Merge pull request #9680 from AndreLYL/add-memkin

Add memkin (local-first personal memory for AI agents)

README.md

@@ -2056,6 +2056,7 @@ Persistent memory storage using knowledge graph structures. Enables AI models to
 - [aidesignblueprint/integrations](https://github.com/aidesignblueprint/integrations) [![aidesignblueprint/integrations MCP server](https://glama.ai/mcp/servers/aidesignblueprint/integrations/badges/score.svg)](https://glama.ai/mcp/servers/aidesignblueprint/integrations) 🐍 ☁️ - Read-only doctrine access for the Agentic AI Blueprint — the industry standard reference for safe, observable, and steerable AI agent UX. Browse and search 10 principles, clusters, curated implementation examples, and application guides for production agentic AI systems. 13 public tools require no credentials. `https://aidesignblueprint.com/mcp`
 - [aliasunder/vault-cortex](https://github.com/aliasunder/vault-cortex) [![vault-cortex MCP server](https://glama.ai/mcp/servers/aliasunder/vault-cortex/badges/score.svg)](https://glama.ai/mcp/servers/aliasunder/vault-cortex) 📇 🏠 ☁️ - MCP server for Obsidian vaults — search, memory, link graph, 23 tools, OAuth-protected.
 - [andreas-roennestad/openhive-mcp](https://github.com/andreas-roennestad/openhive-mcp) [![openhive-mcp MCP server](https://glama.ai/mcp/servers/andreas-roennestad/openhive-mcp/badges/score.svg)](https://glama.ai/mcp/servers/andreas-roennestad/openhive-mcp) 📇 ☁️ - Shared knowledge base where AI agents search and post problem-solution pairs. Agents query before solving, post after resolving. Semantic search via pgvector, duplicate detection, auto-scoring. `npx openhive-mcp`, Free to use
+- [AndreLYL/memkin](https://github.com/AndreLYL/memkin) [![MCP Score](https://glama.ai/mcp/servers/AndreLYL/memkin/badges/score.svg)](https://glama.ai/mcp/servers/AndreLYL/memkin) 📇 🏠 🍎 🪟 🐧 - Local-first personal memory for AI agents. Ingests Feishu/Lark chats and Claude Code / Codex sessions, distills them into a private entity knowledge graph (people, projects, decisions, tasks), and serves it to any agent over MCP — read and write. `npx memkin`
 - [Shweta-Mishra-ai/tokenmizer](https://github.com/Shweta-Mishra-ai/tokenmizer) [![Shweta-Mishra-ai/tokenmizer MCP server](https://glama.ai/mcp/servers/Shweta-Mishra-ai/tokenmizer/badges/score.svg)](https://glama.ai/mcp/servers/Shweta-Mishra-ai/tokenmizer) 🐍 🏠 🍎 🪟 🐧 - Graph-structured session memory for LLMs. Local OpenAI-compatible proxy that extracts tasks, decisions, and files into a typed knowledge graph, auto-checkpoints before context overflow, and resumes any session in ~250 tokens. 6 MCP tools including `why_decision` (traces why a decision changed, with reasons and evidence). `pip install tokenmizer`
   - [ashlesh-t/cognirepo](https://github.com/ashlesh-t/cognirepo) [![ashlesh-t/cognirepo MCP server](https://glama.ai/mcp/servers/ashlesh-t/cognirepo/badges/score.svg)](https://glama.ai/mcp/servers/ashlesh-t/cognirepo) 🐍 🏠 🍎 🪟  🐧 - Persistent memory and codebase context for AI coding agents. FAISS vector store, AST reverse index with O(1) symbol
   lookup, NetworkX knowledge graph, episodic journal, user behavior profiling, error tracking, and cross-agent session handoff. 34 MCP tools. Reduces token usage 50–80% on Python repos ≥ 15K LOC vs. raw