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 agents. SQLite + local embeddings (all-MiniLM-L6-v2), hybrid semantic + FTS5 recall, secret detection, and contradiction handling. 6 MCP tools (remember, recall, forget, feedback, context, status) over stdio. Zero cloud, no API keys, fully offline. Works with Claude Desktop/Code, Cursor, and Windsurf. npm install -g @hbarefoot/engram
Hindsight: Agent Memory That Works Like Human Memory - Built for AI Agents to manage Long Term Memory
Quality signal
53/100 (Fair)
40/100 (Fair)
Install path
npx · high
npx · high
Engagement
0 0 0 7
1 0 0 19,087
Tools
Local SQLite database with all-MiniLM-L6-v2 embeddingsHybrid semantic and FTS5 full-text search recallAutomatic secret detection on every write operationSix MCP-native tools: remember, recall, forget, feedback, context, statusFully offline operation with zero external dependenciesIn-process integration with no separate server or IPC overhead
State-of-the-art performance on LongMemEval benchmarkSupports multiple LLM providers including OpenAI and AnthropicEasy integration via LLM wrapper or SDK/APIDocker deployment with PostgreSQL or Oracle AI Database supportClient libraries for Python and Node.jsEmbedded Python option without server dependency