How to Implement Long-Term Memory for AI Companions: Pinning, Compaction, and Lessons from Mem0 and Letta

说明与用途

文章说明了如何使用固定、压缩以及 Mem0 和 Letta 的经验来实现 AI 伴侣的长期记忆。提出了四层上下文结构，用户固定重要事实，系统自动提取并存储摘要和记忆卡。

问题

AI companions often forget user facts when conversations exceed the model’s context window, leading to incorrect or irrelevant responses.

结果

The four‑layer context strategy reduces memory‑related failures, ensuring user‑pinned facts are always present and that long‑term memories are accurately extracted and retrieved.

工作流

• 1. User pins important facts (e.g., allergies) which are stored in a pinned memory layer.
• 2. Every turn the system injects pinned memory into the model’s context.
• 3. Recent messages are kept in a sliding window for immediate context.
• 4. When the conversation window closes, an extraction step creates a medium-term summary and long-term memory cards from the closed window.
• 5. The agent retrieves relevant cards on demand based on the current query.
• 6. Unfinished plans that span beyond the current window are promoted to cards to avoid loss during compaction.

证据

The model suggests peanut butter cookies.

来源

Mem0 keeps memory at user, session, and agent level, so the same store can hold "Alice prefers dark mode" and "this support session is about billing".

来源

Letta answers the three questions very differently from Mem0. Memory belongs to the agent, and the agent edits it itself.

来源

Our context for each reply has four layers: Pinned Memory, Recent messages, Medium‑term summary, Long‑term memory cards.

来源