How do I give my LLM workflow persistent context across independent client connections?

Описание и применение

Контекст LLM, привязанный к соединению, теряется при новом подключении. Хранение контекста под стабильной идентичностью (пользователь, проект) и чтение его в начале каждого соединения обеспечивает постоянный контекст между независимыми клиентами.

Задача

An LLM workflow loses context when a new client connection is made, because context was keyed to the connection or session.

Результат

By storing context under a stable identity and reading it at the start of each connection, the LLM workflow retains persistent context across independent client connections.

Рабочий процесс

• 1. Scheduled job connects to MCP server at 06:00 and writes context under the user/project identity using the Mnemoverse API.
• 2. Chat client connects at 10:00, authenticates with the same API key or OAuth token, reads context from the identity‑scoped store before acting.
• 3. Agent uses the retrieved context to answer queries about duplicate tickets.

Доказательства

Context kept under that ID could be found only by requests that carried the same ID, which means only inside the same session.

Источник

The 2026-07-28 revision drops the session: the first major change in its changelog is "Remove protocol-level sessions and the Mcp-Session-Id header from the Streamable HTTP transport".

Источник

Memory is scoped to the account behind the key and that "two keys from the same console account share one memory".

Источник

Sign in again with the same Mnemoverse account and everything is back, unchanged.

Источник