Coredence

Roadmap

What is next, and what is not happening

Dates are not promised. The order is, and so is the list of things that have been considered and turned down — that half is usually more useful.

Being built now

  • Handing the identity to your assistant

    An MCP server, running on your machine, that lets the tools you already use read the identity. It is a local process the client starts over stdio: no network, no account, no key. This is the piece the whole product is for.

  • Choosing what an assistant sees

    Not every rule belongs in every conversation. A way to say which layers and which subjects go out, per client.

After that

  • Windows

    The part that reads your work is already portable — same code, every platform. It is the window that draws the identity that has to be built again, and it is the most asked-for thing here.

  • Watching the identity change

    The rules move as you do. A view of what appeared, what faded and what contradicted itself over a month is a different product from a snapshot.

  • Freshness as a colour

    The engine records when a rule was last seen. Nothing on screen uses it yet, so an identity that describes who you were two years ago looks exactly like one that describes today.

  • Sharing a slice, deliberately

    Handing one subject or one layer to somebody else — a collaborator, a new team — without handing over the whole identity.

Decided against

  • An account

    Nothing the product does needs one, and having one would make “it stays on your machine” a thing we ask you to believe rather than a thing you can check.

  • Publishing the engine, for now

    The claims that matter are checkable without it, and more conclusively — lsof and sqlite3 say what is happening rather than what should. Opening later stays possible; closing again would not be.

  • Hosted distillation

    Reading your work on somebody else's computer is the thing this product exists not to do, however much faster it would be.

  • Letting the app write

    The viewer stays read-only. The confidence formula and the requirement that every rule keeps its evidence live in the engine; a second copy inside the app is how the two would start disagreeing about who you are.

  • Guessing to fill gaps

    A thin identity is honest. Padding it with plausible-sounding rules would make the picture look better and the product worthless.

Asking for something

The engine’s issue tracker is the whole process. There is no roadmap board behind a login.