Questions people ask first
Straight answers about seats, billing, data, safety and the AI tools coreCerebrum runs. If yours is not here, email [email protected] and a person from the team replies.
Do I still pay for ChatGPT, Claude or Gemini?
Yes. You keep your own plan or keys and keep paying your AI provider directly. coreCerebrum never resells or marks up your AI usage. Its job is to make that spend go further.
What is the difference between Memory, Build and Studio?
Memory ($30 a user) is team memory and lighter requests for anyone who uses AI to write, research or answer questions. Build ($100) adds agents that run side by side, each in its own safe workspace, plus the developer toolkit. Studio ($200) adds Design DNA for websites, landing pages and presentations, with export and one-click publish.
How do you define an active seat?
A seat that used coreCerebrum that month. A seat that did not costs nothing.
When will my card be charged?
Nothing for 30 days. Your first charge is on day 31, for your active seats. Cancel before then and you will not be charged.
What happens when I want my DNA website live?
Three options. Export it and host it anywhere, included. Publish it to our hosting for a flat monthly price per site. Or hand it to the 'corePHP' team for WordPress builds, integrations, maintenance and security, quoted as a project.
What does Enterprise include?
A custom coreCerebrum built inside your own infrastructure: on-prem, private cloud, AWS GovCloud or Azure Gov. Custom seat pricing, SSO, a security review and a named contact.
What is team memory, and how is it different from the memory in my chat app?
Your chat app remembers one person's preferences. Team memory keeps your whole team's solved work: decisions, conventions and gotchas are captured as you work, de-duplicated, and recalled on the prompt that needs them, so when one person figures something out, everyone can reuse the answer.
Does my code leave my machine?
The board runs locally against your own checkouts, and every agent works in a git worktree that is a normal directory on your disk. The local server only listens on your own machine. When the optional team backend records usage, it sends totals such as token counts and cost, never transcript content.
Is it safe to let several agents run at once?
Each agent works on its own branch in its own worktree, so two agents never edit the same checkout. A guard hook refuses destructive operations before they run, such as force pushes to a protected branch, dropped tables and hardcoded secrets in a write. Every card passes a review gate before it is done.
Can people who never open a terminal use it?
Yes. The Coworker view has no terminal. It offers guided workflows for drafting email, marketing, security, dev requests and Design DNA, plus a chat box that turns a plain request into the right workflow with the fields already filled in.
How does coreCerebrum help me spend less on AI?
Several ways at once. Solved work is recalled from team memory so it is not paid for again. A session that has already read a file is told so before reading it again. A session whose context has grown large raises a warning with the option to compact it. And spend is shown by project and person, so you can see where it goes.
Which AI tools does it run?
Board cards run real Claude Code sessions, and coreCerebrum can connect Cursor to the same team memory. Cowork chat, writing and research can run on Claude Code, Anthropic, OpenAI, Gemini or a custom OpenAI-compatible endpoint. The Reflex launcher can also run local model sessions.
What does it run on?
A desktop app for macOS and Linux that starts the board for you, signed and notarized on macOS with automatic updates. The same board also runs in your browser.
Still deciding?
Give your team one brain this month
Start with a Memory seat at $30 a person, add Build for the people who run agents, and see the difference on your own work. No charge for 30 days.
No charge for 30 days. Your card is billed starting month 2.