people use standalone AI tools
Each tool starts cold unless your context travels with you.

Each tool starts cold unless your context travels with you.
A simple 35 percent estimate across monthly AI users.
Multi-tool users leaving 5,000 useful context tokens behind.
| Native features | ||||
|---|---|---|---|---|
| Context loaded before every answer | ||||
| One human-readable profile | ||||
| Agent changes require approval | ||||
| Section-level edit permissions | ||||
| Plain Markdown is the source | ||||
| Open source and self-hostable |
Before it answers, any agent pulls your Creed over MCP, so you never re-explain who you are, what you're building, or how you like to work.
When an agent notices something durable, it proposes a precise edit. It lands in your Creed as a diff. Approve it and the section updates in place.
Deep work 7 to 11am, no meetings before noon.
Review the week every Friday at 4pm.
Ship to production Monday through Thursday only.
Open Activity to see what changed, who changed it, and whether it was accepted, rejected, or edited directly.
Agents propose updates in real time, but nothing changes until you approve it.
Agents can update your Creed without review, keeping your context current as you work.
Score every section for signal, weak spots, and what to sharpen next.
Search, ask, and let Creed draft reversible edits without leaving the file.
Press Tab and it finishes the thought in your voice, drawn from your whole file.
Answer a few quick questions and Creed drafts your starter profile.
Pull the context you've already built across your tools into one profile.
Give each agent the same approved context through Creed's MCP connection.
Who you are, what you're working toward, how you like AI to talk to you, the people and routines that shape your week, plus any health, accessibility, or hard noes AI should respect. One concise profile, not a journal.
Because it doesn't stick, doesn't cross tools, and you end up repeating yourself. Creed gives every AI the same profile to read before answering, and lets them propose updates as they learn more about you.
Creed connects to agents like Claude Code, Codex, Cursor, and ChatGPT over MCP, and integrates with GitHub for version control. Support for tools like Notion and Obsidian is coming for editing and storage.
Durable things AI learns about you, a sharper preference, a new routine, a goal that shifted. Not session recap, not mood, not generic praise.
No. You can keep agent edits reviewable, or trust them to write directly when you want a lighter loop. The point is control when you want it, not friction by default.
Creed Open v1 is built for one owner and Personal Creeds. Shared Creeds are being developed for Creed Cloud and are listed on the roadmap.
