Loading video...

Video Failed to Load

There was a problem loading this video. This could be due to a temporary network issue or the video might be unavailable.

Finally. I shipped a side-project. Introducing inbrowser. Pluggable AI architecture totally in the browser. site: repo: @inbrowser/model: on-device w/ transformers.js & webgpu. Cloud model proxies and OpenRouter BYOK flows. @inbrowser/agent: pluggable client-side agent architecture @inbrowser/resumable: pick up and resume across refreshes @inbrowser/relay: when you need a server, syncs resumable... show more

David East

25,316 subscribers

18,832 views • 4 months ago •via X (Twitter)

Science & Technology

Anya Rossi• Live Now

Private livecam show

10 Comments

Dave Geddes4 months ago

wait we're supposed to ship our side projects?!

Abhinav4 months ago

Sir, I really love your POV and work. Project IDX is great product (idk why it killed). BTW nice project.

Thibault Jaigu4 months ago

Cool! will try it out

tako4 months ago

Congrats!

晚晚4 months ago

全在浏览器里跑，调试应该挺爽

Modi4 months ago

the browser becoming a fake backend is still so funny to me

sijirano4 months ago

it's exactly what i needed for a side project. thanks!

David East4 months ago

@sijirano Music to my ears. I actually have two more packages landing that I think are the most useful bits. I would love to get your feedback on them

sijirano4 months ago

sure, can't wait to try them out!

temp.md4 months ago

Congrats on the ship. The resumable-in-browser bit is the sharp part: if a tab refresh or network drop does not erase the job, the browser starts feeling like a real agent runtime.

Related Videos

Introducing Phi-3 WebGPU, a private and powerful AI chatbot that runs locally in your browser, powered by 🤗 Transformers.js and onnxruntime-web! 🔒 On-device inference: no data sent to a server ⚡️ WebGPU-accelerated (> 20 t/s) 📥 Model downloaded once and cached Try it out! 👇

Introducing Phi-3 WebGPU, a private and powerful AI chatbot that runs locally in your browser, powered by 🤗 Transformers.js and onnxruntime-web! 🔒 On-device inference: no data sent to a server ⚡️ WebGPU-accelerated (> 20 t/s) 📥 Model downloaded once and cached Try it out! 👇

Xenova

117,724 views • 2 years ago

Introducing the OpenRouter MCP, live model intelligence right inside your agent Your agent builds and ships, but when it comes to choosing the right model for the right job, it guesses from 6 month old training data Watch it pick, price, and test the right model:

Introducing the OpenRouter MCP, live model intelligence right inside your agent Your agent builds and ships, but when it comes to choosing the right model for the right job, it guesses from 6 month old training data Watch it pick, price, and test the right model:

OpenRouter

265,172 views • 4 months ago

If your coding agent costs more than $2 per feature, read this. You're probably paying for 3 things you don't need: Opus reading every file in the repo. Opus making choices a $0.042 model can make. Simple tasks running on the most expensive model. Fix those 3 and the same agent drops from $6.42 to $2.00 per task. Full architecture with code below 👇

If your coding agent costs more than $2 per feature, read this. You're probably paying for 3 things you don't need: Opus reading every file in the repo. Opus making choices a $0.042 model can make. Simple tasks running on the most expensive model. Fix those 3 and the same agent drops from $6.42 to $2.00 per task. Full architecture with code below 👇

CyrilXBT

10,470 views • 1 month ago

It's finally possible: real-time in-browser speech recognition with OpenAI Whisper! 🤯 The model runs fully on-device using Transformers.js and ONNX Runtime Web, and supports multilingual transcription across 100 different languages! 🔥 Check out the demo (+ source code)! 👇

It's finally possible: real-time in-browser speech recognition with OpenAI Whisper! 🤯 The model runs fully on-device using Transformers.js and ONNX Runtime Web, and supports multilingual transcription across 100 different languages! 🔥 Check out the demo (+ source code)! 👇

Xenova

263,020 views • 2 years ago

Hermes Agent is now in the Cloud! Setup couldn't be simpler: pick a model and a server size. Two clicks and 60 seconds later, your agent is live. Running a team? Spin up agents for everyone at your org with granular access controls and unified billing, all from Nous Portal.

Hermes Agent is now in the Cloud! Setup couldn't be simpler: pick a model and a server size. Two clicks and 60 seconds later, your agent is live. Running a team? Spin up agents for everyone at your org with granular access controls and unified billing, all from Nous Portal.

Nous Research

1,555,707 views • 4 months ago

Connect a GitHub repo and a Google Drive folder in a single project, allowing read and write access across code and docs in the same conversation. Start on the web, pick right up in the app, and let remote plugins follow you across every surface.

Connect a GitHub repo and a Google Drive folder in a single project, allowing read and write access across code and docs in the same conversation. Start on the web, pick right up in the app, and let remote plugins follow you across every surface.

Google Antigravity

35,833 views • 8 days ago

Why have one AI agent handle everything when you can build a team? 🤝 Multi-agent architecture allows a main agent to spin up specialized sub-agents and handle complex tasks in parallel - making workflows faster and more efficient inside Google AI Studio. Check out the full I/O session: 🧵👇

Why have one AI agent handle everything when you can build a team? 🤝 Multi-agent architecture allows a main agent to spin up specialized sub-agents and handle complex tasks in parallel - making workflows faster and more efficient inside Google AI Studio. Check out the full I/O session: 🧵👇

Google for Developers

12,480 views • 5 months ago

I ran the same task on Claude Code and DeepSeek's new agent harness. One cost $150. The other cost $2. Today we're launching (AgentSky), the "OpenRouter for Agents" — one API → Claude Code, Codex, DeepSeek, Kimi, OpenCode, and every major agent in the cloud. And Agent Playground on top: race them on your own task, with your real tools (GitHub, Gmail, more), side by side in a browser: time, cost, tokens burnt. Guess which one was $2.

I ran the same task on Claude Code and DeepSeek's new agent harness. One cost $150. The other cost $2. Today we're launching (AgentSky), the "OpenRouter for Agents" — one API → Claude Code, Codex, DeepSeek, Kimi, OpenCode, and every major agent in the cloud. And Agent Playground on top: race them on your own task, with your real tools (GitHub, Gmail, more), side by side in a browser: time, cost, tokens burnt. Guess which one was $2.

Xiaoyin Qu

2,227,612 views • 2 months ago

Introducing: a coding agent (Pi) running entirely in your browser using a 2B model on WebGPU 🤯 MiniCPM5-2B + Pi, powered by Transformers.js + WebGPU + 4-bit ONNX weights. All previous attempt to create this failed but MiniCPM5 seems to make it usable. Available now on Hugging Face 👇

Introducing: a coding agent (Pi) running entirely in your browser using a 2B model on WebGPU 🤯 MiniCPM5-2B + Pi, powered by Transformers.js + WebGPU + 4-bit ONNX weights. All previous attempt to create this failed but MiniCPM5 seems to make it usable. Available now on Hugging Face 👇

Victor M

90,360 views • 1 month ago

Jev and OpenRouter are now live on Monid with 2,000 tools, your agent picks what it needs and Jev speeds the work up 30x across lead scoring, viral hook scanning, fundraising research and SEO audits.

Jev and OpenRouter are now live on Monid with 2,000 tools, your agent picks what it needs and Jev speeds the work up 30x across lead scoring, viral hook scanning, fundraising research and SEO audits.

0xMarioNawfal

40,707 views • 1 month ago

Introducing AltSociety Chat. Access top AI models like ChatGPT, Claude, Gemini, Grok, and Perplexity sharing the same workspace - and the same memory. Switch models with ease. Compare answers side-by-side. Retain context across every model switch. A single interface. A unified workflow. Your AI stack, finally connected.

Introducing AltSociety Chat. Access top AI models like ChatGPT, Claude, Gemini, Grok, and Perplexity sharing the same workspace - and the same memory. Switch models with ease. Compare answers side-by-side. Retain context across every model switch. A single interface. A unified workflow. Your AI stack, finally connected.

AltSociety AI

11,165 views • 11 months ago

Cool it on the tab hopping 🐇 Reviewing agent code usually means switching tabs. The GitHub Copilot app puts the diff, terminal, and browser side by side to check, run, and preview.

Cool it on the tab hopping 🐇 Reviewing agent code usually means switching tabs. The GitHub Copilot app puts the diff, terminal, and browser side by side to check, run, and preview.

GitHub

93,652 views • 1 month ago

Introducing SmolVLM 256M (& 500M): The world’s smallest multimodal model. Designed for efficiency and perfect for on-device applications! 🔥 It’s so small, it can even run 100% locally in your browser on WebGPU! 🤏 Powered by Transformers.js! ⚡️ Try it out yourself! 👇

Introducing SmolVLM 256M (& 500M): The world’s smallest multimodal model. Designed for efficiency and perfect for on-device applications! 🔥 It’s so small, it can even run 100% locally in your browser on WebGPU! 🤏 Powered by Transformers.js! ⚡️ Try it out yourself! 👇

Xenova

25,302 views • 1 year ago

Cloud agents and automations now support multi-repo environments. Configure a single environment with all the repos an agent needs, and reuse it across sessions.

Cloud agents and automations now support multi-repo environments. Configure a single environment with all the repos an agent needs, and reuse it across sessions.

Cursor

47,600 views • 6 months ago

The right model depends on the task. NVIDIA NeMo Switchyard helps developers route each agent workflow step across a chosen model pool based on their own quality, latency and cost criteria. Kari Briski joins MTS to explain why agent workflows need model routing.

The right model depends on the task. NVIDIA NeMo Switchyard helps developers route each agent workflow step across a chosen model pool based on their own quality, latency and cost criteria. Kari Briski joins MTS to explain why agent workflows need model routing.

NVIDIA

97,320 views • 2 months ago

Introducing Agent Baseline: a vendor-neutral reference architecture for safely building, deploying, and operating AI agents in enterprise environments. Created with Snyk and Keycard, this open-source framework sets the minimum standard for agent safety:

Introducing Agent Baseline: a vendor-neutral reference architecture for safely building, deploying, and operating AI agents in enterprise environments. Created with Snyk and Keycard, this open-source framework sets the minimum standard for agent safety:

Docker

18,594 views • 3 months ago

✨ Introducing Gemma 3n, available in early preview today. The model uses a cutting-edge architecture optimized for mobile on-device usage. It brings multimodality, super fast inference, and more.

✨ Introducing Gemma 3n, available in early preview today. The model uses a cutting-edge architecture optimized for mobile on-device usage. It brings multimodality, super fast inference, and more.

Google AI Developers

125,354 views • 1 year ago

Following this week's frontier video model launches, we're opening up early access to something we've been building. Introducing fal Agent. A creative partner for working across the best image, video, and 3D models.

Following this week's frontier video model launches, we're opening up early access to something we've been building. Introducing fal Agent. A creative partner for working across the best image, video, and 3D models.

fal

104,325 views • 3 months ago

Introducing Agent Effectiveness. Measure Factory usage across cycle time, work priorities, and shipped artifacts, so you can actually see what your AI spend produces.

Introducing Agent Effectiveness. Measure Factory usage across cycle time, work priorities, and shipped artifacts, so you can actually see what your AI spend produces.

Factory

61,390 views • 3 months ago

AI agents can now connect to real cloud devices🔥 agent-device now supports BrowserStack and AWS Device Farm. Test, inspect, and debug on real devices in cloud instead of stopping at local simulators. » agent-device connect browserstack » agent-device connect aws-device-farm

AI agents can now connect to real cloud devices🔥 agent-device now supports BrowserStack and AWS Device Farm. Test, inspect, and debug on real devices in cloud instead of stopping at local simulators. » agent-device connect browserstack » agent-device connect aws-device-farm

Michał Pierzchała

12,743 views • 4 months ago