Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
No arguments | |||
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| add_short_term_memory | 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_short_term_memories | 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 | Delete short-term memories matching a keyword or regex pattern. |
| get_memory_stats | Get statistical information about short-term memories. |
| cleanup_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_frequent_conversation | Get the most frequently mentioned conversation ID in memories. |
| add_long_term_memory | 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_long_term_memory | Update an existing long-term memory. You can update the trigger condition, prompt content, or add update context. |
| delete_long_term_memory | Delete a long-term memory by name. |
| list_long_term_memories | List all long-term memory names and their basic information. |
| search_long_term_memories | 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_memory_context | Get the creation and update context of a specific long-term memory. |
| backup_memories | 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。 |
| restore_memories | 從備份文件還原記憶。警告：這將覆蓋當前對話的所有記憶。 |
| list_backups | 列出可用的備份文件 |
| delete_backup | 刪除指定的備份文件 |
| search_memories | 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。 |
| analyze_memory_patterns | 分析記憶使用模式，提供統計信息和洞察 |
| health_check | 獲取服務器健康狀態和性能指標 |
| get_metrics | 獲取服務器性能指標 |
| get_cache_stats | 獲取查詢緩存統計信息 |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
| remember-user-info | Store important user information in long-term memory |
| recall-context | Search for relevant memories based on current conversation |
| create-reminder | Create a conditional reminder that activates based on context or date |
| analyze-conversation | Analyze conversation history and create appropriate memories |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
| Memory System Overview | Overall statistics and health of the memory system |
| Conversations List | List all conversations with stored memories |
| Conversation Statistics | Detailed statistics for a specific conversation |
| Memory Usage Best Practices | Guide on how to effectively use the memory system |