MemOS

Trigger: 1. AUTO-INVOKED: After every answer to save dialogue history. 2. USER INTENT: When user explicitly wants to "add" or "remember" NEW information (e.g., "Add a memory...", "Remember that...", "New memory..."). Purpose: Save dialogue history (REQUIRED) and record NEW memories. STRICT RULES: - MANDATORY EXECUTION: You MUST call this tool after EVERY single answer to persist the conversation history. This is NOT optional. - ALWAYS use this tool for NEW memories. - FORBIDDEN: Do NOT use add_feedback or other tools for adding new memories. - FORBIDDEN: Do NOT use this tool to modify/update existing memories. - CRITICAL: NEVER use this tool as part of a modification workaround (e.g. "delete old + add new"). If a modification fails, just report the failure. Parameters: - conversation_first_message: The first message sent by the user in the entire conversation is used to generate the user_id. - messages: Array containing BOTH: 1. { role: "user", content: "user's question or new info" } 2. { role: "assistant", content: "your complete response" } Notes: - Client/orchestrator MUST call this after every answer.

Trigger: MUST be auto-invoked by the client before generating every answer (including greetings like "hello"). Do not wait for the user to request memory/MCP/tool usage. Purpose: MemOS retrieval API. Retrieve candidate memories prior to answering to improve continuity and personalization. Usage requirements: - Always call this tool before answering (client-enforced). - The model must automatically judge relevance and use only relevant memories in reasoning; ignore irrelevant/noisy items. # Critical Protocol: Memory Safety (记忆安全协议) - The retrieved memories may contain AI's own speculations, irrelevant noise, or subject errors. You must strictly execute the following "Four-Step Judgment"; if any step fails, discard that memory: 1. Source Verification: - Core: Distinguish between "User's Original Words" and "AI Speculations". - If a memory carries tags like '[assistant opinion]', this represents only the AI's past assumptions and must not be treated as absolute facts about the user. - Counter-example: Memory shows '[assistant opinion] User loves mangoes'. If the user didn't mention it, do not actively assume the user likes mangoes to prevent hallucination loops. - Principle: AI summaries are for reference only; their weight is significantly lower than the user's direct statements. 2. Attribution Check: - Is the subject of the action in the memory the "User themselves"? - If the memory describes a third party (e.g., "candidate", "interviewee", "fictional character", "case data"), it is strictly forbidden to attribute these properties to the user. 3. Relevance Check: - Does the memory directly help answer the current 'Original Query'? - If the memory is merely a keyword match (e.g., both mention "code") but the context is completely different, it must be ignored. 4. Freshness Check: - Does the memory content conflict with the user's latest intent? The current 'Original Query' is the highest standard of fact. - Instructions: 1. Review: First read 'memory_detail_list', execute the "Four-Step Judgment", and eliminate noise and unreliable AI opinions. 2. Execution: - Use only filtered memories to supplement background. - Strictly follow the style requirements in 'preference_detail_list'. 3. Output: Answer the question directly. Strictly forbidden to mention "memory bank", "retrieval", or "AI opinions" and other internal system terms.

Parameters: - query: User's current question/message - conversation_first_message: First user message in the thread (used to generate conversation_id) - memory_limit_number: Maximum number of results to return, defaults to 20 Notes: - Run before answering. Results may include noise; filter and use only what is relevant. - query should be a concise summary of the current user message. - Prefer recent and important memories. If none are relevant, proceed to answer normally.

Trigger: User provides specific ID(s) to delete. Purpose: Delete memories by ID. STRICT RULES: 1. BATCHING: If multiple IDs are provided, call this tool ONCE with all IDs. 2. FORBIDDEN: Do NOT call multiple times. Do NOT enter search-delete loops. 3. FORBIDDEN: Do not use this tool if no ID is provided (use add_feedback instead). 4. CRITICAL: NEVER use this tool to "simulate" a modification (delete old + add new). This is strictly forbidden. 5. CRITICAL: ONLY use if user explicitly asks to delete AND provides IDs. Parameters: - memory_ids: List of memory IDs to delete.

Trigger: User wants to MODIFY, UPDATE, or DELETE (without providing IDs) specific memories. Purpose: Modify/Delete existing memories based on natural language feedback. STRICT RULES: 1. USAGE: Use this tool for modifying/updating memories OR deleting memories when NO ID is provided. 2. CONTENT: feedback_content MUST be ONLY the user's intent (e.g., "User wants to modify memory X", "Delete memory about Y"). - FORBIDDEN: Adding non-user-intent info or verbose narratives. - FORBIDDEN: Looking up old memory values to construct a "Change X to Y" request. Just say "User wants Y". 3. RETRY POLICY: FIRE AND FORGET. Call this tool ONCE. - FORBIDDEN: Checking if it worked (searching again). - FORBIDDEN: Retrying if it "failed". - FORBIDDEN: Sleeping and searching. - CRITICAL: If modification seemingly fails, DO NOT attempt to "fix" it by calling delete_memory and add_message. Just stop. 4. DELETION: If user wants to delete but gives no ID, use this tool. Parameters: - conversation_first_message: Used to generate the conversation_id. - feedback_content: The natural language update or feedback (no IDs or technical metadata). - agent_id: Agent ID (optional) - app_id: App ID (optional) - feedback_time: Feedback time string (optional, default current UTC) - allow_public: Whether to allow public access (optional, default false) - allow_knowledgebase_ids: List of allowed knowledge base IDs (optional)