muninn-memory
от phillipneho
Search & ResearchКратко
Memory system for AI agents.
Описание
Что делает этот навык
Local-first memory system for AI agents that stores episodic, semantic, and procedural memories in a SQLite database. Uses Ollama for local embeddings to enable hybrid BM25 and semantic search. All data stays on the user's machine with no external network calls.
Runs entirely locally with no API keys or cloud dependencies, and scores 93% on the LOCOMO benchmark compared to 66.9% for Mem0.
Когда его использовать
- Persisting user preferences across agent sessions
- Recalling past meeting notes by topic or person mentioned
- Building a knowledge base from ongoing conversations
- Tracking project context across long-running tasks
- Storing step-by-step workflows for later retrieval
Пример сценария
User asks: 'Remember that I met with Sarah about the Q3 roadmap today'
- 1
Initializes MemoryStore with the local SQLite database
- 2
Calls remember() with type 'episodic' and entities ['Sarah', 'Q3 roadmap']
- 3
Assigns a salience score and stores the memory
- 4
On follow-up 'What did I discuss with Sarah?', calls recall() with hybrid BM25 and semantic search
- 5
Returns ranked results with entity-boosted relevance
The Q3 roadmap meeting memory is retrieved and surfaced to the agent
Требования
- Ollama installed and running locally
Установка
clawhub install phillipneho/muninn-memoryВыполните команду CLI или вставьте промпт в Claude Code, Cursor, Codex — любой кодинг-агент, которым пользуетесь.