Phoenix V2: A Cognitive Architecture for AI That Remembers, Feels and Evolves — Paper, Code and Book

Описание и применение

Phoenix V2 – это локальная архитектура ИИ, которая хранит память и эмоциональный контекст в SQLite, позволяя ассистенту сохранять отношения с пользователем даже после обновления модели.

Задача

AI assistants lose context when the model is updated, causing loss of persistent memory and relationship with the user.

Результат

Phoenix V2 enables a persistent, emotionally‑aware AI assistant that survives model updates, runs on legacy hardware, and keeps all user data locally.

Рабочий процесс

• 1. Store user messages and retrieved memories in a local SQLite database.
• 2. Retrieve relevant memories using semantic similarity, recency, and importance scoring.
• 3. Build a structured prompt with current message, memories, emotional state, and self‑model.
• 4. Send prompt to the LLM for reasoning (single API call).
• 5. Apply local heuristic to draft response; if flagged, revise via LLM.
• 6. Modulate tone with Personality Agent based on affective state.
• 7. Periodically run SubconsciousEngine to consolidate memories and update beliefs.
• 8. Persist all changes back to SQLite; only text of messages and embeddings are sent to external APIs.

Доказательства

All persistent state — every memory, every emotional context, the system's model of who you are — lives outside the LLM, in a local SQLite database on your machine.

Источник

The entire pipeline requires no GPU. Embedding generation uses a remote API call. LLM calls go to whichever provider you configure — the client is a single file, and swapping providers is a one-line change.

Источник