Merge pull request #4499 from yakuphanycl/add-instinct-mcp

Add instinct — self-learning memory for AI coding agents 🤖🤖🤖

README.md

@@ -1577,6 +1577,7 @@ Persistent memory storage using knowledge graph structures. Enables AI models to
 - [whynowlab/jarvis-orb](https://github.com/whynowlab/jarvis-orb) [![whynowlab/jarvis-orb MCP server](https://glama.ai/mcp/servers/whynowlab/jarvis-orb/badges/score.svg)](https://glama.ai/mcp/servers/whynowlab/jarvis-orb) 🐍 🏠 - Persistent 4-tier AI memory (episodic, semantic, project, procedural) with temporal scoring, contradiction detection, entity tracking, and real-time desktop visualization orb.
 - [teolex2020/AuraSDK](https://github.com/teolex2020/AuraSDK) [![teolex2020-aurasdk MCP server](https://glama.ai/mcp/servers/teolex2020-aurasdk/badges/score.svg)](https://glama.ai/mcp/servers/teolex2020-aurasdk) 🐍 🏠 — Persistent cognitive memory for Claude Desktop. Sub-ms recall, offline, encrypted.
 - [arthurpanhku/Arthor-Agent](https://github.com/arthurpanhku/Arthor-Agent) [![arthor-agent MCP server](https://glama.ai/mcp/servers/@arthurpanhku/arthor-agent/badges/score.svg)](https://glama.ai/mcp/servers/@arthurpanhku/arthor-agent) 🐍 🏠 ☁️ - ...
+- [yakuphanycl/instinct](https://github.com/yakuphanycl/instinct) [![yakuphanycl/instinct MCP server](https://glama.ai/mcp/servers/yakuphanycl/instinct/badges/score.svg)](https://glama.ai/mcp/servers/yakuphanycl/instinct) 🐍 🏠 🍎 🪟 🐧 - 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.
 
 ### ⚖️ <a name="legal"></a>Legal