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

# ContentHero for Developers

> The context and execution layer for AI content creation. Your agent is the brain. ContentHero supplies the grounding and does the work.

ContentHero is the **context and execution layer** for AI content creation. Your own LLM is the **brain**. ContentHero feeds it grounding (your brand voice, your inspiration outliers, your past posts) and executes the work (generate media, assemble posts, schedule, publish).

Whichever agent you use can drive all of it, three ways.

<CardGroup cols={2}>
  <Card title="MCP server" icon="plug" href="/mcp/overview">
    Hosted at `mcp.contenthero.ai` over OAuth. Everything ContentHero can do, no key handling.
  </Card>

  <Card title="CLI" icon="terminal" href="/cli/overview">
    `npm install -g @contenthero/cli`. Shell-native, scriptable, browser-assisted login.
  </Card>

  <Card title="TypeScript SDK" icon="code" href="/api-reference/overview">
    `@contenthero/sdk`. A typed kernel for the `/api/v1` REST surface.
  </Card>

  <Card title="Agent skills" icon="robot" href="/for-ai-agents">
    Installable workflows for Claude, Codex, and Cursor that drive all of the above.
  </Card>
</CardGroup>

## How it works

ContentHero gives your agent two things: the **grounding** to make content that sounds like you, and the **execution** to produce and publish it.

<CardGroup cols={2}>
  <Card title="Grounding" icon="layer-group">
    Your brand voice, your top-performing inspiration, and your own past posts. The context that makes content on-brand instead of generic.
  </Card>

  <Card title="Execution" icon="bolt">
    Generate the media, assemble the post, schedule it, publish it. The work, done for you.
  </Card>
</CardGroup>

Your agent brings the intelligence. ContentHero brings the context and the tools to act on it. When your agent drafts copy, it grounds the draft in your real context (your outliers, brand voice, and past posts) and shows it to you for approval before anything goes live.

## What you can do

<CardGroup cols={2}>
  <Card title="Generate" icon="wand-magic-sparkles" href="/guides/generate">
    Image, video, audio, reference boards, and lip-sync, with output-id chaining and cost preflight.
  </Card>

  <Card title="Run the pipeline" icon="diagram-project" href="/guides/pipeline">
    Research outliers, ground a draft in your voice, produce the media, assemble the post, schedule or publish.
  </Card>

  <Card title="Read and grow your brand" icon="book" href="/guides/brand">
    Read and edit your brand kit, and search, add to, and grow a semantic knowledge base.
  </Card>

  <Card title="Mine inspiration" icon="magnifying-glass-chart" href="/guides/inspiration">
    Read tracked accounts, outliers, and brand-account performance to ground every decision.
  </Card>
</CardGroup>

## Start here

If you are an AI coding agent acting on a user's behalf, read [For AI Agents](/for-ai-agents) **before** anything else. It defines the auth-detection ladder you must follow and the failure mode to avoid. If you are a human integrating ContentHero, go straight to the [Quickstart](/quickstart).