Save a memory to long-term storage so it survives the conversation. Content is routed automatically to a procedure, episode, core memory, or fact, and the stored memory id is returned.
Apache 2.0
699,904 tools. Updated 2026-10-24 21:39
"A memory-efficient MCP server with vectorized memory bank synchronization" matching MCP tools:
- Lists all memory volumes (projects) accessible by your API key, each serving as an independent memory space for persistent memory management.MIT
- Check macOS memory health with detailed stats: free, active, swap, and memory tier. Identifies pressure levels before builds or heavy tasks.Sustainable Use v1.0
- Evaluate your agent's memory quality with a health score. Identify stale memories, conflicts, and contradictions to monitor memory health over time.MIT
- Store or update a JSON value for a memory key with optional TTL, importance, source, and confidence score. Persists AI agent memory across sessions and changes.MIT
- Merge a reviewed draft into canonical memory, optionally marking an older memory as superseded.MIT
Matching MCP Servers
- AlicenseBqualityDmaintenanceProvides a read-only MCP interface to query and retrieve verifiable evidence from a local memory bank, supporting search, dossier, chronology, source, and evidence tools.6BSD Zero Clause
- AlicenseNot gradedqualityFmaintenanceMemory Bank Server provides a set of tools and resources for AI assistants to interact with Memory Banks. Memory Banks are structured repositories of information that help maintain context and track progress across multiple sessions.16 npm46MIT
Matching MCP Connectors
- Pryzm MemoryOAuth
Encrypted long-term memory shared across your AI assistants (Claude, ChatGPT, Perplexity).
- memoryOAuth
Persistent long-term memory for AI agents: semantic search, knowledge graph, and task canvas.
- Check memory-bank occupancy vs capacity, hit rates, true-drop count, and totals to gauge how much is remembered or diagnose retrieval problems.Apache 2.0
- Index a .txt, .md, or .pdf file into a reference bank for background documents, keeping them separate from conversational memory so they remain retrievable by cosine similarity.Apache 2.0Destructive
- Compares a memory draft against an existing memory to show changed fields and provide a merge recommendation.MIT
- Change a shared memory back to private, removing it from team visibility. Use when a memory should no longer be shared.MIT
- Retrieve the full chronological history of a memory, including creation, updates, links, and supersedes. Shows every operation affecting the memory.MIT
- Delete a specific memory by providing its UUID. Removes unwanted or outdated records from the memory store.MITDestructive
- Query memory relationship graphs with filters for memory ID, relation type, and direction. Understand connections between memories.MIT
- Retrieve all incoming and outgoing links for a memory, optionally filtered by relation type, to view connections in the memory graph.MIT
- Share a memory with specific agents to provide them with relevant context for coordinated and accountable actions.MIT
- Detect memory-poisoning risks in agent code: unsanitized untrusted input in persistent memory and memory retrievals used as trusted context.MIT
- Search vectorized files in a group using semantic queries to find relevant content based on meaning rather than keywords.MIT
- Fetch a ClawMem memory using an issue number or memory reference string. Retrieve specific stored data for your AI agent.MIT
- Replace an outdated memory with a new version atomically, preserving governance history and audit details.MIT
- Query a specific memory layer with structured filtersMIT
- Update an existing memory by providing its memory ID, along with optional new content and importance.MIT