> ## Documentation Index
> Fetch the complete documentation index at: https://docs.core-ai.dev/llms.txt
> Use this file to discover all available pages before exploring further.

# Introduction

> A type-safe abstraction layer over LLM provider SDKs for TypeScript

# Welcome to core-ai

core-ai is a type-safe abstraction layer over LLM provider SDKs for TypeScript. Write provider-agnostic code with a unified API for chat completion, streaming, embeddings, image generation, and tool calling.

## Why core-ai?

Switch between OpenAI, Anthropic, Google Gemini, and Mistral without changing your application code. core-ai provides a consistent interface across all providers while maintaining full type safety and access to provider-specific features when you need them.

<CardGroup cols={2}>
  <Card title="Installation" icon="download" href="/installation">
    Get started with npm, yarn, or pnpm
  </Card>

  <Card title="Quickstart" icon="bolt" href="/quickstart">
    Build your first chat completion in 2 minutes
  </Card>

  <Card title="API Reference" icon="code" href="/api/core/generate">
    Explore the complete API documentation
  </Card>

  <Card title="Examples" icon="lightbulb" href="/examples/overview">
    See real-world implementation examples
  </Card>
</CardGroup>

## Key features

<CardGroup cols={2}>
  <Card title="Unified API" icon="layer-group">
    Write once, run on any provider. Switch between OpenAI, Anthropic, Mistral, and Google GenAI without code changes.
  </Card>

  <Card title="Full type safety" icon="shield-check">
    Strict TypeScript types, Zod-based tool definitions, and zero `any` types for complete type safety.
  </Card>

  <Card title="Streaming support" icon="water">
    Replayable async iterable streams with `.result` and `.events` for both text (`ChatStream`) and structured outputs (`ObjectStream`).
  </Card>

  <Card title="Structured outputs" icon="table">
    Schema-validated object generation and streaming with `z.infer<TSchema>` for type-safe results.
  </Card>

  <Card title="Tool calling" icon="wrench">
    Define tools with Zod schemas that automatically convert to JSON Schema for any provider.
  </Card>

  <Card title="Multi-modal" icon="image">
    Support for text, images (base64 and URL), and file inputs across compatible providers.
  </Card>

  <Card title="Embeddings & images" icon="sparkles">
    First-class support for embeddings and image generation, not just chat completions.
  </Card>

  <Card title="Lightweight" icon="feather">
    Thin wrappers over native SDKs with no heavy runtime dependencies.
  </Card>
</CardGroup>

## Supported providers

| Provider              | Package                 | Chat | Streaming | Embeddings | Image Generation |
| --------------------- | ----------------------- | ---- | --------- | ---------- | ---------------- |
| OpenAI                | `@core-ai/openai`       | ✓    | ✓         | ✓          | ✓                |
| Anthropic             | `@core-ai/anthropic`    | ✓    | ✓         | —          | —                |
| Google GenAI (Gemini) | `@core-ai/google-genai` | ✓    | ✓         | ✓          | ✓                |
| Mistral               | `@core-ai/mistral`      | ✓    | ✓         | ✓          | —                |

## Next steps

<Steps>
  <Step title="Install core-ai">
    Choose your package manager and install the core package with your preferred provider.

    [Go to installation →](/installation)
  </Step>

  <Step title="Run your first example">
    Create a simple chat completion in under 10 lines of code.

    [Go to quickstart →](/quickstart)
  </Step>

  <Step title="Explore features">
    Learn about streaming, structured outputs, tool calling, and more.

    [Browse examples →](/examples/overview)
  </Step>
</Steps>