From 3599db83e80c22c7129486e490899a38fb7fc545 Mon Sep 17 00:00:00 2001
From: BaskDuan <133692311@qq.com>
Date: Mon, 27 Apr 2026 16:05:51 +0800
Subject: [PATCH] Add SubDownload

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

diff --git a/README.md b/README.md
index 2953cb0b..7c0efd41 100644
--- a/README.md
+++ b/README.md
@@ -1663,6 +1663,7 @@ Persistent memory storage using knowledge graph structures. Enables AI models to
 - [smith-and-web/obsidian-mcp-server](https://github.com/smith-and-web/obsidian-mcp-server) 📇 🏠 🍎 🪟 🐧 - SSE-enabled MCP server for remote Obsidian vault management with 29 tools for notes, directories, frontmatter, tags, search, and link operations. Docker-ready with health monitoring.
 - [smriti-AA/smriti](https://github.com/smriti-AA/smriti) [![smriti MCP server](https://glama.ai/mcp/servers/@Smriti-AA/smriti/badges/score.svg)](https://glama.ai/mcp/servers/@Smriti-AA/smriti) 🦀 🏠 🍎 🪟 🐧 - Self-hosted knowledge store and memory layer for AI agents with knowledge graph, wiki-links, full-text search (FTS5), and agent memory with namespaces and TTL.
 - [skill-seekers/Skill_Seekers](https://github.com/yusufkaraaslan/Skill_Seekers) [![yusufkaraaslan/Skill_Seekers MCP server](https://glama.ai/mcp/servers/yusufkaraaslan/Skill_Seekers/badges/score.svg)](https://glama.ai/mcp/servers/yusufkaraaslan/Skill_Seekers) 🐍 🏠 🍎 🪟 🐧 - Transform 17 source types (docs, GitHub repos, PDFs, videos, Jupyter, Confluence, Notion, Slack/Discord) into AI-ready skills and RAG knowledge. 35 MCP tools for scraping, packaging, enhancing, and exporting to vector databases (Weaviate, Chroma, FAISS, Qdrant). Supports 16+ target platforms.
+- [SubDownload](https://subdownload.com) 🏎️ ☁️ 📺 - YouTube knowledge base for AI agents. Summarize videos, fetch full transcripts (including videos without captions, via AI ASR), search channels and playlists, and save everything into a per-user knowledge base for cross-session recall. OAuth 2.1 with Dynamic Client Registration. `https://api.subdownload.com/mcp`, free credits on signup.
 - [TechDocsStudio/biel-mcp](https://github.com/TechDocsStudio/biel-mcp) 📇 ☁️ - Let AI tools like Cursor, VS Code, or Claude Desktop answer questions using your product docs. Biel.ai provides the RAG system and MCP server.
 - [tomohiro-owada/devrag](https://github.com/tomohiro-owada/devrag) 🏎️ 🏠 🍎 🪟 🐧 - Lightweight local RAG MCP server for semantic vector search over markdown documents. Reduces token consumption by 40x with sqlite-vec and multilingual-e5-small embeddings. Supports filtered search by directory and filename patterns.
 - [topoteretes/cognee](https://github.com/topoteretes/cognee/tree/dev/cognee-mcp) 📇 🏠 - Memory manager for AI apps and Agents using various graph and vector stores and allowing ingestion from 30+ data sources