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

# Marcia CLI

> Run and manage up to 100,000 AI agents executing millions of tool calls, fast and secure at any scale. For developers, business operators, and everyone in between, with third-party LLM support, on-prem or in the cloud.

<Note>
  **Agents at scale.** One tool to run and manage up to 100,000 AI agents executing millions of tool calls, fast and secure, no matter the scale.
</Note>

Marcia CLI lets developers, business operators, and everyone in between put AI agents to work on real tasks. Run a single agent in your terminal, or fan out to a fleet of up to 100,000 agents executing millions of tool calls in parallel, and manage all of it from one place. It connects everything you already run, new systems and legacy alike, into one agent layer, and the agents self-heal and keep learning as they work.

## Built for any task, at any scale

<CardGroup cols={2}>
  <Card title="Up to 100,000 agents" icon="layer-group">
    Orchestrate one agent or a fleet of up to 100,000, executing millions of tool calls in parallel to get work done.
  </Card>

  <Card title="Fast and secure at any scale" icon="shield-check">
    Built to stay fast and secure whether you run a single task or saturate a fleet, with permissioned tools and auditable runs.
  </Card>

  <Card title="For everyone, not just engineers" icon="users">
    Developers, business operators, and non-technical teams can all put agents to work on the tasks they own.
  </Card>

  <Card title="Any task" icon="list-check">
    Code, research, operations, data work, browser automation: if it can be done with tools, a fleet of agents can do it.
  </Card>

  <Card title="Bring your own LLM" icon="plug">
    Works with third-party LLMs alongside the Marcia Code models, so you are never locked to a single provider.
  </Card>

  <Card title="On-prem or in the cloud" icon="server">
    Deploy where your data and policies require: on your own infrastructure or in the cloud.
  </Card>

  <Card title="Connects your whole stack" icon="diagram-project">
    Bring everything you already run, new systems and legacy alike, into one agent layer: your tools, APIs, data, and services.
  </Card>

  <Card title="Self-heals and learns" icon="brain">
    Agents recover from failures on their own and keep getting better at your tasks over time, so the system improves as you use it.
  </Card>
</CardGroup>

## One place to manage it all

A self-contained binary brings the agent runtime, parallel sub-agent fan-out, and a built-in dashboard together: launch agents, watch their tool calls in real time, and steer or stop them, from the command line or the local board.

## How it fits

Marcia CLI is the command-line surface of the Marcia platform. The same models and account work across the CLI and the [Marcia Code](/public/products/marcia-code) API, and fleets scale up through [Marcia Fleet](/public/products/marcia-fleet).

<Note>
  [Request access at marciacli.com](https://marciacli.com). For a walkthrough or partnership questions, [get in touch](https://crestadvisorygroup.com/#contact).
</Note>