Add a new short-term memory entry from recent conversation messages. The memory will be indexed by keywords and scored based on relevance over time.

Search and retrieve relevant short-term memories based on recent conversation context. Returns top relevant, next relevant, and random flashback memories.

Delete short-term memories matching a keyword or regex pattern.

Get statistical information about short-term memories.

Manually trigger cleanup of old or low-relevance short-term memories. This removes memories older than 1 year or with very low relevance scores, keeping at least 512 memories.

Get the most frequently mentioned conversation ID in memories.

Add a new long-term memory with a trigger condition. The trigger is JavaScript code that determines when this memory should be activated. Available context: context.messages (array), context.conversation_id (string), context.participants (object). Available functions: match_keys(messages, keywords, scope, depth), match_keys_all(messages, keywords, scope, depth).

Update an existing long-term memory. You can update the trigger condition, prompt content, or add update context.

Delete a long-term memory by name.

List all long-term memory names and their basic information.

Search and activate relevant long-term memories based on current conversation context. Returns activated memories (whose triggers evaluated to true) and random memories for serendipity.

Get the creation and update context of a specific long-term memory.

將指定對話的所有記憶備份到文件。支持導出短期和長期記憶，包含完整的元數據和時間戳。

從備份文件還原記憶。警告：這將覆蓋當前對話的所有記憶。

列出可用的備份文件

刪除指定的備份文件

使用高級過濾條件搜索記憶。支持關鍵詞、時間範圍、分數過濾等。

分析記憶使用模式，提供統計信息和洞察

獲取服務器健康狀態和性能指標

獲取服務器性能指標

獲取查詢緩存統計信息