- Sooveryn @sooveryn/sooverynAI personas with a lasting, encrypted memory per project, for Claude Code. Hosted in France.10% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; it needs your API key.
- amu-pgvector @sangaraju1988/amu-pgvectorLineage-gated agent memory tools on Postgres + pgvector, enforced by row-level security.Not assessed yet.Runs on your machine, installed from PyPI.
- Pyunto Diary @pyunto/diaryRead, search and write your encrypted Pyunto diary from Claude. Decrypts only on your own machine.6% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from PyPI.
- Mnemodb @mnemodb/mnemodbPersistent agent memory as plain Markdown in your repo - readable, diffable, with provenance.3% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.
- Hypermarrow @qianqiuwanzi/hypermarrow-mcpLocal-first AI memory MCP server. Record, recall and consolidate memory on your own machine.5% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.
- memory-boost @arnaugonzalez/memory-boostMarkdown memory for coding agents that audits itself: drift reports and session digests.3% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from PyPI.
- ChronoKey @dyln01/chronokeyMCP tools: timestamps, UUID v4, gas prices, domain WHOIS, text extraction, and persistent memory.9% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; no sign-in.
- Invest Brain @lj22503/invest-brainA-share investment research: quotes, financials, behavior patterns, and trading journals.6% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from MCPB.
- Gather @hunta-ai/gatherAttestable memory for AI agents: curated writes, verifiable tenant isolation, bi-temporal facts.7% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; you sign in with your account.
- repo-memory-mcp @umarjaum/repo-memory-mcpPersistent local memory for MCP-compatible AI coding agents, stored per repository in SQLite.4% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from PyPI.
- contextkeeper @therealdataboss/contextkeeperZero model drift between AI agents. Session continuity for Claude, GPT, Gemini, and any LLM.19% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from PyPI.
- Shelbymcp @studio-moser/shelbymcpKnowledge-graph memory server for AI tools via MCP4% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.
- Agent Memory @mastadoonprime/agent-memoryPersistent, agent-owned memory with encrypted storage and shared knowledge commons.15% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; no sign-in.
- Assertion Memory @assertion-ai/assertionRecall your team's coding-agent memory. Install the Assertion plugin to capture it automatically.8% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; no sign-in.
- Locker @veritap/lockerAgent memory that survives you: free to start (any keypair, no signup); opened only by your key.7% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; no sign-in.
- ASR Memory (에사 AI) — Shared memory for AI tools @asrmemory/asrShared memory for AI tools: save once, recall word for word from Claude, ChatGPT, Codex or Gemini.9% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; you sign in with your account.
- Telys — on-device memory @thyn-ai/telysPrivate on-device memory & retrieval for AI assistants — offline vector + lexical search.4% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from PyPI.
- Agent Memory @theprodsde/agent-memoryPersistent agent memory with a decision layer: replay, restore, verify, or none — explainable.4% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from PyPI.
- Memento @mementoagi/mementoHosted MCP memory for coding agents: persistent across sessions, editable markdown, team sharing.7% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; it needs your API key.
- Claims @dgonzap30/claims-mcpA claims memory for agents: assert beliefs, let them decay, surface contradictions.5% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.
- Chip MCP @chip-ai/chipProject memory, tasks and Telegram notifications for your coding agent. Chip account required.6% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; no sign-in.
- SOKI (想起) — Personal Memory @kitemir/sokiPersonal memory outside the AI. Due dates, loose ends and old notes come back on their own.6% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; you sign in with your account.
- Kika @usekika/kikaShared memory for client engagements: decisions with reasons, blockers, promises, what was tried.7% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; you sign in with your account.
- Memoro @circassian1977-byte/memoroPersonal AI memory layer on your own computer. Read/write durable memory across MCP clients.10% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.
