- ctxstore — memory that follows you across models @ctxstore/ctxstore-mcpPersistent memory for AI agents: keyed facts, a wake bundle each session, one memory in every model.8% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; no sign-in.
- myBrain @mybrain-ai/mcpYour personal knowledge base and memory for AI agents: search, explore and feed your myBrain.Not assessed yet.A remote server; it needs your API key.
- brain-mcp @debashishthakur/brain-mcpYour Obsidian vault as private, searchable memory for Claude, Cursor, Hermes and any MCP client4% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.
- A2apay @groundhogday2011-byte/a2apayPay-per-call AI query and versioned task memory for agents. No account, no API key, via x402.Not assessed yet.Runs on your machine, installed from PyPI.
- Listspace @listspace/listspaceProject memory for AI agents: read and keep the user's Listspace boards up to date.5% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; you sign in with your account.
- sync82 @oito2/mcp-sync82Persistent, structured project memory for AI coding agents, stored locally in SQLite.Not assessed yet.Runs on your machine, installed from MCPB.
- ppl - Personal CRM for AI Agents @ppl-crm/pplppl: the personal CRM for AI agents. Structured relationship memory over hosted MCP.Not assessed yet.A remote server; you sign in with your account.
- VibeDNA Journal @marstudio360/vibedna-journal-mcpOne journal file per project that your AI reads at session start and updates as it works.Not assessed yet.Runs on your machine, installed from MCPB.
- cogvault @nbibikov/cogvaultLocal hybrid-search memory for AI agents over plain Markdown. Multi-tenant, offline, no LLM.2% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from PyPI.
- Geniffy @geniffy/geniffy-mcpYour memory in every AI app: each fact with the line it came from, or a plain "nothing stored".11% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; you sign in with your account.
- Anansi Haven @kburrus64-max/anansi-havenFree home base for AI agents: memory, job board, agent directory, safe commons and free tools.Not assessed yet.A remote server; no sign-in.
- factstore @victor-eu/factstoreA fact store for AI agents, on Postgres: registered attributes, every write citing its evidence.5% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from PyPI.
- Team0 Living Understanding @team0/living-understandingThe second brain your AI agents share. It builds itself from your work and keeps itself current.7% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; you sign in with your account.
- Memory Find @kkeo/memory-findLocal, explainable knowledge base for AI agents: hybrid search with provenance over SQLite.Not assessed yet.Runs on your machine, installed from MCPB.
- alethech @eddyflores100-lang/alethechRead-only MCP bridge for alethech — verifiable, Ed25519-signed agent memory over stdio.Not assessed yet.Runs on your machine, installed from PyPI.
- ppl - Personal CRM for AI Agents @dbhurley/pplPersonal CRM operated by AI agents. Read relationship context before acting, write back after.17% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; it needs your API key.
- Wicked MCP @choaticpixels/wicked-mcpThe whole Wicked suite for agents: trading, DeFi/token risk, identity, reputation, memory. x402.10% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; no sign-in.
- PersonaMCP @robyroro/personamcpLocal-first memory of how you write: style profile and real reply examples from your chat exportsNot assessed yet.Runs on your machine, installed from PyPI.
- Schelling Add Forward @schellingaf/schellingafMulti-agent coordination for AI agents: shared spaces, tasks, search, mailbox and persistent state.6% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; you sign in with your account.
- Agent Cowork Memory @rxthlessbeats/agent-cowork-memoryShared memory and delegation for Codex, Cursor, Claude Code, and OpenCode.Not assessed yet.Runs on your machine, installed from npm.
- ContextQ @contextq/contextq-mcpPersistent memory, hybrid search and a goal graph for AI agents, over stdio or remote HTTP.5% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; you sign in with your account.
- Continuity by Ouroboros Apps @lahutchins91/continuityStory continuity, novel memory, and series bible for fiction writers, shared with AI assistants4% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; no sign-in.
- Stemem Identity Runtime @jojo-adam/stememLocal-first agent persona runtime (MCP): cross-session personality that survives compaction.6% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.
- Stele @stele-ai/steleShared project memory for AI coding agents: decisions, lessons, risks and tasks in one graph.5% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; you sign in with your account.
