Your personal contextall in one place

Your personal information is valuable.It should stay in your control.Creed gives it back to you.

How it works

Every agent reads it first

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.

Plan my week so I actually ship Helm v2.
Read Creed
Thought for 4s
Blocking7to11amfordeepwork,nomeetingsbeforenoon,andWednesdaysstaycall-free.IlinedtheweekuparoundtheHelmv2beta.Wantitdaybyday?
Ask anything…

It updates as it learns

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.

Routines
  • Deep work 7 to 11am, no meetings before noon.

  • Review the week every Friday at 4pm.

  • Ship to production Monday through Thursday only.

·+10

And every change is visible

Open Activity to see what changed, who changed it, and whether it was accepted, rejected, or edited directly.

chamath.md
Goals
Work

Review everything or nothing

·+11

You control what gets remembered.

Agents propose updates in real time, but nothing changes until you approve it.

Require approval for agent edits
BeliefsDirect
Codex·+113w ago
Keep the file large and exhaustive. Capture every passing preference so nothing is left out. Retain details that stopped mattering months ago. Treat completeness as more important than signal.
Keep the file tight and high-signal. Prune stale detail so the file stays sharp. Trust that less is more. Prefer a short true file over a complete one.

Let trusted agents write directly.

Agents can update your Creed without review, keeping your context current as you work.

Models <inside> the file

Identity
/ 100
SpecificConcreteThinVague
Scoring this section…
Reads like a real person
Names the shared, the role, and where you are.
One line stays generic
Tighten the opener so it could only describe you.
Contains a stray line
A leftover scratch note near the end reads like noise.

Analysis

Score every section for signal, weak spots, and what to sharpen next.

Panel

Search, ask, and let Creed draft reversible edits without leaving the file.

Preferences
Tab

Tab

Press Tab and it finishes the thought in your voice, drawn from your whole file.

Works with your stack

ChatGPT
ChatGPT
Claude
Claude
Grok
Grok
OpenClaw
OpenClaw
Hermes
Hermes
Cursor
Cursor
OpenCode
OpenCode
Devin
Devin
Codex
Codex
Claude Code
Claude Code
Replit
Replit
Whirl
Whirl
v0
v0
Custom
Custom

Dumb questions

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.