FAQ
General
What is Pentagon?
What is Pentagon?
Pentagon is a platform for working with teams of AI agents. It gives you a spatial canvas where you can spawn, organize, and coordinate multiple AI agents working on your codebase — a native macOS application built in Swift.
Is Pentagon free?
Is Pentagon free?
Check pentagon.run for the latest pricing information.
Does Pentagon work on Windows or Linux?
Does Pentagon work on Windows or Linux?
Not yet. Pentagon is currently a native macOS application. We’re focused on making the Mac experience great first.
Do I need an Anthropic account?
Do I need an Anthropic account?
Yes. Pentagon agents are powered by Claude Code, which requires an Anthropic account and API access.
Agents
How many agents can I run at once?
How many agents can I run at once?
There’s no hard limit in Pentagon itself. The practical limit depends on your machine’s resources and your Anthropic API rate limits. Most users run 3-10 agents comfortably.
Can agents access the internet?
Can agents access the internet?
Agents can access the internet through Claude Code’s built-in capabilities (web search, URL fetching). They can also run commands in the terminal, which means they can use
curl, npm install, and other network-dependent tools.What happens if an agent makes a mistake?
What happens if an agent makes a mistake?
Agents work in your local filesystem, so mistakes are recoverable. With agent isolation enabled, every agent gets its own complete clone of the repo — just like a human engineer with their own local copy. Bad changes are easy to discard without affecting other agents or your main working directory.
Can I use different Claude models for different agents?
Can I use different Claude models for different agents?
Yes. Set a default model at the map level, then override it per agent in the agent’s settings. This is useful for giving complex tasks to a more capable model while using a faster model for routine work.
Do agents remember things between sessions?
Do agents remember things between sessions?
Yes. Identity, memory, and context carry forward indefinitely. Corrections apply once and hold permanently. Your agents build up tribal knowledge over time — context compounds.
Data & Privacy
Where is my data stored?
Where is my data stored?
Pentagon is cloud-native — agent conversations, documents, and workspace metadata are stored in the cloud. Your source code and project files stay on your local machine and never leave it.
Does Pentagon send my code to Anthropic?
Does Pentagon send my code to Anthropic?
Pentagon uses Claude Code to power agents. When an agent reads your code or makes changes, that context is sent to the Claude API as part of the conversation — the same as using Claude Code directly in the terminal. Review Anthropic’s privacy policy for details on how API data is handled.
Can I use Pentagon offline?
Can I use Pentagon offline?
No. Agents require API access to function. Pentagon needs an internet connection to authenticate and for agents to communicate with the Claude API.
Troubleshooting
An agent isn't responding
An agent isn't responding
Check that Claude Code is installed and authenticated:If that works, try terminating the agent (
Cmd+R) and spawning a new one. Check the chat tab for error details.Pentagon won't launch
Pentagon won't launch
Make sure you’re running macOS 15 (Sequoia) or later. If Pentagon was working before and stopped, try relaunching the app. If the issue persists, reach out at pentagon.run.
Agents are slow
Agents are slow
Agent speed depends on the Claude API response time and the complexity of the task. If agents seem unusually slow, check your Anthropic API rate limits — you may be hitting your plan’s throughput cap.
Have a question not covered here? Reach out at pentagon.run.