MCP support in TanStack AI is here! π
π΄ One MCP server or many
π΄ Standalone clients or pooled servers
π΄ CLI for typegen
π΄ Managed lifecycle via chat or complete control
Read the full blog post below π
A tool returns an image of a secret number. The model reads it back. ποΈ
TanStack AI now supports multimodal tool results: return an Array<ContentPart> with an image part and the model sees the actual pixels - not a stringified blob.
https://t.co/8ZTMfxLelk
Your AI chat vanishes on every page reload? π
TanStack AI just shipped a persistence option: pass one adapter and conversations hydrate on load, save on change, clear on reset. localStorage, IndexedDB, anything.
https://t.co/8ZTMfxLelk
One adapter. Every OpenAI-compatible provider. π
openaiCompatible({ baseURL, apiKey, models })
Connects DeepSeek, Kimi, Together, Fireworks, Qwen, local LM Studio/vLLM, and more.
Type-safe model unions, no package per vendor.
https://t.co/8ZTMfxLelk π
Another build path just washed ashore ποΈ
TanStack Start now supports Rsbuild 2 alongside Vite, bringing the full Start feature set to the Rspack / Webpack ecosystem.
https://t.co/FEMQmGfgiz
One of the cooler parts of their writeup: When AI is generating full apps, framework primitives are a direct translation to product quality, so typed routing, clear server/client boundaries, server functions, and route-level rendering choices act as both guardrails for the apps your users create and a measurable lever for user experience.
2/2
New @Lovable projects now ship on TanStack Start.
That means full-stack React with SSR/SSG/CSR per route, server functions colocated with components, deploy-anywhere architecture, and type safety that helps both humans and AI generate better apps.
1/2
https://t.co/Vb962C0h3P
We just released a new version of TanStack AI! π
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. π₯
TanStack AI now runs on react-native! π
Stream down to mobile devices with ease using fetch + polyfills or XHR transports!
Try it out with the latest releases!
Announcing experimental Workflows & Orchestrators for TanStack AI π΄
πΊοΈ Workflows = known path
π§ Orchestrators = dynamically choose the next step
Orchestrate your agents with ease with our experimental release! Build something with it, break it, and show us what you make!
πππ§΅
One of our packages was incorrectly flagged as malicious today as part of the broader false-positive wave affecting a number of widely trusted packages across the ecosystem.
Weβve manually reviewed the published artifacts for the flagged version and can confirm they are clean.
A bit concerning that the first indication we received about the malware flag was via social media instead of a direct notification or outreach process. Hoping the reporting flow around issues like this can improve going forward.
TanStack Virtual now has first-class chat support: end anchoring, append-follow, stable prepends, and streaming messages that stay pinned when they should.
The modern web is now a lot of streaming UI on top of lists, so this needed to feel boring π
https://t.co/qX9sbphpJJ
Your AI no longer forgets its structured outputs π§ β¨
TanStack AI now supports multi-turn structured output that remembers across turns.
Ask for a recipe π
Refine it to vegan π±
Make it cheaper πΈ
Add a salad π₯
And every typed result stays preserved in chat history.π΄β‘