Personal context profile
Creed stores your context as a single Markdown profile that AI agents read before they answer. The file is meant to hold durable information such as values, goals, preferences, routines, and constraints.
Creed
Creed is a personal context profile for AI agents that keeps your durable preferences, goals, and boundaries in one Markdown file. It helps connected tools like Claude Code, Cursor, ChatGPT, and Codex read the same up-to-date context before they respond.
What Creed is
Creed is a personal context profile for AI agents. It keeps one shared, up-to-date Markdown file with the durable details that help tools answer consistently: who you are, what you are working toward, how you prefer AI to respond, and the boundaries or routines that matter.
The product is built around a simple workflow: agents read your Creed before responding, propose precise updates when they learn something lasting, and either wait for your approval or write directly if you trust them. Creed can be self-hosted for free, or used as a hosted service with sync, backups, and managed storage.
Core capabilities
MCP-based agent connections
Agents can read your Creed over MCP, so the same profile can travel across connected tools instead of living inside one chat app.
Inline diff updates
When an agent learns something durable, it can propose a precise edit as an inline diff. You can review the change before it lands in the profile.
Section scoring and review
Creed scores sections for signal, specificity, and weak spots so the profile stays concise and easier for agents to use.
Hosted sync and managed storage
Hosted plans add cross-device sync, backups, and managed backend, auth, and storage.
Usage credits and BYOK
Hosted plans include monthly usage credits for AI analysis and agent work, with BYOK support if you want model spend on your own key.
Common ways to use Creed
Use the same context across multiple AI tools
Keep one stable profile that tools such as Claude Code, Codex, Cursor, and ChatGPT can read before they respond, so your preferences and constraints follow you across conversations.
Prime a new agent with your rules
Store working style, routines, boundaries, and preferences in one file so a new agent can start with your actual defaults instead of a generic prompt.
Review and maintain a living context file
Let agents propose diffs when they learn something durable, then approve or reject updates so the profile evolves without becoming a chat transcript.
Share context with a team
Use the Company plan when a team needs a shared Company Creed, member roles, and an activity view instead of separate personal profiles.
Pros and Cons
Pros
- One profile can be read by multiple connected AI tools, which helps avoid re-explaining context in each app.
- Creed is plain Markdown and exportable, so the source emphasizes portability and ownership.
- Agents can suggest durable edits instead of forcing you to rewrite the profile manually every time something changes.
- The profile is designed to stay concise and specific, with scoring that surfaces thin or vague sections.
- Self-hosting is available at no cost, while hosted plans add sync, backups, and managed infrastructure.
Cons
- The source material does not show a complete published integration list beyond MCP connections and GitHub, so platform coverage is still partially documented.
- Hosted plans include usage credits, but the source does not give a full breakdown of how much AI work a given workflow will consume in practice.
- Teams can use Creed through the Company plan, but the page gives limited detail on collaboration workflows beyond shared context, member roles, activity views, and admin controls.
FAQ
What is Creed built from, and can I export it?
Creed is a personal context profile made of plain Markdown. You can export it at any time, and the site says there is no lock-in.
Which tools does Creed connect to?
Creed connects to agents like Claude Code, Codex, Cursor, and ChatGPT over MCP. The site also says GitHub integration is available for version control, with Notion and Obsidian support on the way for editing and storage.
Do I have to approve every agent edit?
You can keep proposed edits reviewable, or let trusted agents write directly. Creed is designed so agents propose durable changes and you decide how much approval you want in the loop.
Is Creed free?
Yes. The pricing page says Creed is open source and free to self-host, while hosted plans start at $12 per month for Personal and $129 per month for Company.
Is Creed only for individuals, or can teams use it too?
Creed starts as a personal profile. The Company plan adds a shared Company Creed, member roles, an activity view across the team, and admin controls.
Quick Facts
- Category
- AI context management
- Primary use
- Shared personal context for connected agents
- Format
- Plain Markdown
- Connection method
- MCP
- Source domain
- creed.md
- Pricing shape
- Free self-hosted; hosted Personal and Company plans available
Alternatives à Creed
Goldfish
Goldfish is an AI memory app for macOS that helps you reply, write, summarize, and continue using the context already on your Mac. It stores memory locally and writes in your tone.
Dcyde
Dcyde is a decision log for product teams that captures what was decided, the reasoning behind it, and the source in one shared place. It supports pinning decisions from Slack, Figma, or inside Dcyde and keeps the record searchable over time.
Lasso
Lasso is an ecommerce product data platform for enriching catalog records, processing supplier files, generating product content, and monitoring competitors. It combines a web app with a REST API, SDK, and MCP server for teams and developers.
Biji
Biji est une plateforme polyvalente conçue pour améliorer la productivité grâce à des outils et des fonctionnalités innovants.
Struere
Struere is an AI-native platform for turning spreadsheet data into structured operational software with dashboards, alerts, and automations. It is aimed at teams that want to replace manual spreadsheet workflows without building custom tools from scratch.
garden-md
garden-md is an open-source Node.js CLI that turns meeting transcripts into a local company wiki. It links entities across transcripts, keeps the original text intact, and renders the result as a browsable wiki.