- Memory Arbiter @billy12151/memory-arbiter-mcpLocal SQLite MCP memory: evidence-based recall, advisory conflict notices, authorized governance.5% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from a package registry.9 GitHub stars.
- Context @alex-feel/mcp-context-serverAn MCP server that provides persistent multimodal context storage for LLM agents.3% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from PyPI.9 GitHub stars.
- Lore @agentkitai/loreCross-agent memory over MCP: hybrid recall, knowledge graph, private/shared visibility, redaction.5% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from PyPI.9 GitHub stars.
- Engram @hbarefoot/engramLocal-first persistent memory for AI agents — SQLite + local embeddings, MCP-native, no cloud.4% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.9 GitHub stars.
- Emercoin Agent (moved) @emercoin/emercoin-agentMoved to com.steledger/gateway — same service, now hosted at api.steledger.com.Not assessed yet.Runs on your machine, installed from a package registry.9 GitHub stars.
- Blue Synergy Cortex @novotapeter-bs/cortexLong-term, drift-free cognitive memory engine for AI Agents and Cursor IDE.9% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; no sign-in.8 GitHub stars.
- skillmem @liza-studio/skillmemSkill memory for coding agents: learn, recall, reinforce, decay. Local SQLite, no API key.4% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from PyPI.8 GitHub stars.
- remem-mcp — Local-first MCP Memory + CodeGraph + Wiki @tinhien11/remem-mcpLocal-first memory for AI coding agents. Memory + CodeGraph + Wiki in one SQLite file.4% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.8 GitHub stars.
- Crbro Memory @octonove/crbro-memoryPersistent file-based memory for AI agents: inspectable, versionable, fully local.8% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.8 GitHub stars.
- mozg @mozg/mozgExam-scored knowledge brains your agent searches over MCP, plus a public list of their gaps.8% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; you sign in with your account.8 GitHub stars.
- TinyContext @tinysuitehq/tinycontextToken-light local memory with SQLite hybrid retrieval for MCP agents.3% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from Docker.8 GitHub stars.
- CPersona @cloto-dev/cpersonaPersistent AI memory in one SQLite file: 3-layer hybrid search, confidence scoring, 29 tools.4% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from PyPI.8 GitHub stars.
- Kortexio Memory @kortexio/memoryHosted ambient memory for AI agents. Retrieve context and save notes via MCP tools with OAuth.10% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from a package registry.8 GitHub stars.
- inspeximus: agent memory with provenance, GDPR erasure and a tamper-evident audit trail @dancenitra/inspeximusSelf-correcting agent memory: recall, supersede, revert, forget, GDPR erasure, audit receipts.4% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from PyPI.8 GitHub stars.
- Mnemo @dancenitra/mnemoSelf-correcting agent memory + MCP server: recall, supersede/revert/review corrections, erasure.5% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from PyPI.8 GitHub stars.
- kg @nnar1o/kg-mcpLocal knowledge graph memory MCP server for AI assistants.4% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from a package registry.8 GitHub stars.
- Wikimoth @juliangeymonat-jpg/wikimothDeterministic, token-minimal agent memory: multi-hop [[wikilink]] recall with no LLM in the loop.4% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from PyPI.8 GitHub stars.
- Recall @recallworks/recallOpen-source MCP memory server. Persistent, searchable, tiered memory across sessions.4% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from PyPI.8 GitHub stars.
- Dakera @dakera-ai/dakera-mcpAgent memory engine — 102 MCP tools, self-hosted, single Rust binary5% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from Docker.8 GitHub stars.
- Palace @ancientice/palace-rsLocal-first memory for coding agents — MCP server, single SQLite file, local embeddings4% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from MCPB.8 GitHub stars.
- Sdk @mnemopay/sdkMemory + wallet for AI agents. Real payment rails, Agent FICO 300-850, Merkle audit, identity.9% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.8 GitHub stars.
- Epitome @gunning4it/epitome-mcpPersonal AI memory — gives every AI agent shared, persistent memory of you9% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; it needs your API key.8 GitHub stars.
- Artel @nicolasprimeau/artelSelf-hosted shared-memory & coordination mesh for AI agent fleets. You host it; agents connect.6% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from a package registry.8 GitHub stars.
- Open Brain @bobby-cell-commits/open-brainGraph-structured MCP memory server. 37.2% LongMemEval. Auto dedup, themes, decay, synthesis.5% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from a package registry.8 GitHub stars.
