# TanStack AI 1.0 stabilises its provider-neutral SDK — but the agent harness is still experimental TanStack AI 1.0 locks down its core provider-neutral chat, tool and media APIs across 23 adapters, but the new long-running agent harness is still on experimental 0.x packages. Existing users must upgrade client and server together and migrate stored conversations. The three-maintainer TanStack AI project has reached stable 1.0 for its core SDK, with 23 providers; its long-running agent harness is not yet stable. - Status: Active - Published: 2026-10-29T18:45:01+13:00 - Updated: 2026-10-29T18:45:01+13:00 - Categories: Artificial Intelligence, Web Development, AI Agents, Frameworks, Developer Tools - Tags: AI agents, JavaScript, open source, TanStack AI - Canonical HTML: https://beyondthe.news/dossiers/tanstack-ai-1-stable-sdk-agent-harness-experimental-2026 ## What changed On October 23, 2026, the TanStack maintainers released TanStack AI 1.0, making its core chat, tool, media, MCP and streaming interfaces stable. The project reports 23 provider adapters and support for several UI frameworks, plus sandbox and coding-agent integrations. The release also introduces an experimental long-running agent harness, packaged separately at 0.x rather than covered by the 1.0 stability commitment. Migrating from 0.x requires coordinated 1.0 client and server packages, replacing deprecated APIs, updating streaming completion events and handling stored conversation data. TanStack says its core tests use deterministic model fixtures rather than live provider calls. ## Why it matters Teams building AI features into existing web applications can choose a framework-neutral SDK rather than tie their UI and provider to one proprietary stack. Stable core APIs reduce the risk of surprise changes, but the upgrade isn't a zero-work dependency bump: existing clients and servers must agree on protocol versions and saved state may need migration. The more ambitious background agent features are explicitly experimental, so production builders should separate the stable core from evolving harness internals. A small open-source project can change development practice without having a large commercial sponsor. ## Stable means core APIs, not every package TanStack's maintainers say the 1.0 contract applies to the core chat, tools, media and integration APIs. The new @tanstack/ai-harness and CLI remain experimental 0.x packages, as do relevant harness entry points elsewhere. Avoid treating a stable package label as proof that background agents, scheduling and persistence APIs are fixed. ## Provider and UI independence is the central design The project reports 23 provider adapters plus an OpenAI-compatible option, and integrations spanning React, Vue, Svelte, Solid and other UI layers. It also exposes MCP tools, supports provider switching and supplies deterministic test helpers. Those are upstream-reported capabilities; a production deployment should verify the exact providers and modalities it needs. ## The 0.x to 1.0 migration can break connected clients The official upgrade guide says all stable @tanstack/ai* packages should move together because a 1.0 client expects a 1.0 server. Deprecated APIs were removed; the project provides a codemod, but developers must supply thread IDs, handle tool approvals through interrupts, replace certain UI hooks and stop emitting the old [DONE] streaming marker in favour of RUN_FINISHED. Passing TypeScript checks does not migrate saved conversations, runs or files. ## The harness targets sessions that outlive requests The new defineHarness/createHarnessHost approach lets applications model persistent sessions, subagents, plugins, background workers, tool permissions and multiple transports including HTTP, ACP and MCP. These features may enable coding agents and support bots to survive deployments, but their APIs remain experimental and may change in minor versions. Operational safety still depends on persistence backends, authentication and idempotent external actions. ## A small maintainer team needs practical validation TanStack credits three maintainers and 143 contributors. Its deterministic provider-adapter tests reduce regressions but are not live tests against every model endpoint or sandbox. Builders should stage upgrades with representative tool calls, provider-specific edge cases, streaming reconnects and persisted conversation replay before using the new version in production. ## Key details - TanStack AI 1.0 announced October 23, 2026. - Stable core APIs span chat, tools, media, MCP and streaming; 23 provider adapters are reported by maintainers. - Agent harness and CLI remain experimental 0.x, not part of the stable 1.0 contract. - Upgrade client and server packages together; 1.0 clients require compatible 1.0 servers. - Migration removes deprecated interfaces and changes thread identifiers, approvals and stream completion. - A codemod helps but cannot migrate persisted conversations and runs automatically. - Maintainers report three core maintainers and 143 contributors. ## Builder takeaways - Audit your current TanStack AI package versions and upgrade client/server as one tested unit. - Follow the official migration guide for threadId, tool approvals, UI hooks and RUN_FINISHED streaming events. - Back up and rehearse migration of persisted conversation and run data; type checking alone is insufficient. - Keep the experimental harness behind clear interfaces and test reconnection, retries and authorisation. - Verify provider adapter behaviour with the exact models, tool schemas and UI framework your application uses. ## What to watch - Stabilisation timeline and breaking changes in the 0.x agent harness. - Provider adapter coverage and real-world reliability reports. - Migration fixes and tooling for persisted conversation state. - Whether developers adopt the provider-neutral SDK for production applications beyond demos. ## Uncertainties - The 23-adapter count and compatibility claims come from TanStack's own release material. - Deterministic fixtures do not prove every live provider integration works identically. - Experimental harness APIs may change in minor versions and should not be described as production-stable. - Independent long-running production reliability evidence remains limited. ## Sources - [TanStack AI 1.0: Still Your AI, Still Your Way](https://tanstack.com/blog/tanstack-ai-1-0) — TanStack · primary release · 2026-10-23T00:00:00+13:00. Core stability, adapter counts, experimental harness, migration instructions and project contributors. - [TanStack AI documentation and release history](https://tanstack.com/ai/latest/docs/blog) — TanStack · primary documentation · 2026-10-23T00:00:00+13:00. Official stable release and earlier release candidate history. - [JavaScript Weekly issue 808](https://javascriptweekly.com/issues/808) — JavaScript Weekly · independent specialist radar · 2026-10-27T00:00:00+13:00. Independent coverage of TanStack AI 1.0 and its experimental harness; not an independent benchmark.