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.
Reversibly compress a large tool output to a recoverable 8-hex handle over stdio, expand it on demand, and report a local token/dollar savings ledger.
Self-learning memory for AI coding agents. Observes tool sequences, user preferences, and recurring fixes; confidence-based promotion (hits ≥5 → mature, ≥10 → rule) so agents stop repeating mistakes without explicit instruction. SQLite-backed, project-aware, zero external deps. Works with Claude Code, Cursor, Windsurf, Goose, Codex. Published on PyPI as instinct-mcp and registered in the MCP Registry.