The problem: when switching between AI assistants, context must be rebuilt from memory, causing friction and loss of fidelity.
Segue allows saving a working context (brief, notes, plans) in one AI and getting a short, pronounceable handle (e.g., 'brelavo') that can be passed to another assistant.
The second AI loads the context via the handle, picking up exactly where the user left off — no copy-paste or re-explaining.
Handles are three syllables, case-insensitive, and unique within a user's account; they are meaningless outside that account.
Segue is a neutral relay using the Model Context Protocol (MCP) and OAuth, connecting any MCP-capable AI (Claude, ChatGPT, Cursor, etc.).
Users control all transfers: saves and loads are explicit, and nothing syncs without user action.
Data is readable, editable, searchable, and exportable as .md files; no lock-in format.
Free plan includes full access to load, edit, export, and delete data; paid plans only add headroom for storage.