- 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.
- 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.
- 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.
- 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.
- 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.
- 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.
- Banyan Memory @labacacia/banyan-memoryPersistent, governed local memory for MCP-compatible AI clients.6% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from NuGet.
- Kilonova MCP @milnaos/kilonova-mcpPersistent local knowledge for AI coding agents with structured records, search, and DOT context.5% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from PyPI.
- Ace Context @dw-dwain/ace-context-mcpLocal-first memory for AI chats: save context in one chat, load it in any other via MCP.6% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.
- Jamgate @amirj4m/jamgateA neutral memory quality-gate MCP server: save_memory, recall_memory, forget_memory over stdio.6% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.
- Bourdon @bourdon/bourdonRecognition-first cross-agent memory federation. One shared memory across all your agents.6% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from PyPI.
- Acta — Verifiable Agent Memory @kylewilson04/acta-mcpVerifiable agent memory with signed ledger receipts — verify every write offline.9% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from MCPB.
- Wontopos MCP @wontopos/mcpWontopos (WOS) long-term memory (beta) - one memory across Claude Code, Cursor, and your agents.7% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.
- In Memoria @pi22by7-me/in-memoriaPersistent codebase intelligence that gives AI assistants memory across sessions6% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.
- Wyrm @ghosts/wyrmLocal-first memory for AI agents: ground truths, failure firewall, negotiated recall over MCP.6% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.
- Nexo @wazionapps/nexoCognitive memory for AI agents. Atkinson-Shiffrin, RAG, knowledge graph. 100+ tools.6% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.
- Memforge Memory @volsier/memforge-memoryTeam engineering memory for AI coding assistants. 47 MCP tools, pgvector semantic search.5% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.
- Mimir — Persistent Memory Engine @tcconnally/mimirPersistent memory for AI agents. 36+ MCP tools: encryption, decay, hybrid search, knowledge graph.6% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from a package registry.
- CogniRelay @stef-k/cognirelaySelf-hosted agent continuity server with bounded, recoverable memory and restart orientation.5% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from PyPI.
- Memorymesh @sparkvibe-io/memorymeshPersistent, zero-dependency AI memory using SQLite. Local-first, cross-tool portable.5% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from PyPI.
- Stellar Memory @sangjun0000/stellar-memoryPersistent AI memory using orbital mechanics. 100% local, zero API keys, MCP-native.6% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.
- Nex @nex-crm/nexOrganizational context & memory for AI agents. Connect 100+ tools into one knowledge graph.7% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.
