Mcptube – Karpathy's LLM Wiki idea applied to YouTube videos
I watch a lot of Stanford/Berkeley lectures and YouTube content on AI agents, MCP, and security. Got tired of scrubbing through hour-long videos to find one explanation. Built v1 of mcptube a few months ago. It performs transcript search and implements Q&A as an MCP server. It got traction (34 stars, my first open-source PR, some notable stargazers like CEO of Trail of Bits). But v1 re-searched raw chunks from scratch every query. So I rebuilt it. v2 (mcptube-vision) follows Karpathy's LLM Wiki pattern. At ingest time, it extracts transcripts, detects scene changes with ffmpeg,…
In plain words
Mcptube is an open-source tool that lets users search and ask questions about YouTube video content, particularly Stanford and Berkeley lectures on AI topics. It extracts transcripts, detects scene changes, and generates structured summaries from video frames to create searchable knowledge bases. Users can query videos through a command-line interface or as an MCP server integrated with tools like Claude and VS Code, eliminating the need to scrub through hour-long videos to find specific explanations.
written from the facts on this page · September 2026
From the sources
In the maker’s words, at launch
I watch a lot of Stanford/Berkeley lectures and YouTube content on AI agents, MCP, and security. Got tired of scrubbing through hour-long videos to find one explanation. Built v1 of mcptube a few months ago. It performs transcript search and implements Q&A as an MCP server. It got traction (34 stars, my first open-source PR, some notable stargazers like CEO of Trail of Bits). But v1 re-searched raw chunks from scratch every query. So I rebuilt it. v2 (mcptube-vision) follows Karpathy's LLM Wiki pattern. At ingest time, it extracts transcripts, detects scene changes with ffmpeg, describes key frames via a vision model, and writes structured wiki pages. Knowledge compounds across videos rather than being re-discovered. FTS5 + a two-stage agent (narrow then reason) for retrieval. MCPTube works both as CLI (BYOK) and MCP server. I tested MCPTube with Claude Code, Claude Desktop, VS Code Copilot, Cursor, and others. Zero API key needed server-side. Coming soon: I am also building SaaS platform. This platform supports playlist ingestion, team wikis, etc. I like to share early access signup: https://0xchamin.github.io/mcptube/ Happy to discuss architecture tradeoffs — FTS5 vs vectors, file-based wiki vs DB, scene-change vs fixed-interval sampling. Give it a try via `pip install mcptube`. Also, please do star the repo if you enjoy my contribution (https://github.com/0xchamin/mcptube)
Does the same job
all alternatives →- AKA Karpathy-style LLM wiki your agents maintain (Markdown and Git)Apr 2026 · github.com · ▲260
I shipped a wiki layer for AI agents that uses markdown + git as the source of truth, with a bleve (BM25) + SQLite index on top. No vector or graph db yet. It runs locally in ~/.wuphf/wiki/ and you can git clone it out if you want to take your knowledge with you. The shape is the one Karpathy has been circling for a while: an LLM-native knowledge substrate that agents both read from and write into, so context compounds across sessions rather than getting re-pasted every morning. Most implementations of that idea land on Postgres, pgvector, Neo4j, Kafka, and a dashboard. I…
- HLHow LLMs Work – Interactive visual guide based on Karpathy's lectureApr 2026 · ynarwal.github.io · ▲245
All content is based on Andrej Karpathy's "Intro to Large Language Models" lecture (youtube.com/watch?v=7xTGNNLPyMI). I downloaded the transcript and used Claude Code to generate the entire interactive site from it — single HTML file. I find it useful to revisit this content time to time.
- YMYouTube MCP, give any AI agent access to YouTubeMay 2026 · github.com · ▲5
I have a long YouTube watch-later playlist and wanted Claude to help me triage it by summarizing each video. It couldn't. I later discovered YouTube is not accessible to Claude, ChatGPT and majority of AIs. So I built this MCP server to fix that. This is a local MCP server that gives any MCP-compatible client (Claude, ChatGPT, OpenClaw and others) 8 tools for working with YouTube content: - fetch full transcript, with or without timestamps - download transcript as a .md file - get video metadata (title, channel, views, duration, likes, description) - search within captions for a keyword or…
MCP server for full YouTube workflowJun 2026 · vidseeds.ai · ▲4Analyze videos, generate metadata, then automate publishing
More ai this month
the category →
I trained a 125M-parameter transformer to autocomplete piano performances in real time (~108 notes/sec on an iPhone 15). The idea is basically GitHub Copilot or Tabnine, except instead of prompting it with code, you prompt it by playing a few notes on a MIDI piano. The model then continues what you played, entirely on-device. The app is free if anyone wants to try it. Happy to answer questions about the model, training, Core ML, or the many things that didn't work.
AI · 17d ago · simedw.com
Astute▲585Automate your B2B brand going viral, with new media creators
AI · 18d ago · company-app.joinastute.com
Hey HN, Henry from Cactus here! We previously released Cactus Needle, a 14MB agentic LLM for tool call, device use, and structured extraction for phones, wearables, smart homes, small robots and microcontrollers. We got really great feedback here, and have now incorporated the suggestions to release Needle 2. The whole model is a single 14MB binary that runs a full session in 28MB of RAM; 45m parameters at 2bit compression. Needle hits 500 tokens/sec decode speed on a Raspberry Pi 5, sits between 400-1,500 tokens/sec on VR devices like Meta Quest 3S and Apple Vision Pro, and ranges…
AI · 27d ago · cactuscompute.com
Launched alongside, April 2026
the whole month →
- AG
Thought the resources for GPU arch were lacking, so here we are
Life & fun · Apr 2026 · jaso1024.com
- IB
Built a ~9M param LLM from scratch to understand how they actually work. Vanilla transformer, 60K synthetic conversations, ~130 lines of PyTorch. Trains in 5 min on a free Colab T4. The fish thinks the meaning of life is food. Fork it and swap the personality for your own character.
AI · Apr 2026 · github.com
- BC
Life & fun · Apr 2026 · sam-burns.com
- IB
With social media and now AI, its important to keep the indie web alive. There are many people who write frequently. Blogosphere tries to highlight them by fetching the recent posts from personal blogs across many categories. There are two versions: Minimal (HN-inspired, fast, static): https://text.blogosphere.app/ Non-minimal: https://blogosphere.app/ If you don't find your blog (or your favorite ones), please add them. I will review and approve it.
AI · Apr 2026 · text.blogosphere.app