🛠️ June 17: AGI House x Bright Data Real-Time Agents Build Evening, w/ @livekit, @agi_inc, and @GuildAI. Build agents on the live web. Bright Data's new Scraper Studio is free for builders — apply now, demo Wednesday. app.agihouse.org/events/real…

Orchestrate low latency tele-operation and multi-model remote inference with ease using LiveKit Portal.

Taking @zoox to the office has been great. Super roomy and comfortable compared to a normal car.

Introducing the LiveKit C SDK. Realtime audio, video, and data tracks for C apps, with the same low-latency transport our other clients use. Built for the C stacks behind robotics, autonomous vehicles, and high-performance media pipelines. livekit.com/blog/livekit-cpp…

@pham_blnh, @chenosaurus and Jacob’s Desktop Robot Assistant looks simple, but the architecture is wild. To move a candy bar, it orchestrates: Voice Agents, VLMs for spatial awareness, ACT policies, and Momo Act 2. The models are distributed across laptops in the room and an H200 server in Finland, executing physical tasks over the internet with real-time, ultra-low latency.

Best way to kick off a week with the @LiveKit robotics team: win the @southpkcommons Embodied AI Hackathon the weekend before. Over 48 hours, we really cooked something special. Distributed low latency inference (VLMs, ACT, MolmoAct 2), teleop, voice agent orchestration, all powered by @LiveKit.

check out my claude knob @trq212 github.com/pham-tuan-binh/cl…

what can i say, my models always get the best data there is so they always work first try built this to test remote hg-dagger style data collection, can’t wait to share the tutorial

collect data remotely using @livekit, infer remotely using @livekit excited for what’s to come, handling transport layer for robots should be as easy as setting up a call

You can now play Doom as a world model inside your browser. I’m happy to finally release learning world model learning part 3. pham-tuan-binh.github.io/lea… This time we finally go through the entire pipeline and train a “playable” world model. Unlike previous articles, in this one, we’ll go through some more practical notes like: > How to train a model cheaply using spot instances > Identifying when low loss is bad > Loading data from large datasets Hope you like this one. Thanks to my readers for pressuring me into releasing this in time.

used @livekit @LeRobotHF @rerundotio to destroy a wasp nest on my balcony today mission successful, now i can drink my coffee in peace full video in comment

i bet you haven't seen a SO101 mounted on a wall like this before if you want to do the same, here is LeSlider: github.com/pham-tuan-binh/le… i built it cause i wanted something that can cover my whole desk for tasks like organizing and cleaning i originally wanted to have a belt system like what 3D printers have, but i was too lazy and used a pinion/track with another sts3215 so: > the extra motor shares the same bus as the rest of SO101 > you can have arbitrary length of track > really cheap and easy to assemble and control it turned out better than expected with this, i'm gonna train a model to pick random stuff up across my table and put it into a bin at the end of table (realistically using yolo to scan table, two policies, one for picking up objects, one for dropping)

DJI unveiled its new FC200 transport drone. Standout feature: a four-drone coordinated formation that has a max payload of 600 kg. This will change lots of industries.

This is cool

Since livekit-wakeword release, the number one question we’ve been asked is if we support wake word in other languages. The answer is yes. By leveraging VoxCPM2 from @OpenBMB, we can generate samples in 30 languages and train on them. All local. All in a single command. All open-source.

Our newest model, π0.7, has some interesting emergent capabilities: it can control a new robot to fold shirts for which we had no shirt folding data, figure out how to use an appliance with language-based coaching, and perform a wide range of dexterous tasks all in one model!

We launched livekit-wakeword, an open-source library that lets you train a custom wake word model from scratch with a single command. It handles synthetic data generation, augmentation, training, and ONNX export all in one shot.

@chenosaurus and me won third place at nvidia cosmos cookoff✌️

if you have tried to train a wake word model before, you know the pain today we are open sourcing livekit-wakeword, a tool that lets you train production-grade wake word models with a single command on any platform compared to openwakeword, livekit-wakeword achieved dramatically better results across every metric: > 100× fewer false positives per hour > 60× lower detection error > 86% vs 69% recall this is thanks to our improvements with the data generation pipeline (diverse samples and config options), training pipeline (focal loss and label smoothing) and model architecture (attention) a big bonus: models trained with livekit-wakeword are fully backward compatible with openwakeword, so you can drop in our wake word models into your existing @home_assistant setup or any oww project check it out here github.com/livekit/livekit-w…