Configure Exo agent memory backends with conversation_id scoping and embeddings.
npx skills add https://github.com/midsphere-ai/exo --skill exo-memory
Please help me install this Agent Skill. Skill: exo:memory Source: https://github.com/midsphere-ai/exo/tree/main/skills/memory Command: npx skills add https://github.com/midsphere-ai/exo --skill exo-memory
Exo agents require configurable short-term and long-term memory along with persistence to maintain context across conversations. This skill provides a structured guide to configure memory backends (in-memory, SQLite, and vector stores), set up conversation_id scoping, and use embeddings to enable semantic search.
Create an Agent with a configured memory system (short_term, long_term, and persistence) and begin using conversation_id to scope conversations.
High-intent search queries and answers about installing and using this skill.
To configure long-term memory for autonomous agents, you set up persistence backends like SQLiteMemoryStore or ChromaVectorMemoryStore using memory persistence hooks. This enables deterministic memory behavior and maintains conversation context across multiple sessions.
The best way to scope agent memory for multi-session conversations is mapping conversation_id to your memory backends. This supports multi-topic agents by isolating short-term and long-term memory retrieval to specific chat sessions.
Embeddings enable semantic search within agent memory by vectorizing stored context in a ChromaVectorMemoryStore. This allows long-term memory backends to retrieve conceptually similar information rather than relying on exact keyword matches.
Yes, you can use SQLite for agent memory persistence by configuring SQLiteMemoryStore as your memory backend. This replaces default in-memory storage to ensure short-term and long-term agent context survives application restarts.
Yes, Exo agent memory supports configuring both short-term and long-term memory simultaneously through AgentMemory composition. Developers can combine in-memory, SQLite, and vector store backends to achieve deterministic memory behavior.
masteringpants-devSave and retrieve AI agent conversation states via HTTP API endpoints.
AcosmiSearch long-term memory by keyword with semantic retrieval and relevance scores.
flashfoxerDesign and orchestrate meta-skills integrating multiple existing skills.
woody1234567Manages persistent and temporary storage for Deep Agent memory across sessions and threads.
