Загрузка видео...

Не удалось загрузить видео

На главную

Your context window is fixed. Your chat is not. 📉 TanStack AI shrinks what the model sees and leaves your transcript alone allowing for infinite compacting chats. You pick your compaction strategy! npm i @tanstack/ai-compaction

tan_stack's profile picture

TANSTACK

66,309 subscribers

23,182 просмотров • 2 месяцев назад •via X (Twitter)

Наука и технологии
LIVE

Anya Rossi• Live Now

Private livecam show

Комментарии: 0

Нет доступных комментариев

Здесь появятся комментарии из оригинального поста

Похожие видео

TanStack AI now supports Cloudflare as an official adapter! Connect to your gateway via bindings, api key or expose it to the OpenAI adapter directly! npm i @tanstack/ai-cloudflare
0:35

TanStack AI now supports Cloudflare as an official adapter! Connect to your gateway via bindings, api key or expose it to the OpenAI adapter directly! npm i @tanstack/ai-cloudflare

TANSTACK

22,553 просмотров • 2 месяцев назад

TanStack AI 1.0 is officially stable! 🎉 Build chat, voice, image generation, agents, and harnesses into your apps, with your choice of models, UI framework, and infrastructure. Your AI, your way.
1:40

TanStack AI 1.0 is officially stable! 🎉 Build chat, voice, image generation, agents, and harnesses into your apps, with your choice of models, UI framework, and infrastructure. Your AI, your way.

TANSTACK

97,117 просмотров • 13 дней назад

TanStack AI 🤝Angular Today we have released an official Angular adapter for TanStack AI! 🚀 Try it out in your Angular apps today and find the docs here:
0:45

TanStack AI 🤝Angular Today we have released an official Angular adapter for TanStack AI! 🚀 Try it out in your Angular apps today and find the docs here:

TANSTACK

11,461 просмотров • 4 месяцев назад

Compaction is death Repo Prompt turns deep orientation and planning into a single tool call, so your agent can ship complete features in one context window And when compaction does hit, Context Builder re-anchors them efficiently Big updates soon, but here's how it works today
9:35

Compaction is death Repo Prompt turns deep orientation and planning into a single tool call, so your agent can ship complete features in one context window And when compaction does hit, Context Builder re-anchors them efficiently Big updates soon, but here's how it works today

eric provencher

38,616 просмотров • 9 месяцев назад

You might've seen recently that Docker released support for microVM sandboxes for agents. We just shipped an adapter for it directly in TanStack AI! Run your agents inside of Docker Sandboxes with TanStack AI today.
0:30

You might've seen recently that Docker released support for microVM sandboxes for agents. We just shipped an adapter for it directly in TanStack AI! Run your agents inside of Docker Sandboxes with TanStack AI today.

TANSTACK

20,254 просмотров • 2 месяцев назад

Hosted skills are now supported in TanStack AI. 🧩 Pass { skills } to your code-execution tool, TanStack AI lifts them into container skills and auto-wires the beta headers. Anthropic + OpenAI. 🚀
0:30

Hosted skills are now supported in TanStack AI. 🧩 Pass { skills } to your code-execution tool, TanStack AI lifts them into container skills and auto-wires the beta headers. Anthropic + OpenAI. 🚀

TANSTACK

14,549 просмотров • 5 месяцев назад

We just released a new version of TanStack AI! 🚀 In today's release we have added client/server context for tools and middleware. Plug it into your useChat/chat and have it available, fully typesafe out of the box. 🔥
0:34

We just released a new version of TanStack AI! 🚀 In today's release we have added client/server context for tools and middleware. Plug it into your useChat/chat and have it available, fully typesafe out of the box. 🔥

TANSTACK

33,646 просмотров • 5 месяцев назад

Your AI stream is a black box. 🕳️ One flag in TanStack AI and every chunk, middleware hook, and tool call prints itself for easy debugging. 🔥 No OpenTelemetry. No dashboard. No platform. chat({ ..., debug: true }) 🚀 Blog 👇
0:45

Your AI stream is a black box. 🕳️ One flag in TanStack AI and every chunk, middleware hook, and tool call prints itself for easy debugging. 🔥 No OpenTelemetry. No dashboard. No platform. chat({ ..., debug: true }) 🚀 Blog 👇

TANSTACK

33,891 просмотров • 6 месяцев назад

Your AI agents are running blind in prod? One line of otelMiddleware() and every chat, iteration, and tool call lands in your OTel backend with full GenAI semconv attributes. Vendor-neutral. Optional peer dep. Already shipped on TANSTACK ai.
0:22

Your AI agents are running blind in prod? One line of otelMiddleware() and every chat, iteration, and tool call lands in your OTel backend with full GenAI semconv attributes. Vendor-neutral. Optional peer dep. Already shipped on TANSTACK ai.

TANSTACK

16,944 просмотров • 6 месяцев назад

The TANSTACK form devtools are here!!! 🔥🎊 New addition to the TanStack devtools family is finally out! 🚀 Debug your forms like never before! 🤖 Check out the docs how to add them to your project here:
0:22

The TANSTACK form devtools are here!!! 🔥🎊 New addition to the TanStack devtools family is finally out! 🚀 Debug your forms like never before! 🤖 Check out the docs how to add them to your project here:

Alem Tuzlak 🇧🇦

45,190 просмотров • 1 год назад

Own the algorithm or be owned We live in a world where what we see + experience is not determined by us Time for that change Your unique actions, preferences + skills should determine what you see and do Your AI, your context, your rewards NEAR AI x ConsumerFi 🤝
0:48

Own the algorithm or be owned We live in a world where what we see + experience is not determined by us Time for that change Your unique actions, preferences + skills should determine what you see and do Your AI, your context, your rewards NEAR AI x ConsumerFi 🤝

Jon Cooks

20,733 просмотров • 1 год назад

TANSTACK Start is stable at 1.0! Come try it out! Docs: TanStack Start + Sandboxes: We've overhauled support to make getting started smooth. We want your full TanStack app running fast. Frontends, APIs, DBs, and Sandboxes.
0:47

TANSTACK Start is stable at 1.0! Come try it out! Docs: TanStack Start + Sandboxes: We've overhauled support to make getting started smooth. We want your full TanStack app running fast. Frontends, APIs, DBs, and Sandboxes.

Railway

23,180 просмотров • 23 дней назад

Your AI chat vanishes on every page reload? 🔄 TanStack AI just shipped a persistence option: pass one adapter and conversations hydrate on load, save on change, clear on reset. localStorage, IndexedDB, anything.
0:45

Your AI chat vanishes on every page reload? 🔄 TanStack AI just shipped a persistence option: pass one adapter and conversations hydrate on load, save on change, clear on reset. localStorage, IndexedDB, anything.

TANSTACK

25,395 просмотров • 5 месяцев назад

🚀 Global Launch: Jarvix, Your Context OS is now live! Meet the next generation of personalized AI built around your context, your taste, and your way of thinking. #JarvixOS transforms how you work with AI by understanding your patterns, carrying your context across agents, and helping you move from ideas to action. Step into a new era of AI collaboration: • Discover your AI-native archetype • Build your personal AI model from your evolving AI interactions • Never start from zero - your context moves with you across sessions • Coordinate Codex, Claude Code, Gemini, Hermes, OpenClaw, and more as one connected AI team. • Turn insights into your next move, with you always in control Instead of adapting yourself to every agent, Jarvix carries the context you choose, helps you understand what it reveals, and brings the right agents together when you decide to act. Your AI tools shouldn’t work like separate assistants. They should work like one team. That’s the future of AI: Not more agents. One shared context. One Jarvix.
1:34

🚀 Global Launch: Jarvix, Your Context OS is now live! Meet the next generation of personalized AI built around your context, your taste, and your way of thinking. #JarvixOS transforms how you work with AI by understanding your patterns, carrying your context across agents, and helping you move from ideas to action. Step into a new era of AI collaboration: • Discover your AI-native archetype • Build your personal AI model from your evolving AI interactions • Never start from zero - your context moves with you across sessions • Coordinate Codex, Claude Code, Gemini, Hermes, OpenClaw, and more as one connected AI team. • Turn insights into your next move, with you always in control Instead of adapting yourself to every agent, Jarvix carries the context you choose, helps you understand what it reveals, and brings the right agents together when you decide to act. Your AI tools shouldn’t work like separate assistants. They should work like one team. That’s the future of AI: Not more agents. One shared context. One Jarvix.

Jarvix

1,692,634 просмотров • 2 месяцев назад

Sam Altman says today's models are still dumb because they barely understand your life The next shift is a model that knows your context, your work, your goals, your people, and the way you use your computer "that is gonna be a complete change to what it feels like to use AI"
0:52

Sam Altman says today's models are still dumb because they barely understand your life The next shift is a model that knows your context, your work, your goals, your people, and the way you use your computer "that is gonna be a complete change to what it feels like to use AI"

Haider.

118,014 просмотров • 6 месяцев назад

Your AI stack just stopped being closed. 🔓 TanStack AI now speaks AG-UI client-to-server. - The same client hits any AG-UI server. - Any AG-UI client hits a TanStack server. Zero breaking changes. Migration guide in the tweet below 👇
0:30

Your AI stack just stopped being closed. 🔓 TanStack AI now speaks AG-UI client-to-server. - The same client hits any AG-UI server. - Any AG-UI client hits a TanStack server. Zero breaking changes. Migration guide in the tweet below 👇

TANSTACK

79,086 просмотров • 5 месяцев назад

Introducing TanStack Redact 🌴 A smaller runtime for your existing React app. Add it to your build config and ship less JavaScript without changing a single line of application code. Works with TanStack Start, Vite, Vinext, and Next.js.
0:37

Introducing TanStack Redact 🌴 A smaller runtime for your existing React app. Add it to your build config and ship less JavaScript without changing a single line of application code. Works with TanStack Start, Vite, Vinext, and Next.js.

TANSTACK

185,564 просмотров • 10 дней назад

🙌🏽 Side chats with /btw Ask questions without interrupting your workflow in the VS Code Agents window. With /btw, you can open a side chat that shares the context of your primary chat—perfect for quick questions without disrupting your current task.
0:56

🙌🏽 Side chats with /btw Ask questions without interrupting your workflow in the VS Code Agents window. With /btw, you can open a side chat that shares the context of your primary chat—perfect for quick questions without disrupting your current task.

Visual Studio Code

36,183 просмотров • 2 месяцев назад

In the next few years, every digital action will be mediated by AI. Moving money. Business communications. Researching decisions. Booking meetings. Paying bills. Running workflows. Choosing what to do next. If you want to stay effective, you will need your own architecture around your personal AI agent. Not just a subscription. A personal system that helps your AI understand your world: your goals, context, rules, obligations, decisions, and outcomes. That is ODEI. Built to help you get more from the AI you already use: ChatGPT. Claude. Gemini. Grok (soon). Not by replacing them. By giving them your memory, rules, context, receipts, and local control. The model is not enough. The real leverage comes when your AI understands your world, works inside your rules, and compounds with you over time. (Footage captured live in a local staging environment)
0:33

In the next few years, every digital action will be mediated by AI. Moving money. Business communications. Researching decisions. Booking meetings. Paying bills. Running workflows. Choosing what to do next. If you want to stay effective, you will need your own architecture around your personal AI agent. Not just a subscription. A personal system that helps your AI understand your world: your goals, context, rules, obligations, decisions, and outcomes. That is ODEI. Built to help you get more from the AI you already use: ChatGPT. Claude. Gemini. Grok (soon). Not by replacing them. By giving them your memory, rules, context, receipts, and local control. The model is not enough. The real leverage comes when your AI understands your world, works inside your rules, and compounds with you over time. (Footage captured live in a local staging environment)

Anton Illarionov

1,118,705 просмотров • 5 месяцев назад