# Stackline AI

Stackline AI is a provider-neutral AI app foundation by Stackline.

Current releases: core family 0.0.3; UI 0.0.5.

Canonical repository:

https://github.com/alexandroit/ai

Core packages:

- @stackline/ai: TypeScript contracts and server core.
- @stackline/ai-server: Fetch-compatible backend HTTP handler.
- @stackline/ai-ui: Framework-neutral Studio web component with extensible
  language picker.
- @stackline/ai-ollama: Ollama provider adapter.
- @stackline/ai-memory-sqlite: SQLite memory store.
- @stackline/ai-rag-postgres: PostgreSQL read-only RAG retriever.

Install by scenario:

- Core only: `npm install @stackline/ai`
- Ollama provider only: `npm install @stackline/ai @stackline/ai-ollama`
- Backend API with Ollama: `npm install @stackline/ai @stackline/ai-server @stackline/ai-ollama`
- Full UI with Ollama: `npm install @stackline/ai @stackline/ai-server @stackline/ai-ollama @stackline/ai-ui && npm install -D vite`
- Complete stack: `npm install @stackline/ai @stackline/ai-server @stackline/ai-ollama @stackline/ai-ui @stackline/ai-memory-sqlite @stackline/ai-rag-postgres && npm install -D vite`

Recommended runtime path:

Browser -> <stackline-ai-studio> -> GET /api/ai/models -> POST /api/ai/chat
-> @stackline/ai-server -> @stackline/ai -> provider adapter.

Recommended backend first:

```ts
import { createStacklineAIServer } from "@stackline/ai/server";
import { createStacklineAIHttpHandler } from "@stackline/ai-server";
```

After those routes work, render:

```html
<stackline-ai-studio endpoint="/api/ai/chat" models-endpoint="/api/ai/models"></stackline-ai-studio>
```

Security rule:

Do not put provider API keys or database credentials in frontend code. Use a
backend route powered by @stackline/ai-server.

The 0.0.3 HTTP handler bounds request streams, returns HTTP 413 for oversized
payloads, and requires an explicit model when allowedModels is configured.