- Lobu @lobu-ai/lobuShared, permission-aware company context for AI agents, with provenance, approvals and audit.7% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; you sign in with your account.225 GitHub stars.
- Mengram @alibaizhanov/mengramLong-term memory for AI agents: semantic facts, episodic events, and procedural workflows42% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; you sign in with your account.204 GitHub stars.
- ContextLattice @sheawinkler/contextlatticePrivate-by-default, local-first memory/context/task orchestrator for MCP apps and agents.6% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; no sign-in.154 GitHub stars.
- Knowl @dat999zx/knowlPersistent memory for Claude Code, Cursor and Codex. Facts retire when they change.5% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; you sign in with your account.122 GitHub stars.
- DeepMem @deepmemteam/deepmemMem0-compatible persistent memory for AI agents: write facts once, recall them semantically.5% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; no sign-in.114 GitHub stars.
- ClariLayer @clarilayer/clarilayerIndividual-analyst context layer: recall, remember, and reconcile your data and engineering context.8% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; you sign in with your account.82 GitHub stars.
- Synap Memory @maximem/synapPersistent memory for AI agents — log and recall conversation context over MCP.5% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; no sign-in.77 GitHub stars.
- NeuroStack @raphasouthall/neurostackToken-efficient MCP memory for Markdown vaults. Tiered search, GraphRAG, AI memories.7% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; no sign-in.47 GitHub stars.
- ContextStream MCP Server @contextstream/mcp-serverProject memory, semantic code search, and grounded agent context.10% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; you sign in with your account.44 GitHub stars.
- ContextStream @contextstream/mcpPersistent memory and cross-session learning for AI coding assistants (hosted remote MCP).13% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; you sign in with your account.44 GitHub stars.
- Mnemoverse Memory @mnemoverse/mcp-memory-serverHosted AI agent memory that learns from outcomes, with shared rooms, in Claude, Cursor and ChatGPT.9% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; you sign in with your account.26 GitHub stars.
- Claude Faf @wolfe-jam/claude-faf-mcpPersistent project context for Claude. IANA-registered .faf format.7% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; no sign-in.23 GitHub stars.
- Cairn.ink Memory @cairn/memoryCross-session memory for AI agents with a Source Receipt for every memory, over MCP.6% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; you sign in with your account.20 GitHub stars.
- Memory Journal @smithery/neverinfamous-memory-journal-mcpA MCP server built for developers enabling Git based project management with project and personal…16% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; it needs your API key.20 GitHub stars.
- Persistent Project Context for xAI Grok @wolfe-jam/grok-faf-mcpPersistent project context for xAI Grok. IANA-registered .faf format.7% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; no sign-in.19 GitHub stars.
- NeuroDock (hosted) @tlennon-ie/neurodock-remoteHosted NeuroDock — stateless communication and planning tools over OAuth-secured Streamable HTTP.8% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; you sign in with your account.16 GitHub stars.
- Engram @getengram/engramPersistent, verbatim, searchable memory for AI assistants — one memory across every MCP client.10% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; you sign in with your account.15 GitHub stars.
- Synapse Layer — Trust Infrastructure for AI Agents @synapselayer/synapse-layerMCP-native Trust Infrastructure for AI Agents. Persistent encrypted memory with Trust Quotient.9% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; no sign-in.13 GitHub stars.
- Kagura Memory Cloud @kagura-ai/memory-cloudPersistent memory for AI assistants: store, search, and connect knowledge across conversations.7% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; you sign in with your account.12 GitHub stars.
- XMemo @yonro/xmemoShared, governed long-term memory for AI agents across tools and sessions via MCP and REST.7% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; you sign in with your account.12 GitHub stars.
- ChromaDB Remote MCP Server @meloncafe/chromadb-remote-mcpRemote ChromaDB vector database MCP server with streamable HTTP transport6% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; no sign-in.12 GitHub stars.
AI memory MCP servers
A server here gives an AI assistant long-term memory of past conversations, facts or preferences.
Not here: note taking apps and team wikis.
428 remote795 localTagged by Odel's AI, which can make mistakes
Most popular in AI memory
By GitHub stars, at most two per publisher- Number 1: Honcho@plastic-labs/honchoMemory that reasons: continual learning for stateful agents. Better context, fewer tokens.7% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; you sign in with your account.7,549 GitHub stars.
- Number 2: Nautilus Compass Memory@chunxiaoxx/nautilus-compassLocal-first long-term memory for AI agents, with byte-recomputable signed verification receipts.7% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; it needs your API key.1,260 GitHub stars.
- Number 3: Kody@kentcdodds/kodyYour agents' cloud. MCP server with search, execute, packages, jobs, secrets, and integrations.7% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; you sign in with your account.753 GitHub stars.
