Accept a shared context invitation to gain access to another user's memories. Use the provided token to activate the shared space.
MIT
784,176 tools. Updated 2026-11-15 06:14
"A tool for storing and accessing shared memories across multiple Claude.ai users" matching MCP tools:
- Merge related episodic memories into a unified semantic memory while preserving originals as provenance. Use when multiple memories cover the same topic.MIT
- Search community-shared memories to discover what other users have saved about any topic. Filter by tag, platform, or sort by popularity to find solutions from the collective knowledge base.MIT
- Run multiple tool calls in parallel and aggregate results. Execute plan steps or batch queries across APIs, with per-step error isolation.MIT
- Discover all users and agents with stored memories and their memory counts to identify system participants before conducting searches.MIT
- Correct or reorganize saved memories by editing text or bucket for a single memory, or moving multiple memories to another bucket.MIT
Matching MCP Servers
- AlicenseNot gradedqualityCmaintenanceEnables AI coding agents to collaborate on the same project by sharing session briefs and reading each other's native transcripts, memories, and instructions in place, with zero-copy, across different agent tools.12 npmMIT
- AlicenseNot gradedqualityDmaintenanceLocal MCP server enabling Codex and ChatGPT to read/write files, execute commands, manage processes, use Git, and inspect images on the user's machine with full privileges.Apache 2.0
Matching MCP Connectors
- Hebby MemoriesOAuth
Long-term memory for AI agents: graph memory with Hebbian learning, shared by Claude, Codex and co.
Shared team memory for agents. $4.75/seat/mo.
- Retrieve all shared memory pools in the workspace, showing name, access level, member count, and memory count for collaborative agent memory spaces.MIT
- List all stored memories for the current user from both Arc and Atlas in the shared store.MIT
- Search stored memories using natural language queries and filters to find relevant information based on user, agent, or time criteria.Apache 2.0
- Find specific memories by full-text query and filters for date, tags, source, status, and shared flag, enabling targeted retrieval of past knowledge.MIT
- Retrieve new shared memories from other agents since the last synchronization to maintain up-to-date collaborative memory.MIT
- List users, agents, apps, or runs that currently hold stored memories to track memory ownership and usage.Apache 2.0
- List memories with optional filters for status, query, limit, and agent ID to retrieve relevant past decisions and context.MIT
- Search long-term AI memories semantically and filter by author, source, date range, or libraries to retrieve relevant facts and summaries.Apache 2.0
- List recurring concepts across memories with filters for entity type, minimum mentions, and limit.MIT
- Archive multiple confirmed memories at once with atomic all-or-nothing execution, requiring explicit user confirmation for each item.MIT
- Fetch public keys for multiple users by supplying their user IDs. This read-only tool returns account public key data for the specified users.MIT
- Save durable, searchable memories for decisions, facts, preferences, and lessons. Indexes immediately, persists across sessions, and is recallable from any MCP host.MIT
- Clear all stored memories for a specific user namespace. This destructive, irreversible action wipes out the user's memory history while leaving other users' data untouched.Apache 2.0
- Build a read-only, bounded context pack from multiple relevant memories for answers needing several items or scoped/path-filtered context. Limit by item and token budgets and report omitted memories.MIT
- Retrieve stored memories using structured filters for specific users, agents, or time periods, with pagination support for browsing results.Apache 2.0