# Which agents beafk runs

> The real Claude Code, Codex, Grok Build and Kimi Code, plus one more that does not chat — all on your own subscriptions.

beafk installs and runs the command-line tools their makers ship, signed in as
you. We do not wrap them or replace them with an API. Skills and tool servers
you set once reach every agent you run.

## The four you chat with

| Agent | Who makes it | Chat | Signs in with |
| --- | --- | --- | --- |
| **Claude Code** | Anthropic | yes | your Anthropic account, or an API key |
| **Codex** | OpenAI | yes | your ChatGPT account, or an API key |
| **Grok Build** | xAI | yes | your x.ai account, or an API key |
| **Kimi Code** | Moonshot AI | yes | your Moonshot account |

These four are what the install offers by default, and they are the ones that
appear in a chat. Install one, or all four, and add the rest later
without touching the machine.

## One more, which does not chat

**Codex Security** (OpenAI) reads a repository and reports what is wrong with
it — `codex-security scan .`. There is nothing to converse with. It sits with
the others because the questions about it are the same: is it installed, is it
signed in, and how do you sign it in from a phone.

## Mixing them

You are not choosing one. A machine can have all of them, a chat names
which one it is with, and a [crew](https://beafk.app/docs/what-a-crew-is.md) can put several to work
on one job at the same time — one scouting, one building, one reading the diff.
They are not equally good at the same things, and you are already paying for
more than one.

## What each one costs you

Nothing extra here — beafk charges per **machine**, and every message goes on
the subscription that agent is already signed in with. See
[what it costs](https://beafk.app/docs/what-it-costs.md).

## Next

[Signing an agent in](https://beafk.app/docs/signing-an-agent-in.md) is the how, from your phone,
without going back to the server.

---

beafk documentation · Agents · https://beafk.app/docs/which-agents-beafk-runs

In this section:
- Which agents beafk runs — https://beafk.app/docs/which-agents-beafk-runs.md (this page)
- Models, effort and permission — https://beafk.app/docs/models-effort-and-permission.md
- When an agent needs you — https://beafk.app/docs/when-an-agent-needs-you.md
- Closing the tab — https://beafk.app/docs/closing-the-tab.md

Every page, one line each: https://beafk.app/docs/llms.txt
All of it in one file: https://beafk.app/docs/llms-full.txt