Side-by-side comparison of two Model Context Protocol servers — install paths, tools, quality signals, and directory engagement so you can pick the right one for Claude, Cursor, and other MCP clients.
Loads your personal profile, mined from your local Claude Code/Codex/OpenCode logs, so your agent works like you instead of a cold start. One tool, loademuloprofile. Run with uvx emulo mcp.
Memory manager for AI apps and Agents using various graph and vector stores and allowing ingestion from 30+ data sources
Quality signal
55/100 (Good)
48/100 (Fair)
Install path
npx · high
pip · high
Engagement
0 0 0 216
0 0 0 29,758
Tools
Mines local AI coding session logs without uploading raw dataSupports multiple AI coding platforms including Claude Code, Codex, Copilot CLI, OpenCodeCreates layered profiles for task-specific agent behaviorIntegrates natively or through adapters with various AI agentsOperates locally with zero dependencies and MIT license
Self-hosted knowledge graph with vector and graph searchIngestion from over 30 data sources and multiple formatsOntology generation grounded in cognitive sciencePersistent memory across AI agent sessionsSupport for multimodal data and evolving knowledge relationshipsOpen-source with Python client and plugins for integration
