VMTP

In plain words

VMTP is a video processing protocol that enables large language models and AI agents to understand video input. Designed for developers and AI practitioners, it provides an API for integrating video understanding capabilities into LLM applications. The protocol allows AI systems to process and analyze video content, making it useful for applications requiring video comprehension alongside language processing.

written from the facts on this page · September 2026

From the sources

VMTP or Visual Media Transcription Protocol is a video processing protocol for LLMs. Using this, you can let your LLMs & AI agents understand video input.

• 
  LLM Gateway2025 · llmgateway.io · ▲296

  I built an OpenAI-compatible LLM gateway that routes requests to OpenAI, Anthropic, Ollama, vLLM, llama-server, SGLang... anything that speaks /v1/chat/completions. Single Go binary, one YAML config file, no infrastructure. It does the things you'd expect from this kind of gateway... semantic routing via a three-layer cascade (keyword heuristics, embedding similarity, LLM classifier) that picks the best model when clients omit the model field, weighted round-robin load balancing across local inference servers with health checks and failover. The part I think is most…

• 
  LLM Explorer2023 · ▲152

  Find your best LLM for a local inference

• HL
  How 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.

• 
  Vmaker AI Video Editor2024 · vmaker.com · ▲312

  Turn your raw videos into wow videos in minutes

• 
  An MCP server that gives LLMs temporal awareness and time calculation2025 · github.com · ▲91

  This is an open‑source Model Context Protocol (MCP) server that gives any LLM a sense of the passage of time. Most MCP demos wire LLMs to external data stores. That’s useful, but MCP is also a chance to give models perception — extra senses beyond the prompt text. Six functions (`current_datetime`, `time_difference`, `timestamp_context`, etc.) give Claude&#x2F;GPT real temporal awareness: It can spot pauses, reason about rhythms, and even label a chat’s “three‑act structure”. Runs locally in <60 s (Python) or via a hosted demo. If time works, what else could we surface? - Location &#x2F;…

• 
  Vany2025 · vany.ai · ▲108

  Hey HN - long-time reader, first-time poster, My friends and I built Vany, a tool that responds to any LLM query with a TikTok – essentially a short narrated video answer to your prompt. We built it because we often prefer watching a short video over reading a block of text or long article. There are many impressive AI video tools out there that generate visually striking content for creators, but we wanted something that gives helpful videos back to the queries we put into LLMs or search engines every day. Vany lets anyone quickly get an engaging and useful video back to any question –…

Questions this answers

• llm llvm

• 
  Spira Maxima▲578

  Video model that turns script into viral social media videos

  AI · 17d ago · spira.ai

• 
  Rill Browser▲540

  The browser where Claude Code and Codex work beside you

  AI · 17d ago · rill.love

• 
  Germany's new sovereign AI model Kolibri▲424

  Kolibri is Aleph Alpha

  AI · 19d ago · tej.as

• 
  Giving Opus 5.5 a simulated paint canvas▲392

  Paintings by AI models: programs run through a simulation of oil paint.

  AI · 20d ago · stillwet.art

• 
  Onepin▲384

  AI voiceover with every name, price and date said right

  AI · 30d ago · onepin.ai

• 
  PixVerse R2▲381

  A real-time world model you can explore and change

  AI · 29d ago · world.pixverse.video

• 
  I made an open-source laptop from scratch▲3,237

  Hello! I'm Byran. I spent the past ~6 months engineering a laptop from scratch. It's fully open-source on GH at: https:&#x2F;&#x2F;github.com&#x2F;Hello9999901&#x2F;laptop

  Dev tools · 2025 · byran.ee

• TI
  Tetris in a PDF▲1,289

  I realized that the PDF engines of modern desktop browsers (PDFium and PDF.js) support JavaScript with enough I&#x2F;O primitives to make a basic game like Tetris. It was a bit tricky to find a union of features that work in both engines, but in the end it turns out that showing&#x2F;hiding annotation "fields" works well to make monochrome pixels, and keyboard input can be achieved by typing in a text input box. All in all it's quite janky but a nice reminder of how general purpose PDF scripting can be. The linked PDF is all ASCII so you can just open it in a text editor, or have a look at…

  Life & fun · 2025 · th0mas.nl

• 
  21st.dev▲1,211

  I originally built this app to organize and reuse interesting React + Tailwind components I came across on Twitter, inspired by the shadcn&#x2F;ui approach. Later, a friend started contributing their own components, and it got me thinking—this could grow into something bigger, like an NPM for design engineers to share and use components. Would love to hear your thoughts!

  Dev tools · 2025 · 21st.dev

• 
  JoggAI 2.0: AI Avatar Generator▲967

  Create lifelike, personalized AI avatars from text prompts

  AI · 2025 · jogg.ai

• 
  Lovable + Builder.io▲873

  Turn Figma designs into full stack apps with AI

  Dev tools · 2025 · figma.com

• 
  Cs16.css – CSS library based on Counter Strike 1.6 UI▲819

  CSS library based on Counter Strike 1.6 UI.

  Life & fun · 2025 · cs16.samke.me