- 0Latency Memory @jghiglia2380/0latencyPersistent memory layer for AI agents. Sub-100ms recall, semantic search, knowledge graphs.11% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from a package registry.
- CacheTank @jacobsilver7-art/cachetank-mcpCacheTank MCP server gives every AI tool your personal context so you never start from zero.12% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.
- Hindsight MemPalace @holetron/hindsight-mempalaceSelf-hosted long-term memory for AI agents over MCP — hierarchical recall backed by pgvector4% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.
- Engrm @dr12hes/engrmShared memory across devices, sessions, and agents for OpenClaw, Claude Code, and Codex.6% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.
- Hipocampo MCP @carrasquelalex1/hipocampoBilingual dual memory with SSC for AI agents. Semantic search, embeddings, profiles.7% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; no sign-in.
- Brains @brainsforai/brains-mcp-connectorPersonal wiki and memory layer for AI assistants. Persistent, structured memory across sessions.9% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; you sign in with your account.
- Cortex @abbacusgroup/cortexPersistent knowledge system with OWL-RL reasoning and 22 MCP tools. Local-first.5% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from PyPI.
- Claude Amplifier @sisuthros/claude-amplifierPersistent memory + decision tracking for Claude across sessions. Local SQLite, no cloud.6% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.
- MCP Memory Graph @retrorobai/mcp-memory-graphAuthority-weighted memory graph for AI agents with conflict detection and semantic search.6% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from PyPI.
- Perseus Vault — persistent, encrypted memory for AI agents @perseus-computing-llc/perseus-vaultPersistent, encrypted, deterministic memory for AI agents. Local-first, 173 canonical tools.6% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from Docker.
- Vector Memory @neerajg03/vector-memorySemantic document memory using Redis vector store. Save and recall files with natural language.5% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from PyPI.
- Verifiable Memory @mars-proj/verifiable-memoryMemory for AI agents that can't hallucinate — cited or abstains, provable forget, deterministic.6% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from PyPI.
- Hebbian Mind @for-sunny/hebbian-mind-enterpriseAssociative memory via Hebbian learning. Connections strengthen through use, decay through disuse.5% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from PyPI.
- RecallMax-Neural @evozim/recallmaxSemantic context compression and cognitive memory layer for LLM swarms.21% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; it needs your API key.
- SEAM Runtime @blackhatshiftey/seam-runtimeSEAM: local-first memory runtime for AI agents, with retrieval and glassbox provenance over MCP.7% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from PyPI.
- Agentage Memory @agentage/memoryOne memory, every AI. A shared, user-owned markdown memory your AI clients read and write over MCP.7% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; you sign in with your account.
- ITHZ MCP @ithz/ithz-mcpLocal deterministic project memory for AI agents with context packs, gates and checkpoints.6% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from PyPI.
- Memnode Hosted MCP @memnode/memnodePersistent, inspectable memory for AI agents with lineage, correction, and a hosted MCP endpoint.9% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; you sign in with your account.
- Mnemolog MCP @mnemolog/mnemologHosted MCP memory and agent control plane for durable conversations, jobs, and operations.10% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; it needs your API key.
- Native Soil @nativesoil/soilSave an AI chat's working state, load it in any other model or provider. Verified, secret-safe.9% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; you sign in with your account.
- AI Cortex Storage @aic0rt3x/mcpPersistent cloud memory for AI agents. Store and search key-value memories across sessions.10% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; no sign-in.
- Taproot @taproothq/taprootPersistent memory layer for AI tools. Save and recall notes across Claude and other MCP clients.9% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; it needs your API key.
- Squirrel Brain @squirrelbrainapp/squirrel-brainGive your AI agent a memory and body on your iPhone: set alarms, ring your phone, over MCP.23% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; it needs your API key.
- stagenth · AI 记忆库 @stagenth/memory-kitHosted persistent memory with semantic search, importance and TTL for AI agents.9% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; it needs your API key.
