- Great Arrow @greatarrow/great-arrowShared memory and actions for Claude, Kiro, OpenAI, Cursor, and other MCP-compatible AI clients.9% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; you sign in with your account.
- SPM @spmos/spmAgent memory that refuses to guess: evidence-gated recall, exact-source reads, verifiable deletion.12% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; you sign in with your account.
- KEZAI Cultural Memory @kezai/memoryPrivate cross-media memory for AI assistants: recommendations, progress and controlled actions.11% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; you sign in with your account.
- Sirro @jonathanmberg/sirroShared memory for AI coding agents. Save once, reuse from Cursor, Claude Code, Codex.9% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; you sign in with your account.
- Kognite @kognite/memoryHosted agent memory: store, search, and recall facts across sessions from any MCP client.8% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; you sign in with your account.
- Sentarion @sammyboi81/sentarionGoverned MCP orchestration, tamper-evident memory, and Claude Code Seatbelt hooks.7% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from PyPI.
- emdly @emdly/emdlySearch, install and submit Markdown skills for AI agents; private Brain files when signed in.6% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; no sign-in.
- OrcaVault @keiko-dev-lcai/orcavault-mcpPermanent on-chain memory for AI agents on Lightchain via a one-time unlock.10% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; no sign-in.
- Brainiall Memory @brainiall/memoryPersistent semantic memory storage, associative recall, and recent memory index by namespace.8% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; you sign in with your account.
- Recall — persistent memory for agents @notdown-app/memoryPersistent memory for AI agents. Free, no LLM, no SDK. Open Worker you can self-host in 2 commands.10% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from a package registry.
- Warden @rynald0cst0ltziam/wardenVerified context layer for AI coding agents — prunes, compresses, indexes, remembers. 32 MCP tools.9% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.
- Contextaco @contextaco/contextacoNever explain the same context twice. Capture it once, load it anywhere, fork it to make it yours.9% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; you sign in with your account.
- Savantis Memory @savantisai/savantis-memoryOne user-owned memory shared across AI assistants: recall, spaces, and confirmed references.7% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; you sign in with your account.
- OneDroid Engram @onedroid/engramVersioned agent memory in your own Postgres: portable context, permissioned, audit trail.7% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; it needs your API key.
- Fomite @thefomite/fomiteA field station for AI agents: free memory, a message board, a peer oracle, an open census.17% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; no sign-in.
- Dijin Memory @dijin/memoryDijin is a Memory Layer: recall notes, decisions, and evidence-backed answers across every AI.8% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; you sign in with your account.
- Memory Vault @apurv101/memory-vaultPortable AI memory shared across models and harnesses - plain markdown you own.10% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; you sign in with your account.
- JustOnce @justonce/memoryPersistent memory for AI assistants — one shared, OAuth-secured vault for every MCP client.10% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; you sign in with your account.
- MemorySync @memorysync/memoryPersistent memory for AI agents. Search and store durable facts, preferences and decisions.7% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; you sign in with your account.
- AgentBrink @agentbrink/mcpGive your AI agent an identity: its own email, webhook, repo, secrets vault, memory and skills.11% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; it needs your API key.
- LLMnesia @llmnesia/mcpSearch your AI chat history from Claude, Cursor, Codex, and other MCP clients.6% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.
- MemoryRouter @memoryrouter/memoryrouterPersistent AI memory shared across Claude, ChatGPT, coding agents, and compatible MCP clients.5% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; no sign-in.
- Mnemos — memory as a service @virohanalife/mnemosBi-temporal memory-as-a-service and paid agent labor. Pay-per-call USDC via x402; signed receipts.10% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; no sign-in.
- Workledge @workledge/workledgeA growing notebook shared by every AI you use. Save in conversation, recall from any connected AI.9% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; you sign in with your account.
