From 5a4ea801a939cd85b56a7a1329243e5da5d0e13a Mon Sep 17 00:00:00 2001
From: JackJin <1037461232@qq.com>
Date: Mon, 2 Nov 2026 11:31:06 +0800
Subject: [PATCH] Add jackjin1997/markindex to Knowledge & Memory

---
 README.md | 1 +
 1 file changed, 1 insertion(+)

diff --git a/README.md b/README.md
index 539d1b0e0..5103450f0 100644
--- a/README.md
+++ b/README.md
@@ -3064,6 +3064,7 @@ Persistent memory storage using knowledge graph structures. Enables AI models to
 - [irisxc4/memoryguard](https://github.com/irisxc4/memoryguard) [![irisxc4/memoryguard MCP server](https://glama.ai/mcp/servers/irisxc4/memoryguard/badges/score.svg)](https://glama.ai/mcp/servers/irisxc4/memoryguard) 🐍 🏠 🍎 🪟 🐧 - Local-first governed shared memory for coding agents with CLI and desktop console: classify, dedupe, supersede, quarantine and roll back memories.
 - [zsxh1990/pr-genius](https://github.com/zsxh1990/pr-genius) [![zsxh1990/pr-genius MCP server](https://glama.ai/mcp/servers/zsxh1990/pr-genius/badges/score.svg)](https://glama.ai/mcp/servers/zsxh1990/pr-genius) 🐍 🏠 - Pull request contribution advisor based on case studies from real repos: merge probability analysis, pattern matching and contribution strategy.
 - [JAAvila-Of/vivac](https://github.com/JAAvila-Of/vivac) [![JAAvila-Of/vivac MCP server](https://glama.ai/mcp/servers/JAAvila-Of/vivac/badges/score.svg)](https://glama.ai/mcp/servers/JAAvila-Of/vivac) 🦀 🏠 🍎 🪟 🐧 - A provenance tree for coding agents: every node records the node it was born from, so the agent can ask why the work is where it is. A session brief with the standing decisions and what not to touch, a close that refuses over open work, and decisions kept with the alternatives they rejected. Local JSON-lines file, no telemetry.
+- [jackjin1997/markindex](https://github.com/jackjin1997/markindex) [![jackjin1997/markindex MCP server](https://glama.ai/mcp/servers/jackjin1997/markindex/badges/score.svg)](https://glama.ai/mcp/servers/jackjin1997/markindex) 📇 🏠 🍎 🐧 - Vectorless, structure-first retrieval over large Markdown libraries: walk library, folder, document and section trees, read original text with line numbers for citations, and fall back to mixed Chinese/English BM25 search. Five read-only tools, no embeddings, no API key.
 - [jaimenbell/rag-mcp](https://github.com/jaimenbell/rag-mcp) [![jaimenbell/rag-mcp MCP server](https://glama.ai/mcp/servers/jaimenbell/rag-mcp/badges/score.svg)](https://glama.ai/mcp/servers/jaimenbell/rag-mcp) 🐍 🏠 - Minimal local RAG that vector-searches a document corpus and returns cited passages.
 - [JamesANZ/cross-llm-mcp](https://github.com/JamesANZ/cross-llm-mcp) 📇 🏠 - Cross-LLM communication and memory sharing so different AI models can collaborate and share context across conversations.
 - [JamesANZ/memory-mcp](https://github.com/JamesANZ/memory-mcp) 📇 🏠 - Store and retrieve conversation memories from multiple LLMs in MongoDB, with timestamps and LLM identification.