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.
Local-first persistent memory for AI coding agents. Captures facts, decisions, patterns, and architecture notes in SQLite (with optional cloud embeddings) to reduce repeated context across sessions.
Memory manager for AI apps and Agents using various graph and vector stores and allowing ingestion from 30+ data sources
Quality signal
48/100 (Fair)
48/100 (Fair)
Install path
npx · high
pip · high
Engagement
0 0 0 2
0 0 0 29,758
Tools
Local-first storage using SQLite with optional cloud embeddingsToken-aware context retrieval with progressive disclosureSupport for multiple MCP-compatible clients including Claude Code and CodexImport existing project memory files automaticallyTeam-scoped memory synchronization through gitWeb-based UI for inspection and management
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
