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

# Agents & models overview

> Choose an agentic coding CLI per task, and configure the LLM backend once for your org.

Two independent choices shape how a task runs:

<CardGroup cols={2}>
  <Card title="Agent — which CLI runs" icon="terminal">
    The agentic coding CLI that runs in the workspace: **Claude Code**, **Codex CLI**, **Gemini
    CLI**, or **Kiro CLI**. Chosen **per task**.
  </Card>

  <Card title="Provider — which LLM backend" icon="server">
    For Claude Code, the backend + auth path: Anthropic API, an internal gateway, AWS Bedrock,
    Google Vertex, or Azure. Configured **once per org** in Admin.
  </Card>
</CardGroup>

## The agents

| Agent                      | Credential               | Where the key comes from                  |
| -------------------------- | ------------------------ | ----------------------------------------- |
| **Claude Code** (`claude`) | Anthropic API key        | Org LLM key (or cloud identity / gateway) |
| **Codex CLI** (`codex`)    | OpenAI API key           | Org "OpenAI key (Codex)"                  |
| **Gemini CLI** (`gemini`)  | Google API key           | Org "Google key (Gemini)"                 |
| **Kiro CLI** (`kiro`)      | None (device-flow login) | Logged in once, then reused               |

<Note>
  There's a reserved `custom` agent for a future bring-your-own CLI. It isn't selectable and can't
  run yet.
</Note>

## Where you choose

* **Per task** — the New Task form shows an **Agent** dropdown (limited to the
  CLIs your org allows) and, when your org has more than one model configured, a
  **Model** dropdown. See [Create a task](/getting-started/create-a-task).
* **Per org** — an admin sets the provider, model(s), keys, and policy under
  **Admin → Agent LLM**. Until an LLM is configured, tasks can't be dispatched.

## What to read next

<CardGroup cols={2}>
  <Card title="Claude Code" icon="a" href="/agents/claude-cli">
    Anthropic, gateway, or cloud identity.
  </Card>

  <Card title="Codex CLI" icon="o" href="/agents/codex-cli">
    Runs on an OpenAI key.
  </Card>

  <Card title="Gemini CLI" icon="g" href="/agents/gemini-cli">
    Runs on a Google key.
  </Card>

  <Card title="Kiro CLI" icon="k" href="/agents/kiro-cli">
    Device-flow login, once.
  </Card>

  <Card title="LLM configuration" icon="sliders" href="/agents/llm-configuration">
    Provider, model, and keys.
  </Card>

  <Card title="Internal gateway" icon="shield-halved" href="/agents/internal-gateway">
    Route everything through one proxy.
  </Card>

  <Card title="Multiple models" icon="layer-group" href="/agents/multiple-models">
    Offer several models per org.
  </Card>
</CardGroup>