- Pensieve @praveen-ilangovan/pensieveManually-triggered, self-organising personal memory for AI agents; SQLite, no vector DB.4% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from PyPI.
- Cambium @jarmstrong158/cambiumKnowledge-lifecycle MCP: turn agent work into memory, recall it across projects, promote to org.4% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from PyPI.
- Kireo @wang1051992187/kireoLong-term memory for Claude Code, Cursor and any MCP client, with a searchable web dashboard.6% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.
- Mnema @zimac/mnemaLocal-first, formally verified memory for AI agents: consult/learn/related/list over MCP.5% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from MCPB.
- Context Autopilot @chiragbachani/context-autopilotMines your Claude Code and Cursor sessions into evidence-based CLAUDE.md / AGENTS.md rules.6% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.
- Zdravo Cursor @zdravo-ai/zdravo-cursorPersistent AI memory for Cursor. Save and search memories via Zdravo.7% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.
- Toki Toki @xfloukiex-lab/toki-tokiA local causality ledger: records decisions and the reasons, for an agent to recall.5% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from PyPI.
- WebberSites x402 @webberdesign/webbersites-x402-mcp45 pay-per-call AI agent tools + wallet-owned agent memory. Scraping, SEO, lint, crypto. x402 USDC13% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.
- Subconscious @vishaltorc/subconscious-mcpLocal-first semantic memory for MCP agents. Recall, remember, forget, echo, drift, stats over stdio.5% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from PyPI.
- Uuaid MCP @uuaid/mcpPermanent identity + encrypted, quantum-ready memory that outlives the session, for any AI agent.10% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.
- Memdata @thelabvenice/memdataPersistent memory for AI agents. Store context, retrieve it semantically.5% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.
- Agentresources @sznt2010/agentresources-mcpMCP server for Agent Resources: Trust Cards, signed telemetry, ERC-8004 identity, x402.6% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.
- MADB — Agent Memory Database @spshkar84/madb-memoryDurable causal memory for AI agents — semantic recall, causal lineage, and skills. Local-first.5% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from PyPI.
- HippoDid MCP Server @snowmanjy/hippodid-mcp-serverPersistent, structured cloud memory for AI agents. BYOK — bring your own AI key.8% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from MCPB.
- ZKshare @sp0oby/zkshareZKshare stdio MCP: store/prove/share, semantic search, sandbox proxy to HTTPS /api/v1/context.7% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.
- Memory @shackleai/memoryPersistent memory for AI coding tools. 11 tools for any MCP-compatible AI tool.5% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.
- AgentRAM @seanmarkwei/agentram-mcpModel Context Protocol server for AgentRAM. Persistent memory for AI agents.5% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.
- darwin-memo @rogermsc/darwin-memoSelf-curating agent memory kept honest by survival-based selection over measured outcomes.7% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from PyPI.
- MCP OpenClaw Extensions @romainsantoli-web/mcp-openclaw138-tool MCP server for AI agent firms: security, A2A, Hebbian memory, fleet mgmt7% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from PyPI.
- Adaptive Memory Graph @raskolnikovdd/adaptive-memory-graphPersistent memory for Claude via weighted, interconnected knowledge nodes.5% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from PyPI.
- Manoma @paperdavid/manomaMCP server for soul.md — your portable AI identity layer across every LLM.7% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.
- Smara @parallelromb/smaraPersistent cross-platform memory for AI agents with Ebbinghaus decay scoring.5% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.
- Anamnesis @oscardvs/anamnesisCross-machine, file-first memory for Claude Code: markdown + SQLite FTS5, synced with git3% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from PyPI.
- Casemgr @mstang/casemgr-mcpShared workspace your AI agent writes to. 184 tools, persistent memory, semantic search.5% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.
