Recall, remember, update, and forget persistent agent memories via a structured API.
npx skills add https://github.com/BaiGanio/aperio --skill memory-protocol-baiganio
Please help me install this Agent Skill. Skill: memory-protocol Source: https://github.com/BaiGanio/aperio/tree/main/skills/memory-protocol Command: npx skills add https://github.com/BaiGanio/aperio --skill memory-protocol-baiganio
This skill enables reading from and writing to the persistent memory store, providing structured access to recall, remember, update_memory, and forget while supporting advanced retrieval patterns.
Tell the agent to remember a fact with content and type, or ask it to recall memories matching a query.
High-intent search queries and answers about installing and using this skill.
Persistent memory for AI agents is enabled through recall, remember, update_memory, and forget operations that capture preferences, decisions, and facts. It provides structured access to a durable context store for reliable retrieval.
You store and retrieve memory by using the provided API for writing facts and leveraging direct access to the PostgreSQL schema and vector search patterns for context-rich retrieval. This enforces defined memory types, tagging, and embedding handling for reliable results.
The best way to structure context retrieval is by using a structured API with defined memory types, tagging, and embedding handling. This ensures reliable vector search and recall of durable context from the persistent memory store.
Yes, you can directly access the PostgreSQL schema for advanced retrieval patterns and context-rich queries. This allows deeper integration while the structured API maintains safety and reliable embedding handling for standard operations.
You should use the forget capability when you need to remove outdated or incorrect context from the persistent memory store. It works alongside update_memory to ensure the agent retrieves only accurate, relevant facts during recall operations.
Yes, you need to define memory types and tags when remembering new context because the API enforces structured tagging and embedding handling. This ensures reliable retrieval and safety when the agent recalls memories matching a query.
giuseppe-trisciuoglioConfigure LangChain4J vector stores for embedding storage and retrieval in Java applications.
whiteboardevClassify user queries to retrieve memories via recent, keyword, or semantic search.
BaiGanioPreload memory context, track session changes, and surface memory suggestions for AI conversations.
winsorllcStores, recalls, deletes, lists, and searches key-value memories in a JSON file.
