--- title: TanStack AI Enters the RC Phase | daily.dev description: TanStack AI has moved into its release candidate phase ahead of a stable v1 release. The framework now supports 24 LLM providers, has adopted AG-UI as its... canonical: https://daily.dev/posts/tanstack-ai-enters-the-rc-phase-gufbcxnqj twitter:card: summary_large_image twitter:site: @dailydotdev og:type: website og:site_name: daily.dev og:title: TanStack AI Enters the RC Phase | daily.dev og:description: TanStack AI has moved into its release candidate phase ahead of a stable v1 release. The framework now supports 24 LLM providers, has adopted AG-UI as its... og:url: https://daily.dev/posts/tanstack-ai-enters-the-rc-phase-gufbcxnqj og:image: https://api.daily.dev/og/posts/guFBCxnQj.png og:image:alt: TanStack AI Enters the RC Phase og:image:width: 1200 og:image:height: 630 og:locale: en --- > ## Documentation Index > Fetch the complete documentation index at: https://daily.dev/llms.txt > Use this file to discover all available pages before exploring further. # TanStack AI Enters the RC Phase **[TanStack](https://daily.dev/sources/tanstack-blog)** · 10 min read · 0 upvotes · 0 comments ## Summary TanStack AI has moved into its release candidate phase ahead of a stable v1 release. The framework now supports 24 LLM providers, has adopted AG-UI as its official protocol, and offers a middleware system for chat persistence, agent harnesses, memory, and telemetry. Other highlighted capabilities include lazy tool calling, typed interrupts, unified media generation APIs (image, video, audio, transcription, TTS) across 100+ models, MCP support with type generation, agent sandboxing with ACP-compatible agents like Codex and Claude Code, and durable, resumable chat persistence requiring roughly 20 lines of code. The project is maintained by a three-person team and remains fully open source with no commercial roadmap. ## Full article daily.dev links to this article rather than hosting it. Read it at the original source: ## Questions this post answers ### What is TanStack AI and what does it support now that it's entered release candidate? TanStack AI is an open-source AI and agent framework built around a chat() method, now in release candidate status ahead of a stable v1. It supports 24 LLM providers, the AG-UI protocol used by 20+ agent frameworks, MCP with type-safe code generation, agent sandboxing with ACP-compatible agents like Codex and Claude Code, media generation across 100+ models, and persistent, resumable conversations. _Developers evaluating AI application frameworks can track releases like this one on daily.dev._ ### How does TanStack AI implement persistent and resumable chat conversations? Persistence works by implementing a store that exposes conversation data, validating it against a conformance suite, then passing it into TanStack AI's persistence middleware. Durability adapters persist stream chunks in memory, Durable Streams, or other supported systems, so users can refresh mid-response or return after a month and resume exactly where they left off, in roughly 20 lines of code excluding the store implementation. _Anyone building resumable AI chat experiences can follow framework updates like this via daily.dev._ ### What is lazy tool calling in TanStack AI and why does it matter? Lazy tool calling is a feature in TanStack AI that reduces token costs by controlling tool exposure through a simple boolean flag, rather than sending every tool definition upfront. It works alongside advanced interrupt scenarios, letting developers modify tool-call arguments or trigger multiple interrupts while keeping type safety intact end to end. _Developers optimizing agent token costs can keep up with tooling patterns like this on daily.dev._ ## Similar posts on daily.dev - [TanStack Releases Framework Agnostic AI Toolkit](https://daily.dev/posts/tanstack-releases-framework-agnostic-ai-toolkit-j747yitl6) · InfoQ · 1 upvotes · 0 comments - [TanStack Adds Framework-Agnostic AI Toolkit](https://daily.dev/posts/tanstack-adds-framework-agnostic-ai-toolkit-osqcmpmfc) · The New Stack · 18 upvotes · 0 comments --- Tags: [#llm](https://daily.dev/tags/llm), [#ai-agents](https://daily.dev/tags/ai-agents), [#typescript](https://daily.dev/tags/typescript), [#mcp](https://daily.dev/tags/mcp), [#tanstack](https://daily.dev/tags/tanstack) [View this post on daily.dev](https://daily.dev/posts/tanstack-ai-enters-the-rc-phase-gufbcxnqj) ```json {"@context":"https://schema.org","@graph":[{"@type":"Organization","@id":"https://daily.dev/#organization","name":"daily.dev","url":"https://daily.dev","logo":{"@type":"ImageObject","url":"https://daily.dev/apple-touch-icon.png","width":180,"height":180},"sameAs":["https://twitter.com/dailydotdev","https://github.com/dailydotdev","https://www.linkedin.com/company/daily-dev-ltd"]},{"@type":"WebSite","@id":"https://daily.dev/#website","url":"https://daily.dev","name":"daily.dev","publisher":{"@id":"https://daily.dev/#organization"},"potentialAction":{"@type":"SearchAction","target":{"@type":"EntryPoint","urlTemplate":"https://daily.dev/search?q={search_term_string}"},"query-input":"required name=search_term_string"}}]} {"@context":"https://schema.org","@type":"TechArticle","headline":"TanStack AI Enters the RC Phase","url":"https://daily.dev/posts/tanstack-ai-enters-the-rc-phase-gufbcxnqj","mainEntityOfPage":{"@type":"WebPage","@id":"https://daily.dev/posts/tanstack-ai-enters-the-rc-phase-gufbcxnqj"},"datePublished":"2026-08-23T12:22:22.079Z","dateModified":"2026-08-24T18:06:18.185Z","description":"TanStack AI has moved into its release candidate phase ahead of a stable v1 release. The framework now supports 24 LLM providers, has adopted AG-UI as its...","image":"https://media.daily.dev/image/upload/f_auto,q_auto/v1/posts/f743a07611bef01415f62fcdc438e814?_a=AQAEuop","thumbnailUrl":"https://media.daily.dev/image/upload/f_auto,q_auto/v1/posts/f743a07611bef01415f62fcdc438e814?_a=AQAEuop","isAccessibleForFree":true,"articleSection":"TanStack","inLanguage":"en","publisher":{"@type":"Organization","name":"daily.dev","url":"https://daily.dev","logo":{"@type":"ImageObject","url":"https://daily.dev/apple-touch-icon.png","width":180,"height":180}},"author":{"@type":"Organization","name":"TanStack","logo":"https://media.daily.dev/image/upload/s--TVIrvIT7--/f_auto,q_auto/v1787487634/logos/tanstack-blog?_a=BAMAMicg0","url":"https://daily.dev/sources/tanstack-blog"},"commentCount":0,"discussionUrl":"https://daily.dev/posts/tanstack-ai-enters-the-rc-phase-gufbcxnqj","interactionStatistic":[{"@type":"InteractionCounter","interactionType":{"@type":"LikeAction"},"userInteractionCount":0},{"@type":"InteractionCounter","interactionType":{"@type":"CommentAction"},"userInteractionCount":0}],"keywords":"llm,ai-agents,typescript,mcp,tanstack","timeRequired":"PT10M"} {"@context":"https://schema.org","@type":"BreadcrumbList","itemListElement":[{"@type":"ListItem","position":1,"name":"Home","item":"https://daily.dev"},{"@type":"ListItem","position":2,"name":"TanStack","item":"https://daily.dev/sources/tanstack-blog"},{"@type":"ListItem","position":3,"name":"TanStack AI Enters the RC Phase"}]} {"@context":"https://schema.org","@type":"FAQPage","@id":"https://daily.dev/posts/tanstack-ai-enters-the-rc-phase-gufbcxnqj#faq","mainEntity":[{"@type":"Question","name":"What is TanStack AI and what does it support now that it's entered release candidate?","acceptedAnswer":{"@type":"Answer","text":"TanStack AI is an open-source AI and agent framework built around a chat() method, now in release candidate status ahead of a stable v1. It supports 24 LLM providers, the AG-UI protocol used by 20+ agent frameworks, MCP with type-safe code generation, agent sandboxing with ACP-compatible agents like Codex and Claude Code, media generation across 100+ models, and persistent, resumable conversations. Developers evaluating AI application frameworks can track releases like this one on daily.dev."}},{"@type":"Question","name":"How does TanStack AI implement persistent and resumable chat conversations?","acceptedAnswer":{"@type":"Answer","text":"Persistence works by implementing a store that exposes conversation data, validating it against a conformance suite, then passing it into TanStack AI's persistence middleware. Durability adapters persist stream chunks in memory, Durable Streams, or other supported systems, so users can refresh mid-response or return after a month and resume exactly where they left off, in roughly 20 lines of code excluding the store implementation. Anyone building resumable AI chat experiences can follow framework updates like this via daily.dev."}},{"@type":"Question","name":"What is lazy tool calling in TanStack AI and why does it matter?","acceptedAnswer":{"@type":"Answer","text":"Lazy tool calling is a feature in TanStack AI that reduces token costs by controlling tool exposure through a simple boolean flag, rather than sending every tool definition upfront. It works alongside advanced interrupt scenarios, letting developers modify tool-call arguments or trigger multiple interrupts while keeping type safety intact end to end. Developers optimizing agent token costs can keep up with tooling patterns like this on daily.dev."}}]} ```