- Pensyve @major7apps/pensyveUniversal memory runtime for AI agents — episodic, semantic, and procedural memory.7% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from Docker.95 GitHub stars.
- KIP @ldclabs/kipKnowledge Graphs to enable memory persistence, knowledge evolution, explainable interaction.5% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.86 GitHub stars.
- Robrain @adelinamart/robrainSelf-hosted decision memory for AI coding agents; warns before re-proposing a rejected approach.4% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.82 GitHub stars.
- Vouch @vouchdev/vouchGit-native, review-gated knowledge base for LLM agents. Cited retrieval, audited writes.4% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from PyPI.82 GitHub stars.
- Sverklo @sverklo/sverkloLocal-first MCP code intelligence: 37 tools — hybrid search, blast-radius, diff review, memory.5% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.82 GitHub stars.
- pond @tenequm/pondLossless archive and search for AI agent sessions across clients, exposed to agents over MCP.4% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from cargo.81 GitHub stars.
- brain — the recorder @mordechaipotash/brain-mcpRecords your Claude Code, Codex and Pi history before deletion. Cited-or-abstain recall.7% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from PyPI.78 GitHub stars.
- Hypermnesia @cdeust/hypermnesia-mcpPersistent memory for AI agents — 36 cited neuroscience mechanisms, local-first, hybrid retrieval.4% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from PyPI.73 GitHub stars.
- Total Agent Memory @vbcherepanov/total-agent-memoryPersistent local memory for coding agents: temporal knowledge graph, procedural and episodic recall5% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from PyPI.72 GitHub stars.
- Reverie @knowall/reverieGraph memory that dreams: Neo4j knowledge-graph memory for AI agents with hybrid search3% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.69 GitHub stars.
- ZettelForge @rolandpg/zettelforgeAgentic memory for cyber threat intelligence. STIX graphs, actor aliasing, offline RAG, Sigma/YARA.6% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from PyPI.65 GitHub stars.
- MCP AutoMem @verygoodplugins/mcp-automemGraph-vector memory for AI assistants using FalkorDB and Qdrant7% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.65 GitHub stars.
- Memory Vault @mihaibuilds/memory-vaultLocal-first AI memory layer with hybrid search. Postgres + pgvector. Self-hosted, MIT.3% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from Docker.65 GitHub stars.
- Zikkaron @amanhij/zikkaronBiologically-inspired persistent memory engine for Claude Code MCP agents5% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from PyPI.63 GitHub stars.
- People Context @jinyangwang27/people-contextLocal-first MCP server giving AI agents contextual knowledge about the people in your life3% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from PyPI.58 GitHub stars.
- ChatCrystal @zengliangyi/chatcrystalLocal-first AI PKM memory for coding conversations.5% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.58 GitHub stars.
- AI Memory @alphaonedev/ai-memoryPersistent memory for any AI — zero token cost until recall5% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from Docker.53 GitHub stars.
- State Memory MCP @putervision/state-memory-mcpPersistent workflow graph server tracking tasks, decisions, spatial entities, and blockers.4% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.49 GitHub stars.
- Engram @tstockham96/engramIntelligent agent memory with automatic extraction, consolidation, and bi-temporal recall.5% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.47 GitHub stars.
- Adam Framework @strangeadvancedmarketing/adam-frameworkPersistent memory tools for Claude Desktop. Search your vault or Obsidian notes mid-conversation.7% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from PyPI.46 GitHub stars.
- AiDex @cscsoftware/aidexPersistent code indexing for AI assistants. 50x less context than grep. 11 languages.6% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.46 GitHub stars.
- ContextStream MCP Server @contextstreamio/mcp-serverContextStream MCP server for code context, memory, search, and AI tools.9% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.44 GitHub stars.
- Palinode @phasespace-labs/palinodeInspectable, correctable project memory in git-versioned Markdown for AI agents.4% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from PyPI.44 GitHub stars.
- Waggle @abhigyan-shekhar/waggle-mcpPersistent graph-backed conversational memory for AI agents.3% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from PyPI.44 GitHub stars.
