- Openfuse @openfused/openfuse-mcpEncrypted mail, shared memory, and persistent context for AI agents.7% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.18 GitHub stars.
- Agent Knowledge @keshrath/agent-knowledgeCross-session memory for AI agents - knowledge graph, scoring, semantic search5% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.18 GitHub stars.
- Alaya @securityronin/alaya-mcpLocal memory engine for AI agents with knowledge graphs, forgetting, and semantic recall4% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.18 GitHub stars.
- NeuroDock Cognitive Graph @tlennon-ie/neurodock-mcp-cognitive-graphA local typed-edge graph of people, projects, and decisions that externalises memory.4% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from PyPI.16 GitHub stars.
- openchronicle-mcp @csoai-org/openchronicle-mcpMemory database for LLM agents — persistent semantic + keyword memory, project namespacing, served o4% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from PyPI.16 GitHub stars.
- Titen Memory @ramaaditya49/titen-memoryEvidence-grounded agent memory with mandatory provenance, on local SQLite or Cloudflare D15% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.16 GitHub stars.
- Lians Agent Memory @ebeirne/liansBitemporal memory for AI agents with point-in-time recall and tamper-evident audit history.5% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from PyPI.16 GitHub stars.
- Engram @rwnalds/engramGit-backed markdown memory for AI agents; search hides superseded and archived notes.4% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from Docker.16 GitHub stars.
- Zaxy @syndicalt/zaxyEvent-sourced, auditable agent memory over MCP: cited checkout, replayable provenance.5% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from PyPI.16 GitHub stars.
- Agentic Task System (ATS) @renezander030/agentic-task-systemPersistent task context across TickTick, Notion, GitHub, Obsidian, Taskmaster and Beads6% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.16 GitHub stars.
- Remembra Relay @remembra-ai/remembraCross-agent handoff: the next coding agent starts from the last one's facts, not a blank page.5% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from PyPI.16 GitHub stars.
- Memtomem @memtomem/memtomemMarkdown-first long-term memory for AI agents. Hybrid BM25 + vector search, runs locally.4% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from PyPI.15 GitHub stars.
- NexusMem @yaminbkk/nexusmemLocal-first memory for AI coding agents: shell history with exit codes, git diffs, docs, MCP.5% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.15 GitHub stars.
- Midas @vornicx/midasLocal-first, source-traceable agent memory — no LLM at ingest, fully offline6% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from PyPI.15 GitHub stars.
- Pulse8 Ai Cortex Knowledge Vault @synpulse8-opensource/pulse8-ai-cortex-knowledge-vaultAgent-native knowledge OS on Markdown: typed graph, hybrid search, and compiler over MCP.5% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from PyPI.15 GitHub stars.
- Lore @jordanhindo/loreLightweight MCP for infinite agent memory. Any agent, any session, anytime.6% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.15 GitHub stars.
- PMLL Memory @drqedwards/pmll-memory-mcpPMLL Memory MCP — persistent KV context memory and Q-promise deduplication.5% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.15 GitHub stars.
- Docdex @bekirdag/docdexFast per-repo documentation indexer and full-text search MCP server for codebases.4% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.15 GitHub stars.
- Elefante @amenophis1er/elefanteOpen, Git-native memory protocol for MCP agents. Portable, versioned, human-editable.4% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.15 GitHub stars.
- Octobrain @muvon/octobrainPersistent memory for AI assistants with semantic search and knowledge graph relationships.4% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.15 GitHub stars.
- Memwright @bolnet/memwrightEmbedded memory for AI agents with SQLite, pgvector, and Neo4j graph search.8% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from PyPI.14 GitHub stars.
- Myc @aistastudio/mycTask queue, decisions and memory for coding agents. Local SQLite, no network. Requires Bun.4% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.14 GitHub stars.
- Koragraph @koragraph/koragraphLocal multi-repo code graph over MCP. Blast radius, call graphs, and memory anchored to code.7% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.14 GitHub stars.
- Global Agent Memory @ozankasikci/global-agent-memoryShared, project-aware memory for Claude Code, Codex, and other agents with human review.4% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from PyPI.14 GitHub stars.
