@tanstack/ai
Version:
Type-safe TypeScript AI SDK for streaming chat, tool calling, agents, structured outputs, and multimodal generation.
192 lines (156 loc) • 10.3 kB
Markdown
---
name: ai-core
description: >
Entry point for TanStack AI skills. Routes to chat-experience, tool-calling,
media-generation, structured-outputs, adapter-configuration, ag-ui-protocol,
middleware, locks, custom-backend-integration, and debug-logging, plus the skills
shipped by companion packages (/ai-persistence, @tanstack/ai-code-mode),
and computer use (/ai-computer-use).
Use chat() not streamText(), openaiText() not createOpenAI(),
toServerSentEventsResponse() not manual SSE, middleware hooks not onEnd callbacks.
type: core
library: tanstack-ai
library_version: '0.42.0'
---
# TanStack AI — Core Concepts
TanStack AI is a type-safe, provider-agnostic AI SDK. Server-side functions
live in `/ai` and provider adapter packages. Client-side hooks live
in framework packages (`/ai-react`, `@tanstack/ai-solid`, etc.).
Always import from the framework package on the client — never from
`/ai-client` directly (unless vanilla JS).
## Sub-Skills
| Need to... | Read |
| ------------------------------------------------- | --------------------------------------------- |
| Build a chat UI with streaming | ai-core/chat-experience/SKILL.md |
| Survive a browser reload (no extra package) | ai-core/client-persistence/SKILL.md |
| Add tool calling (server, client, or both) | ai-core/tool-calling/SKILL.md |
| Generate images, video, speech, or transcriptions | ai-core/media-generation/SKILL.md |
| Get typed JSON responses from the LLM | ai-core/structured-outputs/SKILL.md |
| Choose and configure a provider adapter | ai-core/adapter-configuration/SKILL.md |
| Implement AG-UI streaming protocol server-side | ai-core/ag-ui-protocol/SKILL.md |
| Add analytics, logging, or lifecycle hooks | ai-core/middleware/SKILL.md |
| Coordinate multi-instance work with locks | ai-core/locks/SKILL.md |
| Connect to a non-TanStack-AI backend | ai-core/custom-backend-integration/SKILL.md |
| Turn on/off debug logging, pipe into pino/winston | ai-core/debug-logging/SKILL.md |
| Persist chats server-side (history, runs) | See `/ai-persistence` package skills |
| Set up Code Mode (LLM code execution) | See `/ai-code-mode` package skills |
| Give the model a catalog of SKILL.md skills | See `/ai-skills` package skills |
| Let the model use a browser or a desktop | See "Computer use" below |
## Companion packages
Some capabilities live in their own package and ship their own skills. Install
the package, then read its skills — do not guess the API from this file.
### `/ai-persistence` — durable chat state
Makes a conversation survive a reload, a server restart, a second device, or a
paused tool approval. It ships the **store contracts** (`MessageStore`,
`RunStore`, `InterruptStore`, `MetadataStore`), the `withPersistence` /
`withGenerationPersistence` middleware, `reconstructChat` for server-side
hydrate, an in-memory reference backend, and a conformance testkit. Multi-instance
locks are **not** in this package — `LockStore` / `withLocks` ship in
`/ai/locks`; see ai-core/locks. The `runs` store contract is typed
against run lifecycle types (`RunStatus`, `RunRecord`, `RunStore`,
`defineRunStore`, `InMemoryRunStore`), which ship in `/ai` itself;
see ai-core/middleware.
It does **not** ship a backend for your database — you implement the stores
against Postgres, SQLite, D1, Mongo, or whatever you run, and the package's
skills walk you through it (including Drizzle, Prisma, and Cloudflare recipes).
```bash
pnpm add /ai-persistence
npx /intent install
```
The skills ship **inside** the package, so they only exist on disk once it is
installed — the second command re-scans `node_modules` and wires them into the
agent config. Until then the paths below resolve to nothing.
Entry point: `node_modules/@tanstack/ai-persistence/skills/ai-persistence/SKILL.md`
| Need to... | Read |
| ----------------------------------------------- | --------------------------------------- |
| Wire server-side chat history, runs, interrupts | ai-persistence/server/SKILL.md |
| Implement the store interfaces for your DB | ai-persistence/stores/SKILL.md |
| Write the adapter for the DB your app runs | ai-persistence/build-*-adapter/SKILL.md |
Browser-side persistence is **not** in this package — it ships with the
framework packages, so read **ai-core/client-persistence** instead.
### `/ai-code-mode` — LLM code execution
See the `ai-code-mode` skill in that package.
### `/ai-skills` — portable Agent Skills at runtime
Gives the model a library of `SKILL.md` skills it can load on demand, on any
provider, via the `withSkills` middleware and a `load_skill` tool. Skills come
from `inlineSkill`, `skillDirectory`, or a build-time bundle. This is the
runtime feature for the model **inside your app**, not the coding-assistant
skills this file is part of, and not the hosted `codeExecutionTool` /
`shellTool` skills (those run in a provider sandbox).
```bash
pnpm add /ai-skills
npx /intent install
```
Entry point: `node_modules/@tanstack/ai-skills/skills/ai-skills/SKILL.md`
### `/ai-computer-use` — computer use
The model reads screenshots and uses a mouse and a keyboard. One setup runs on
OpenAI and on Claude: each adapter swaps the generic `computer` tool for the
native computer tool of the model. Pick the machine with a driver package:
| Machine | Driver |
| ------------------------------------- | ---------------------------------------------------------------------------------------- |
| A Chromium page | `playwrightComputer()` from `/ai-computer-playwright` (needs `playwright-core`) |
| A Linux desktop in any sandbox | `sandboxComputer({ provider })` from `/ai-computer-sandbox` |
| The real screen of the server machine | `localComputer()` from `/ai-computer-local` (needs `@jitsi/robotjs`) |
```typescript
import {
chat,
chatParamsFromRequest,
toServerSentEventsResponse,
} from '/ai'
import { anthropicText } from '@tanstack/ai-anthropic'
import { createComputerUse } from '@tanstack/ai-computer-use'
import { sandboxComputer } from '@tanstack/ai-computer-sandbox'
import { e2bSandbox } from '@tanstack/ai-sandbox-e2b'
// One time, at module scope. Each threadId gets its own desktop.
const computerUse = createComputerUse({
driver: sandboxComputer({
provider: e2bSandbox({ template: 'desktop', timeoutMs: 60 * 60_000 }),
}),
})
export async function POST(request: Request) {
const { messages, threadId } = await chatParamsFromRequest(request)
const stream = chat({
adapter: anthropicText('claude-opus-5-5'),
messages,
// Required: without a stable threadId, each request gets a new machine.
threadId,
tools: computerUse.tools,
middleware: [computerUse.middleware],
interrupts: [computerUse.interrupt],
})
return toServerSentEventsResponse(stream)
}
```
On the client, register `computerSafetyCheck` (from `/ai-computer-use`)
in `useChat({ interrupts })`, so a person can approve an OpenAI safety check.
- Do not write the action loop or map the actions yourself. `createComputerUse`
does that for both providers.
- Do not use `localComputer()` unless the user asks for it. It moves the real
mouse of the machine. Use a sandbox or a browser instead.
- OpenAI computer use needs a Responses API adapter (`openaiText`). Chat
Completions throws.
- A model without computer use is a type error at `chat()`.
Docs: `docs/computer-use/computer-use.md`, `docs/computer-use/drivers.md`,
`docs/computer-use/safety-checks.md`, `docs/computer-use/custom-driver.md`.
## Quick Decision Tree
- Setting up a chatbot? → ai-core/chat-experience
- Adding function calling? → ai-core/tool-calling
- Generating media (images, audio, video)? → ai-core/media-generation
- Need structured JSON output? → ai-core/structured-outputs
- Choosing/configuring a provider? → ai-core/adapter-configuration
- Building a server-only AG-UI backend? → ai-core/ag-ui-protocol
- Adding analytics or post-stream events? → ai-core/middleware
- Surviving reloads / multi-device / durable approvals? → `/ai-persistence` skills
- Letting the model use a browser or a desktop? → `/ai-computer-use` (see Computer use above)
- Connecting to a custom backend? → ai-core/custom-backend-integration
- Turning on debug logging to trace chunks/tools/middleware? → ai-core/debug-logging
- Debugging mistakes? → Check Common Mistakes in the relevant sub-skill
## Critical Rules
1. **This is NOT the Vercel AI SDK.** Use `chat()` not `streamText()`. Use `openaiText()` not `createOpenAI()`. Import from `/ai`, not `ai`.
2. **Import from framework package on client.** Use `/ai-react` (or solid/vue/svelte/preact), not `/ai-client`.
3. **Use `toServerSentEventsResponse()`** to convert streams to HTTP responses. Never implement SSE manually.
4. **Use middleware for lifecycle events.** No `onEnd`/`onFinish` callbacks on `chat()` — use `middleware: [{ onFinish: ... }]`.
5. **Ask the user which adapter and model** they want. Suggest the latest model. Also ask if they want Code Mode.
6. **Tools must be passed to both server and client.** Server gets the tool in `chat({ tools })`; the client passes the `.client()` implementation through the `clientTools()` helper into the **`tools`** option — `useChat({ tools: clientTools(myTool.client(...)) })`. There is no `clientTools` option. See ai-core/tool-calling.
## Version
Targets TanStack AI v0.42.0.