Roadmap
Version 0.10 is the first release: she runs on your machine, talks, and does things. This is what grows next, in roughly the order of work, and the shorter list of what she is never going to do.
No dates are promised. The order is roughly the order of work, and that is the strongest claim anyone here can make about it.
Pick a voice from a list
A dropdown of the voices your key can actually use, instead of leaving the app to find an ElevenLabs voice ID and pasting it in.
More brains, by name
Providers listed by name with their models and what each one costs, the way OpenAI and xAI already are — not a base URL and a model name typed by hand.
A voice that costs nothing
A local speech engine on your own machine, so ElevenLabs stops being the one thing between Kotoba and someone who just wants to try her.
The full terminal on Windows
The commands run there today; the interactive session does not. Making it native is a piece of work, not a patch.
Saying no to one command
“Never run rm, don’t ask” while keeping the rest of the toolset — today you can only switch a whole toolset off.
A desktop app
One window, no browser tab, no terminal.
Cut on purpose
These are deliberate absences, written down so nobody waits for them. They are not leaves on the branch; they were cut, and the cut has healed over.
A hosted version you sign intoPruned. Not planned, now or later.
Kotoba is self-hosted. Your keys and your conversations stay on your machine; there is no account and no server run by anybody else.
Shipping a Live2D model in the repositoryPruned. Not planned, now or later.
Models belong to their authors. The first-run screen fetches one onto your machine instead, so this is not a gap waiting to be closed.
TelemetryPruned. Not planned, now or later.
Not now, not later.