- Anneal Memory @phillipclapham/anneal-memoryTwo-layer memory for AI agents with an immune system. Zero dependencies.5% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from PyPI.11 GitHub stars.
- Mnemo @n24q02m/mnemo-mcpPersistent AI memory with hybrid search and embedded sync. Open, free, unlimited.6% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from PyPI.11 GitHub stars.
- Hive Vault @mlorentedev/hive-vaultOn-demand Obsidian vault access for AI coding assistants — 17 tools, 5 resources, 4 prompts.6% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from PyPI.11 GitHub stars.
- Engram: AI memory you can edit in Obsidian @engram-app/engramShared memory for Claude, ChatGPT and any MCP client. Read and edit it in Obsidian or the web app.7% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; it needs your API key.10 GitHub stars.
- Lockstep @lockstep-team-agent/lockstepDecision memory for AI coding agents: captures decisions once, briefs every agent before it acts.5% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.10 GitHub stars.
- Genome @northtekdevs/genomeFully local memory for AI agents: zero-LLM ingest, semantic recall, air-gapped, auditable.4% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from PyPI.10 GitHub stars.
- Callosium @callosium/callosiumOne shared memory for every AI you use, in plain Markdown files you own.4% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.10 GitHub stars.
- witness @ingtian/witnessDistills your sessions or any text corpus into a dated history of how its subject changed.4% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.10 GitHub stars.
- Exomem @artexis10/exomemLocal Markdown/Obsidian knowledge substrate for MCP agents with governed memory and hybrid search.7% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from PyPI.10 GitHub stars.
- Postgram @ivo-toby/postgramSelf-hosted memory for AI agents with hybrid search, knowledge graphs, tasks, and document sync.4% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from Docker.10 GitHub stars.
- Hot Memory @michael-denyer/hot-memory-mcpTwo-tier memory: hot cache (0ms) + semantic search. Self-organizing.5% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from PyPI.10 GitHub stars.
- Memory @chenxiaofie/memory-mcp情景+实体记忆 MCP 服务，为 Claude Code 提供持久化记忆能力6% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from PyPI.10 GitHub stars.
- Cathedral — Persistent Memory for AI Agents @ailife1/cathedral-mcpPersistent memory and drift detection for AI agents across session restarts.10% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; it needs your API key.10 GitHub stars.
- AgentPlaybooks @agentplaybooks/agentplaybooksManage portable AI agent playbooks, Agent Skills, MCP configurations, personas, and memory.6% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; you sign in with your account.9 GitHub stars.
- Mob (Demo) @benkaiser/mob-demoEphemeral no-signup demo of Mob, an AI-first personal CRM you run in natural language.6% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; no sign-in.9 GitHub stars.
- Turbo Quant Memory @lexus2016/turbo-quant-memoryLocal-first memory and knowledge graph for coding agents. Compact retrieval, no network.7% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from PyPI.9 GitHub stars.
- Growmos @codician/growmosLiving knowledge graph for your repo: query with citations, remember/link facts, fact-check claims.3% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from PyPI.9 GitHub stars.
- Mob @benkaiser/mobAn AI-first personal CRM you run in natural language: contacts, reminders, notes, and more.5% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; it needs your API key.9 GitHub stars.
- nMEMORY @menot-you/n-memoryMemory your agent can trust — every answer carries its source; when it doesn't know, it says so.7% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from MCPB.9 GitHub stars.
- Veracium @veracium-ai/veraciumProvenance-aware memory for AI agents: quarantine, abstention gate, supersession-with-history.5% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from PyPI.9 GitHub stars.
- Mindpm @umitkavala/mindpmProject memory and a control plane for AI coding agents.4% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.9 GitHub stars.
- Lightning Memory @singularityjason/lightning-memoryDecentralized agent memory for the Lightning economy. Nostr identity, L402 payments.7% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from PyPI.9 GitHub stars.
- Memento @scrypster/mementoPersistent memory for AI tools. Local-first knowledge graph with hybrid search.4% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from Docker.9 GitHub stars.
- Gitmem @gitmem-dev/gitmemPersistent institutional memory for AI coding agents. Memory that compounds.5% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.9 GitHub stars.
