llms.txt
# Command Center
> Command Center (cc.dev) is a desktop app for running AI coding agents such as Claude Code, Codex, and OpenCode in parallel workspaces, then understanding their changes with guided code walkthroughs and cleaning them up with refactoring agents before merge.
- Website: https://www.cc.dev
- Platforms: macOS, Windows, Linux desktop app; download from https://www.cc.dev
- Use it as a skill inside an existing coding agent: `npx skills add command-center-ai/skills`
- Contact: contact@cc.dev
## Pricing
- Free: $0/month ($0/year). 3 all-time workspaces; 3 simultaneous workspaces; 1 walkthrough / day (plus first-day bonus credits); 1 refactoring / day (plus first-day bonus credits); 10 CC Basic coding agent prompts / day; Community Discord support.
- Starter: $9/month ($89/year). Unlimited all-time workspaces; 4 simultaneous workspaces; 4 walkthroughs / day; 4 refactorings / day; Unlimited CC Basic coding agent prompts; Email support.
- Pro: $19/month ($189/year). Unlimited all-time workspaces; Unlimited simultaneous workspaces; Unlimited walkthroughs; Unlimited refactorings; Unlimited CC Basic coding agent prompts; VIP support.
## Pages
- [Pricing](https://www.cc.dev/pricing): plans and limits
- [Examples](https://www.cc.dev/examples): real-world refactoring examples
- [Changelog](https://www.cc.dev/changelog): what is new in each release
- [Codebase Understanding](https://www.cc.dev/blog/codebase-understanding): the learning science behind code walkthroughs
- [Privacy](https://www.cc.dev/privacy): what we do and do not do with your data
## Comparisons
- [Command Center vs Codex](https://www.cc.dev/compare/codex): Command Center and the ChatGPT/Codex app both run coding agents against your repository. Command Center runs Claude Code, Codex, and OpenCode side by side and is built around reviewing, understanding, and refactoring the code they write. The Codex app runs one top-level Codex agent per task inside a chat window. Choose Command Center to get production-quality code out of many agents; choose the Codex app if you want a single OpenAI-only agent, or agents that are not tied to a codebase.
- [Command Center vs the Claude app](https://www.cc.dev/compare/claude-app): Command Center and the Claude app both run coding agents against your repository. Command Center runs Claude Code, Codex, and OpenCode side by side and is built around reviewing, understanding, and refactoring the code they write. The Claude app runs one Claude Code session per task inside a chat window. Choose Command Center to get production-quality code out of many agents; choose the Claude app if you want a single Anthropic-only agent, or agents that are not tied to a codebase.
- [Command Center vs Conductor](https://www.cc.dev/compare/conductor): Command Center and Conductor both run coding agents in parallel git worktrees. Command Center runs Claude Code, Codex, and OpenCode on macOS, Windows, and Linux with no cap on agents per workspace. It is focused on giving you production-ready code, and adds walkthroughs and a refactoring agent for the code they produce. Conductor is a macOS app focused on helping you generate code without aiding you in improving the quality. It offers cloud workspaces and a tab limit per workspace. Choose Command Center to run many agents and polish their output; choose Conductor if you want cloud workspaces or identify as a vibe-coder.
- [Command Center vs HumanLayer](https://www.cc.dev/compare/humanlayer): Command Center and HumanLayer both aim to get production-quality code out of coding agents, but they disagree on how. HumanLayer prescribes a fixed chain of planning skills and uploads your diffs to its servers for review and sharing. Command Center keeps your code on your machine, lets you run any agent with any skill, and focuses on the diff viewer, walkthroughs, and refactoring agent you use after the code exists. Choose Command Center for local, multi-agent development; choose HumanLayer if you want an on-rails planning workflow and team sharing before the pull request.
## FAQ
### Is my code private?
Command Center runs locally and does not send your code to our servers. If you use our free Gemini credits, your AI requests pass through our servers but are not retained. Bring your own key or subscription and everything stays private.
### What do I need to run Command Center?
Basically nothing. It is built for a wide range of developer environments and skill levels, and ships with both git and a modified version of OpenCode — so you can start building even on a completely unconfigured Windows box. It optionally uses your own coding agent.
### Which coding agents does Command Center support?
Claude Code, Codex, and OpenCode. It also works with the deprecated Gemini CLI, and ships its own version of OpenCode (dubbed CC Basic) so you can start right away.
### How does your pricing work?
There's a free tier to get started, with limits on walkthroughs, refactoring, and the number of simultaneous workspaces. Paid plans — Starter ($9/mo) and Pro ($19/mo) — unlock higher limits. See the pricing page for the full breakdown.
### How does signing in work?
To get your Command Center online, sign in with Google or GitHub. We use the name and email address associated with your chosen account only to create your Command Center account, authenticate you, and connect your device.
Authentication occurs through your chosen provider's authorization flow, and Command Center never receives your Google or GitHub password. We do not sell this information or use it for advertising.
### What's the learning science behind how walkthroughs work?
Glad you asked — here is [an explainer we did](https://x.com/0xjimmyk/status/1873357324229984677).
### How is Command Center different from Codex, the Claude app, Conductor, or HumanLayer?
Mostly in what happens after the code is generated: Command Center coordinates many agents per task and focuses on revising, understanding, and refactoring what they write. We keep a specific comparison page for each: [vs Codex](https://www.cc.dev/compare/codex), [vs the Claude app](https://www.cc.dev/compare/claude-app), [vs Conductor](https://www.cc.dev/compare/conductor) and [vs HumanLayer](https://www.cc.dev/compare/humanlayer).
