ReplayAutonomous app testing for teams who ship at AI-speed
Promoted
Creed
Your personal context file for every agent.
204 followers
Your personal context file for every agent.
204 followers
Personal context for your agents. Creed gives every connected AI a shared, up-to-date understanding of who you are, how you work, and what matters.
"Onboarding a new coworker every session" nails the exact tax I feel — I keep hand-copying the same CLAUDE.md into every new agent I try, and it goes stale the second I update it in one place.
A single portable creed.md that every connected tool reads is the right fix. Curious whether tools pull it in over MCP or need native support — but either way it's something I'd actually keep in my stack.
Nice one @connorhpbrn 👌
the 'onboarding a coworker every session' line nails the tax. as the file grows, does the agent read all of it or learn which parts change its answer?
Dial
the idea of one shared context file across all your agents makes sense, but it also means every connected agent gets the same level of access to everything about you - work style, preferences, whatever else ends up in there. is there any way to scope what a given agent can see, or is it all-or-nothing once you connect it?
Congrats on the launch, Connor. This is a clean fix for the re-explain-yourself-every-time problem - once an agent's connected, does it only see the slice of your profile it needs, or does connecting an agent hand it your whole context file?
Really like this idea — "context that follows you across agents" is something I keep running into as a gap. Is it meant to sync automatically as your preferences change, or do you update the context file manually?
Dial
the staleness/scope/precedence questions above are all the right ones. mine is more boring: if I stop paying or Creed shuts down someday, is the file mine to walk away with in a plain, tool-agnostic format, or does it live in a format/schema that's really only useful inside your own MCP layer? for something meant to be the one identity file every agent reads, portability out feels like it should matter as much as portability in.
The idea of a shared context layer is interesting.
Do you see Creed becoming something every AI agent plugs into, or something users actively manage themselves?