… Python and TypeScript SDKs: github.com/urun-sh/sense-sdk

Real-time AI model APIs that run together, for voice agents, live video, and avatars.

Launch post: urun.sh/blog/introducing-sen… Python and TypeScript SDKs: github.com/urun-sh/sense-sdk

uRun is open to everyone, starting with Sense: a decision model that follows live audio and video and answers questions like "is the user done speaking?" up to 12.5 times per second. Free credits to start. We're live on Product Hunt today too 👇️ producthunt.com/posts/urun

Early Model API benchmarks: same Qwen 3.8 27B, same 16 requests. uRun: 115 to 126 output tokens/sec on every request OpenRouter: 94 to 778 Steady throughput first, and now we're tuning it up. urun.sh/blog/early-model-api…

Huge congrats to our friend @rissa_cao and the @FishAudio team on Live 3! A voice model that can say “mm-hmm” while listening, but knows when to stop at “wait, actually...” is a big step towards more natural, real-time conversations. Go give it a try! 🚀 x.com/rissa_cao/status/21202…
Introducing @FishAudio Live 3: a full-duplex voice model that listens, says "mm-hmm," and knows when to shut up. Enterprise? Book a demo for your free custom agent: s.fish.audio/vxhgs6 Reply with your use case - we'll build it free for the first 1,000 people.

Model APIs are live on uRun. In the demo, we plug Qwen 3.8 27B into OpenCode and chat with it over industry-standard chat completions. Working internally, rolling out worldwide. Our waitlist gets access first: urun.sh/contact More: urun.sh/blog/model-apis-are-…

almost everything in ai is still optimized for stateless request and response. that falls apart the second you want video or audio a user can interrupt and steer. @keeganmccallum3 on tank talks, on why the state belongs on the server 👇️
How do you scale 500 to 9,000 H100s in six hours!! That's what it took to keep @DreamLabLA Dream Machine standing when it went viral. Half a million videos in 12 hours. @keeganmccallum3 is now building @urunml for the interactive AI wave. New Tank Talks [links below]

How do you scale 500 to 9,000 H100s in six hours!! That's what it took to keep @DreamLabLA Dream Machine standing when it went viral. Half a million videos in 12 hours. @keeganmccallum3 is now building @urunml for the interactive AI wave. New Tank Talks [links below]

$50 buys a day of continuously generated video. plenty of engineers spend that on coding tokens in an hour. our ceo @keeganmccallum3's @aiDotEngineer talk on what that changes is live. thanks @swyx + team 🙏 new design partners: our dms open 👋 youtu.be/Xln-On3syJk

fast mode costs 2.5x and it's still waitlisted. the market is paying multiples for presence, not batch jobs. @keeganmccallum3 on why we make that the default 👇
OpenAI and Anthropic charge ~2.5x for fast mode. Even then, OpenAI downgrades priority traffic and Anthropic runs a waitlist. That's the tell: a continuous, responsive session is worth multiples of a job you fire off and check on later. At @urunml build for that by default.

everyone with GPUs is being told to build a token factory. same tokens, same price war, margin competed away. the interesting bet is the workloads nobody else can serve. @keeganmccallum3 on why 👇
Everyone with GPUs is being told to build a token factory and price on output. Reasonable advice. Also a race to the bottom. At @urunml we went the other way: serve the hardest workloads first, the ones nobody else can. That's where the margin actually is.




thank you to everyone who gave us their monday night 🥂 one table at @GwenLA during @SIGGRAPH week with studio pipeline leads, vfx supervisors, founders building interactive video, and the researchers they all cite. the kind of conversations that need a dinner table, not a booth. grateful you came. we left feeling full (literally and metaphorically). 🥂


every app you've ever used is pixels rendered to a screen. now there are models that can generate those pixels in real time, in response to you. @keeganmccallum3 on where that goes 👇
Everything you've ever done on a computer is you interacting with a video. We just never had models that could render those pixels in real time, in response to you. Now we do. You can speak an experience into existence and interact with it as it renders with @urunml.