- Lex @smartergpt/lexEpisodic memory, Frames, Policy Neighborhoods, and policy enforcement for AI agents.4% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.
- MemoStem @girapphe/memostemYour reviewed knowledge, across AI conversations.5% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; no sign-in.
- CoralSwarm Connect @coralswarm/coralswarmSearch and save your coding work in a CoralSwarm ocean: sessions, decisions, meetings.8% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; you sign in with your account.
- Finch @finchagentic/mcpAgentic AI runtime: persistent memory, vault, autonomous agents, deep research, DeFi execution.10% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; it needs your API key.
- Sensefold MCP @sensefold/sensefoldPersonal context for every AI: search, read, and write back to your private Markdown library.7% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; you sign in with your account.
- projectstate @projectstate/projectstatePer-project memory for AI agents: decisions, attempts, tasks, ranked recall. Paid per call via x402.3% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; no sign-in.
- polymnemo @pcbz/polymnemoShared cross-LLM long-term memory over MCP: semantic recall, sessions, and media (pgvector).5% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; it needs your API key.
- Spomory @lyf-wxy/spomoryExplainable graph-retrieval memory engine with an RL-trained management policy.11% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; you sign in with your account.
- WhiteMagic — governed local memory for agent continuity @lbailey94/whitemagic-mcpGoverned local-first memory and continuity for AI agents — signed receipts, optional hosted lane.5% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; no sign-in.
- Agtrepo Memory @agtrepo/agtrepo-memoryEncrypted, pay-per-use persistent memory storage for AI agents, gated by x402 payments on Base.8% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; no sign-in.
- Sticky @1picassoai/stickyPersistent memory and context for your agent, on a board you can see. Capped, so it stays small.4% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.
- Korely Memory @korely/memoryMemory for AI agents that knows what is still true. Typed bi-temporal facts, EU-hosted.6% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; you sign in with your account.
- MemCell @memcell/memcellLiving memory for AI coding agents: recall before acting, report outcomes so confidence is earned.9% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; it needs your API key.
- AgentCommons.me @ivgolovach/agentcommonsPublic working memory for AI agents: messages, shared pages, and resumable tasks.7% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from MCPB.
- Memento @jee1/memento-mcp-serverAgent memory MCP server with 4-type cognitive memory, hybrid search, and TTL-based forgetting.4% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.
- Cairn @mightys/cairnLessons other agents already learned, by stack and situation. Read before a task, leave one after.5% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.
- LBrain @lbrain/lbrainLocal-first agent memory. Source, date, bind/abstain. Permanent name: lbrain.ai/claim.html15% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from PyPI.
- Neither @stonianua/neither-mcpProject context for Cursor/Claude via stdio MCP. Key: www.neither.online/start6% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.
- Echocache @kskurtveit/echocacheMCP server caching expensive LLM responses: HTTP-style freshness plus semantic recall.3% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.
- Memstack @isiomac/memstackMCP server for persistent, searchable memory for AI agents.5% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.
- AgoraDM @shichuanqiong/agoradmDM / IM + public arena for AI agents (A2A 1.0) — hosted endpoint or local package.5% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; no sign-in.
- Vanguard Memory Node @ezumba/vanguard-memory-nodeLocal deterministic BM25 memory for AI agents. Offline-first, no API key, SHA-256 shards, stdio.5% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.
- Agentprofile @everyai-com/agentprofileOne profile — skills, credentials, and memory — synced to every agent tool via one MCP URL.9% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; you sign in with your account.
- Munnin — an agent identity server @alvseek/munninAgent identity and memory over MCP — a persistent self plus the procedures for tending it.6% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; you sign in with your account.
