Creed

Your personal context file for every agent.

Productivity

Artificial Intelligence

GitHub

Tech

Visit WebsiteSee on Product Hunt

What I re-explain constantly isn't identity, it's rules, I keep a project guidelines file (folder structure, naming, "don't put business logic in components") for exactly this reason. But the failure mode I hit isn't staleness, it's silent drift: the agent has the file in context and still doesn't follow it three files deep into a task, and nothing flags that it happened. Does Creed have any way to verify an agent actually adhered to the context vs. just having it available? That gap matters more to me than sync timing.

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.

Love how it puts the user in control of what agents actually know about them, rather than just scraping context behind the scenes. That transparent, opt-in approach feels like the right call for something this personal.

Finally something that fixes the blank stare my AI tools give me every time i ask for help with ongoing projects.

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?

I've been solving this with a hand-maintained AGENTS.md per repo and the drift problem is real — it goes stale the moment my workflow changes. How does Creed handle updates: do I edit the file directly, or does it learn from usage over time? Also curious how you keep one shared context file from bloating once every connected agent starts contributing to 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?

love the idea of giving my agents persistent context, honestly this could save me so much repeating myself across tools. one thing i'd love is a way to mark certain context as time sensitive, like project deadlines or temporary preferences, so the agent doesnt treat them as permanent facts about me six months later.

Portable context is a real need. The line I would want kept sharp is durable facts vs. session guesses: preferences, constraints, and project state should survive across agents, while assumptions need timestamps and an easy way to discard them.

This is clever. How does Creed handle context drift when you update the file mid-session?

The shared context layer is such a smart move. Finally my tools stop making me re-explain my preferences every conversation.

Finally feels like my AI tools are on the same page about my projects. Set it up once and noticed Claude and my other assistants stopped asking the same questions about my role and preferences.

Finally something that actually remembers my preferences across different agents, kind of a relief not to repeat myself constantly. Setup was quick and the context sharing feels pretty seamless so far.

Finally connected my daily tools and the agents actually pick up on context without me repeating myself, which is a relief. Setup was quick.

Honestly love how clean the onboarding is. The way it lets you shape context gradually instead of dumping a giant form on you upfront feels really thoughtful, like the team actually thought about how someone would want to build out their profile without it feeling like a chore.

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?

Went through the site before commenting. The MCP pull is the right delivery choice, since a file fetched before the answer rather than pasted into a prompt is what makes this work across tools instead of inside one.

Andrew asked above whether the agent reads all of the file as it grows. I think the prior question is whether it ever shrinks. Both diffs in your own screenshots add lines and remove none, +18 and +9 with a zero on the other side, and that is the shape every memory product drifts into, because agents are good at noticing what to add and have no instinct for what stopped being true. Accept a year of those and it is a long preamble pulled before every answer, mostly stale, all of it paid for on every call.

So the question: does anything ever propose a deletion? A diff that says this line has not been true for four months, here is why, is the harder thing to build and the thing that keeps the file worth reading.

The other one is precedence. Your own example says ship to production Monday through Thursday. If my Creed says that and a repo's own context file says otherwise, I want to know which one the agent is meant to believe before I connect it to anything real.

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?