$ loading_
Add selective persistent memory for AI agents with structured recall and decay.
Copy the install command and let the AI configure it · recommended for beginners
No copy-paste install info for "sostenuto" yet — see the docs or source repo.
Use sostenuto to store this user's long-term preferences: prefers concise answers, Chinese by default, and is interested in AI products and automation tools; prioritize these preferences in future relevant conversations and decay their weight after 30 days without reinforcement.
The tool stores structured preference memories and recalls them later with time-based decay.
Store "The team holds the product sync every Monday at 10 AM" in sostenuto, and automatically reinforce this memory whenever the user mentions it again so it ranks higher in future recall.
The tool creates a reinforceable factual memory whose retrieval relevance increases with repeated mentions.
Use sostenuto to retrieve past memories related to "budget approval workflow," prioritizing items that are recent and frequently reinforced, then summarize them in bullet points.
The tool returns a summary of memories ranked by relevance, reinforcement, and recency.
Give AI assistants persistent personal memory across MCP clients.
Give AI assistants persistent long-term memory through automatic storage and retrieval.
Provide persistent semantic memory storage and retrieval for AI agents via MCP.
Persist long-term AI memory with semantic retrieval and knowledge graph context.
Give AI assistants persistent memory, semantic search, and team collaboration.
Give AI agents persistent long-term memory with hybrid semantic and keyword search.