Script Snap – Extract code from videos
Hi HN, I'm lmw-lab, the builder behind Script Snap. The Backstory: I built this out of pure frustration. A while ago, I was trying to figure out a specific configuration for a project, and the only good resource I could find was a 25-minute YouTube video. I had to scrub through endless "smash the like button" intros and sponsor reads just to find a single 5-line JSON payload. I realized I didn't want an "AI summary" of the video; I just wanted the raw code hidden inside it. What's different: There are dozens of "YouTube to Text" summarizers out there. Script Snap is different because it is…
In plain words
Script Snap extracts code and technical content from videos, pulling out code snippets, terminal commands, API payloads, and security warnings directly from transcripts and on-screen visuals. Built for developers who need to quickly find specific code examples buried in long tutorial videos without wading through introductions and sponsorships. Unlike general video summarizers, it focuses exclusively on technical extraction rather than narrative summaries.
written from the facts on this page · September 2026
From the sources
In the maker’s words, at launch
Hi HN, I'm lmw-lab, the builder behind Script Snap. The Backstory: I built this out of pure frustration. A while ago, I was trying to figure out a specific configuration for a project, and the only good resource I could find was a 25-minute YouTube video. I had to scrub through endless "smash the like button" intros and sponsor reads just to find a single 5-line JSON payload. I realized I didn't want an "AI summary" of the video; I just wanted the raw code hidden inside it. What's different: There are dozens of "YouTube to Text" summarizers out there. Script Snap is different because it is explicitly designed as a technical extraction engine. It doesn't give you bullet points about how the YouTuber feels. It scans the transcript and on-screen visuals to extract specifically: Code snippets Terminal commands API payloads (JSON/YAML) Security warnings (like flagging sketchy npm installs) It strips out the "vibe" and outputs raw, formatted Markdown that you can copy straight into your IDE. Full disclosure on the launch: Our payment processor (Stripe) flagged us on day one (banks seem to hate AI tools), so I've pivoted to a manual "Concierge Alpha" for onboarding. The extraction engine is fully operational, just doing things the hard way for now. I'd love to hear your thoughts or harsh feedback on the extraction quality!
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
