{"id":6877,"slug":"nikitacometa/mnemon-mcp","name":"mnemon-mcp","description":"Persistent layered memory for AI agents — 4-layer model, FTS5 search, fact versioning, EN+RU stemming. Local-first, zero-cloud, single SQLite file.","category":"database","github":"https://github.com/nikitacometa/mnemon-mcp","homepage":"","server_url":"","transport":"http","install":[{"cmd":"npm install -g mnemon-mcp","imports":[]}],"tools":[{"name":"memory_add","description":"Store a memory with layer, entity, confidence, importance, and optional TTL"},{"name":"memory_search","description":"Full-text or exact search with filters by layer, entity, date, scope, confidence"},{"name":"memory_update","description":"Update in-place or create a versioned replacement (superseding chain)"},{"name":"memory_delete","description":"Delete a memory; re-activates its predecessor if any"},{"name":"memory_inspect","description":"Get layer statistics or trace a single memory's version history"},{"name":"memory_export","description":"Export to JSON, Markdown, or Claude-md format with filters"},{"name":"memory_health","description":"Run diagnostics: expired entries, orphaned chains, stale memories; optionally GC"},{"name":"memory_session_start","description":"Start an agent session — returns session ID for grouping memories"},{"name":"memory_session_end","description":"End a session with optional summary; returns duration and memory count"},{"name":"memory_session_list","description":"List sessions with filters by client, project, or active status"}],"env_vars":["MNEMON_EMBEDDING_API_KEY","MNEMON_OLLAMA_URL","MNEMON_AUTH_TOKEN","MNEMON_PORT"],"auth_type":"none","official":false,"stars":2,"status":"active","source":"mcpservers.org","created_at":"2026-05-25T14:14:48.788596+00:00","updated_at":"2026-05-28T12:43:15.008501+00:00","tags":[],"path":"mnemon-mcp"}