I packaged decade of video infra battle scars into tools for AI agents
Hi HN, I’m Ashu, founder of VideoDB. I’ve spent a big chunk of my life building video infrastructure. Not video creation. Video plumbing. The stuff you only learn after production breaks: timebases, VFR, keyframes, audio sync drift, container quirks, partial uploads, live streams, retries, backpressure, codecs, ffmpeg flags, cost blowups, and “why is this clip unseekable on one player but fine on another”. This week we shared VideoDB Skills, a skill pack that lets AI agents call those infra primitives directly, instead of you wiring pipelines with screenshots plus FFmpeg glue. Repo:…
What it does
In the maker’s words, at launch
Hi HN, I’m Ashu, founder of VideoDB. I’ve spent a big chunk of my life building video infrastructure. Not video creation. Video plumbing. The stuff you only learn after production breaks: timebases, VFR, keyframes, audio sync drift, container quirks, partial uploads, live streams, retries, backpressure, codecs, ffmpeg flags, cost blowups, and “why is this clip unseekable on one player but fine on another”. This week we shared VideoDB Skills, a skill pack that lets AI agents call those infra primitives directly, instead of you wiring pipelines with screenshots plus FFmpeg glue. Repo: https://github.com/video-db/skills What it enables (infra level): - Ingest videos and live streams - Index and search moments - Return playable evidence links - Run server side edits and transforms - Trigger automations from video events Why this matters for agents: Agents can reason, write code, browse. But continuous media is still mostly invisible. In an agentic world, perception needs to be a first class interface, not a manual workflow. Try it quickly: npx skills add video-db/skills Then inside your agent: /videodb setup A few prompts to test: 1. “Upload this URL and give me a playable stream link” 2. “Search this folder for scenes with <keyword> and return clips” 3. “Capture my screen for 2 minutes and give me a structured summary” 4. “Monitor this RTSP feed and log events with timestamps” What I’m looking for from HN: 1. Does this feel like the right abstraction layer for perception in agent stacks? 2. What would you consider the minimum viable “perception API”? 3. Where do you think this fails in the real world, latency, cost, privacy, reliability? If you try it and it breaks, tell me the agent, OS, and the error output. I’ll fix it.
Does the same job
all alternatives →- IUI used AI to recreate a $4000 piece of audio hardware as a pluginJan 2026 · ▲160
Hi Hacker News, This is definitely out of my comfort zone. I just wanted to show you guys because I'm super proud of it. It's a 100% faithful recreation based off of the schematics, patents, and ROMs that were found online. So please watch the video and tell me what you think https://youtu.be/auOlZXI1VxA The reason why I think this is relevant is because I've been a programmer for 25 years and AI scares the shit out of me. I'm not a programmer anymore. I'm something else now. I don't know what it is but it's multi-disciplinary, and it doesn't involve writing code myself--for…
- VVideo2SRT2023 · ▲9
Hello HN! I’m a bachelors student pursuing Artificial Intelligence, Robotics and Signal processing and during the year I had the goal to build my first AI Tool and launch it. I got inspired by how capable Whisper is, and combined the Whisper CPP Bindings along with FFMPEG.Wasm to create a tool that is capable of transcribing and captioning video files that contain one or more video tracks. Along with that, I’ve also added the support for transcribing audio files with the option to export those outputs as .SRT, .WebVTT or simply a text file. All done privately on a user’s web browser with…
- IBI built an instant transcription service for any YouTube video2024 · transcrib.ee · ▲8
Hey HN! I built Transcrib.ee to help me generate transcripts for lectures on YouTube with no captions, especially multilingual lectures. I was constantly frustrated with videos that had no transcripts or inaccurate ones, so I built a tool and decided to share it with everyone. This tool uses Groq (an AI inference engine that's different from Grok and offers very fast processing) and OpenAI's Whisper model (really accurate in multilingual) to quickly transcribe any YouTube video, regardless of the language. It's been a game-changer for my studies! To make it even faster, I created a Chrome…
- ISI successfully failed at one-shot-ing a video codec like h.264Apr 2026 · github.com · ▲9
Read an article yesterday about the H.264 codec increasing their licensing fee by an astronomical amount. And as always, my first shot was how hard could it be to try and build a codec which could be that efficient. I've personally been on a drive to improve my ability to one-shot complex features, products, or make even surgical changes. It's been a few months since I've been doing that, and honestly, results have been great for both work and work/life balance. This was a fun experiment. It burned through tokens, but it helped me identify some more improvements I could make to my…
- MAMake AI motion videos with textFeb 2026 · framecall.com · ▲6
Saw the remotion claude skills launch earlier, and honestly even though I was surprised how decent some of the results turned out to be I ended up never trying it out with claude code because I knew I'd have to setup remotion, bundler etc and if I was already doing it once I thought I might as well turn it into a site where anyone could just write messages and get a video without any prerequisites. I also know Claude Code is not something everyone has and setting up remotion is a pain. And one of the biggest lessons I learned from this whole experience is that Opus is actually not that good…
- CACoding Agents swarming your codebaseSep 2025 · infrastructureas.ai · ▲9
I built this because I was tired of creating pull requests in 20 repositories just to change a single line of workflow job version. With Infra as AI, just mention the change. Agents work on all repos in parallel, read the docs, make a bunch of PRs and fill in the description. You can see the demo of the actual dashboard in the landing. Let me know your thoughts :) It means a lot to me!
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, March 2026
the whole month →
Switch from ChatGPT to Claude with import memory feature
AI · Mar 2026 · claude.com
