- Novyx MCP @novyxlabs/novyx-mcpPersistent memory for AI agents with rollback, audit trails, and semantic search.5% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from PyPI.
- Memento Protocol @myrakrusemark/memento-protocolPersistent memory for AI agents. Store what matters, recall by meaning, skip the rest.5% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.
- Memory @infoinlet-marketplace/mcp-memoryPersistent searchable memory for AI agents — save/get/search across sessions, tags.5% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.
- GeraMind @geraservicesuk/mcp-gera-mindGeraMind MCP (placeholder) — personal context vault for AI agents. Launching 2026.5% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.
- Elephia @elephia/elephiaGit for your AI's context: local-first, deterministic memory over MCP. An elephant never forgets.5% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from PyPI.
- EvolutionDB Long-Term Memory @alptekin/evolutiondb-memoryPersistent long-term memory for Claude Desktop / Claude Code, backed by EvolutionDB.6% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from PyPI.
- BrainBrainBrains @aiaiohhh/bbb-mcp-serverPersistent memory + context layer for AI dev teams. 17 tools via MCP.7% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.
- Context Vault @rajdeepdas43/context-vaultGoverned memory for AI agents (Paramind AI): conflict-checked writes, time-travel reads, ACL, audit.8% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from PyPI.
- Vasperamemory @rcolkitt/vasperamemoryPersistent AI memory for coding assistants. 80+ tools for decisions, patterns, errors.10% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.
- Solitaire for Agents @prdicta/solitaireIdentity infrastructure for AI agents. Evolving persona, session continuity, self-tuning retrieval.11% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from PyPI.
- Phloem @canopyhq/phloemLocal-first AI memory with causal graphs. Fully offline, zero config, your data stays local.6% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from MCPB.
- Total Recall @bas-more/total-recallPersistent, verified, cross-session memory for AI agents. 26 tools. SQLite + sync.7% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.
- Tokenmaxxen @austinmunday/tokenmaxxen-mcpCollective episodic memory for AI coding agents — search, deposit, comment, showcase builds.8% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.
- Memory @letta/memory-mcpMCP server for AI memory management using Letta - Standard MCP format5% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.
- Memory @cortex-mem/memoryShared, persistent memory for AI agents — works with Claude, Kiro, Cursor, or any MCP client.7% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.
- Synchronex @synchronex/mcp-proxyConnect any AI agent to your Synchronex workspace — portable memory, decisions, and workers.9% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.
- Contextlayer @autoblocks/contextlayer-mcpPersonal context management for AI assistants5% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.
- Ctxl @autoblocks/ctxlPersonal context management for AI assistants5% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.
- Recalld @bit-robotics/recalldManaged long-term memory for AI agents, with evolving facts and relevant retrieval through MCP.6% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from a package registry.
- Auditable memory (memory3l) @jayzht/memory3l-mcpAudited memory over MCP: an append-only fact ledger plus verifiable invariants I1-I5.4% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from PyPI.
- MemoryLayer @memorylayer/memorylayerLocal-first persistent memory for AI agents, with reasoning and formal verification.7% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.
- logbook-mcp @abduljabbarbxr/logbook-mcpProject memory across sessions for AI agents. A queryable decision log in the repo.5% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.
- HyperMarrow @qianshi/hypermarrowLocal-first long-term memory for AI coding agents. Stored on your own machine.6% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.
- MemVault MCP Server @dreamor/memvaultShared memory router for AI agents: save/search/recall, session-start injection, review inbox.10% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from Docker.
