- ContextDB Customer Memory @atomsai/contextdb-memoryCustomer memory with recall, confirmation, forgetting, and pre-action evidence checks.9% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; you sign in with your account.
- CortexPlus @cortexplus/cortexplusPersonal memory layer: files, notes, messages, tasks and email, semantically indexed.11% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; no sign-in.
- thinqOS @thinqos/mindMemory with judgment: decides which of your context reaches each task, per identity.9% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; you sign in with your account.
- Agent Identity Garden @tfitzgerwitness/agent-identity-gardenOptional persistent identity state for autonomous software agents.9% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; no sign-in.
- Auditable memory (memory3l) @jayzht/memory3l-mcpAudited memory over MCP: an append-only fact ledger plus verifiable invariants I1-I5.4% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from PyPI.
- MemoryLayer @memorylayer/memorylayerLocal-first persistent memory for AI agents, with reasoning and formal verification.7% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.
- Threadkeep — Agent Checkpoints @interesting-concepts-ventures/threadkeepAgent checkpoints. Resume after context resets and handoffs with retry-safe, versioned saves.7% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; no sign-in.
- The Continental @oagotus-droid/the-continental-apiPortable client-sealed memory and private rooms for agents from any lab; a free door; a ledger6% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; no sign-in.
- logbook-mcp @abduljabbarbxr/logbook-mcpProject memory across sessions for AI agents. A queryable decision log in the repo.5% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.
- HyperMarrow @qianshi/hypermarrowLocal-first long-term memory for AI coding agents. Stored on your own machine.6% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.
- Nuramem @nuramem/nuramemCross-model memory for people and teams: one memory every AI you use loads at session start.9% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; you sign in with your account.
- Nexus Catalyst @nexus-catalyst/nexus-catalystCross-tool persistent memory and context for AI assistants over MCP.10% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; you sign in with your account.
- Project Fingerprint @projectfingerprint/personal-contextPersonal context and preferences for AI via OAuth-approved profile sections and taste data.11% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; you sign in with your account.
- Free no-signup cloud tools for AI agents: file transfer, static site hosting, memory, conversation… @83blue/agent-cloud-toolsFree no-signup cloud tools for AI agents: file transfer, static site hosting, memory, handoff.9% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; no sign-in.
- Automaton Nebula memory vault @automatoncolony/nebulaPer-client memory for any AI. On a clash, the AI gets both values and is told to ask you.10% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; you sign in with your account.
- MemVault MCP Server @dreamor/memvaultShared memory router for AI agents: save/search/recall, session-start injection, review inbox.10% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from Docker.
- Vilix AI @appfairly/vilixShared memory for connected AI tools. Projects, rules and skills over MCP. OAuth or API key.12% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; you sign in with your account.
- gjalla @gjalla/mcp-serverSelf-curating shared memory that keeps your agents working like a high-performing team6% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from PyPI.
- agentic-recall @dfrancislyondflabc-tech/agentic-recallLong-term memory for agentic tasks. It tells you when it doesn't know.5% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.
- Shared Persistence @sharedpersistence/shared-persistencePersistent shared message space for autonomous agents: read, write, reply, search. Free, no signup.6% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; no sign-in.
- Contextual @contextual-laboratories/contextualPersistent memory for AI coding agents: local-first semantic search, dependency graphs, git history.5% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from PyPI.
- Jotter @jotter/jotSave notes and conversation context from one AI assistant and load them into another.8% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; you sign in with your account.
- SmartMemory @smartmemory/smartmemory-mcpGraph + vector memory for agents: recall, ingest, search, distill. Local or remote backend.5% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from PyPI.
- Verbasil, company memory @verbasil/memoryCompany memory for your team and its AI agents. Hosted service, account required.8% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; you sign in with your account.
