Store and retrieve user memories across conversations with semantic search.
npx skills add https://github.com/nirholas/agenti --skill memory-nirholas
Please help me install this Agent Skill. Skill: memory Source: https://github.com/nirholas/agenti/tree/main/packages/protocols/x402-cloddsbot/src/skills/bundled/memory Command: npx skills add https://github.com/nirholas/agenti --skill memory-nirholas
Persistent memory across conversations helps AI assistants remember user preferences, facts, and notes, enabling more personalized, efficient interactions over time.
Store a memory using a memory command with a supported type, key, and value, then retrieve it with a recall command.
High-intent search queries and answers about installing and using this skill.
Semantic search retrieves relevant memories across conversations by matching meaning rather than exact keywords. It builds context quickly by finding related facts, notes, or preferences stored in the database.
Yes, you can use PostgreSQL, SQLite, or LanceDB as backends for the memory service. These databases support the CRUD operations and semantic retrieval needed for cross-session recall.
You can store multiple memory types for cross-session recall, including facts, notes, preferences, context, rules, and profiles. This enables use cases like daily journaling and persistent user profiling.
Store a preference using a memory command with a specified type and key-value pair, then retrieve it later with a recall command. This process uses semantic search to find relevant stored preferences efficiently.
Yes, persistent memory supports daily journaling by storing notes and context across sessions. You can retrieve these journal entries using semantic search to improve conversation quality over time.
shreed27Store, recall, and search persistent user data with a TypeScript API.
Toperythroblast876Search the ourmem shared memory store for relevant stored memories via semantic search.
bcastelinoDesign and optimize RAG systems for LLM applications.
cxnaiveStore and retrieve conversation context using Pinecone vector databases.
