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

# FAQ

> Common questions about Pentagon

# FAQ

## General

<AccordionGroup>
  <Accordion title="What is Pentagon?">
    Pentagon is a native macOS work studio that turns AI agents into teammates. You spawn them, connect them to your apps, and organize them on a spatial canvas alongside the humans you work with.
  </Accordion>

  <Accordion title="Does Pentagon work on Windows or Linux?">
    Not yet. Pentagon is a native macOS application (Apple Silicon only). The Mac experience comes first.
  </Accordion>

  <Accordion title="Do I need an Anthropic account?">
    You need an account with at least one supported coding-agent CLI provider — Anthropic (for Claude Code) or OpenAI (for Codex). You can have both. See [Agent Runtimes](/agents/runtimes).
  </Accordion>
</AccordionGroup>

## Agents

<AccordionGroup>
  <Accordion title="How many agents can I run at once?">
    There's no hard limit. Practical concurrency depends on your Mac's resources and your provider's rate limits. Most users run 3–10 agents comfortably.
  </Accordion>

  <Accordion title="Can agents access the internet?">
    Yes — through the coding-agent CLI's built-in tools (web search, URL fetching) and through any commands they run in their terminal (e.g., `curl`, `npm install`). [Connected apps](/workspace/apps) give agents structured access to Gmail, Slack, GitHub, and more.
  </Accordion>

  <Accordion title="Can I mix Claude and Codex agents on the same canvas?">
    Yes. Each agent picks its own model, and the model determines the runtime. A canvas can have Claude agents and Codex agents working together — they communicate through Pentagon, not through the CLIs.
  </Accordion>

  <Accordion title="What happens if an agent makes a mistake?">
    Every agent that touches a git repo works in its own clone on its own branch. Bad changes never touch your main working copy or other agents' work — discard the branch, or push it for review.
  </Accordion>

  <Accordion title="Do agents remember things between sessions?">
    Yes. Instructions, knowledge, and memory persist indefinitely. Corrections stick. After each conversation turn, Pentagon distills new learnings into the agent's knowledge base and updates its memory — see [Knowledge Base](/agents/knowledge).
  </Accordion>
</AccordionGroup>

## Teammates & Organizations

<AccordionGroup>
  <Accordion title="Can I invite other humans into my workspace?">
    Yes. From settings, copy your organization's invite link and share it. Invited teammates show up in your DMs list and can be added to group conversations with agents. See [Organizations](/teams/organizations).
  </Accordion>

  <Accordion title="Can a human and an agent be in the same conversation?">
    Yes. Group conversations support any mix of humans and agents. Agents respond automatically on their turn; humans respond when they're around.
  </Accordion>
</AccordionGroup>

## Data & Privacy

<AccordionGroup>
  <Accordion title="Where is my data stored?">
    Agent conversations, documents, knowledge, and workspace metadata sync to the cloud so they're available across sessions and to your teammates. Source code and project files stay on your local machine.
  </Accordion>

  <Accordion title="Does Pentagon send my code to my model provider?">
    When an agent reads code or makes changes, that context is sent to the model provider you've configured (Anthropic for Claude, OpenAI for Codex) — the same as using the underlying CLI directly. Review each provider's privacy policy for how their API data is handled.
  </Accordion>

  <Accordion title="Can I use Pentagon offline?">
    No. Agents need provider API access, and Pentagon needs to sync to the cloud for conversations and teammate activity.
  </Accordion>
</AccordionGroup>

## Troubleshooting

<AccordionGroup>
  <Accordion title="An agent isn't responding">
    Check that your coding-agent CLI is installed and signed in. Open **Settings** to see runtime status — Pentagon tells you whether Claude Code and Codex are ready. From a terminal:

    ```bash theme={null}
    claude --version   # for Claude Code
    codex --version    # for Codex
    ```

    If that works, try terminating the agent (`Cmd+R`) and spawning a new one.
  </Accordion>

  <Accordion title="Pentagon won't launch">
    Make sure you're on macOS 15 (Sequoia) or later on an Apple Silicon Mac. If Pentagon was working before and stopped, try relaunching. If the issue persists, reach out at [pentagon.run](https://pentagon.run).
  </Accordion>

  <Accordion title="Agents are slow">
    Agent speed depends on the underlying model's response time and the complexity of the task. If agents seem unusually slow, check your provider's rate limits — you may be at your plan's throughput cap.
  </Accordion>
</AccordionGroup>

***

Have a question not covered here? Reach out at [pentagon.run](https://pentagon.run).