It uses Playwright for crawling, deterministic analysis for tokens (colors, typography, spacing, CSS variables), and an LLM for semantic interpretation (component recipes, layout structure, design principles).

One command: design-memory learn

Output is a .design-memory/ folder that any LLM can consume to recreate the design with high fidelity.

Comments URL: https://news.ycombinator.com/item?id=47026620

Points: 1

# Comments: 0

ssm find "that stripe error" → finds the screenshot with the Stripe error message

It uses OCR to extract text and a local vision model (Ollama) to describe photos. Everything runs locally, no API keys.

The search is semantic so "connection failed" finds "network error" too.

What surprised me: indexing is the slow part (~2s per image for OCR). Search is basically instant.

Code: https://github.com/memvid/screenshot-memory

Would love feedback on the CLI UX.

Comments URL: https://news.ycombinator.com/item?id=46739459

Points: 2

# Comments: 0

The concept sounded absurd—storing text in video? But modern video codecs have been optimized for compression over decades. So, I converted text into QR codes, then encoded those as video frames, letting H.264/H.265 handle the compression.

The results were surprising. 10,000 PDFs compressed down to a 1.4GB video file. Search latency was around 900ms compared to Pinecone’s 820ms—about 10% slower. However, RAM usage dropped from over 8GB to just 200MB, and it operates entirely offline without API keys or monthly fees.

Technically, each document chunk is encoded into QR codes, which become video frames. Video compression handles redundancy between similar documents effectively. Search works by decoding relevant frame ranges based on a lightweight index.

You get a vector database that’s just a video file you can copy anywhere.

GitHub: https://github.com/Olow304/memvid

Comments URL: https://news.ycombinator.com/item?id=44125598

Points: 61

# Comments: 23

The idea sounds absurd - why would you store text in video? But modern video codecs have spent decades optimizing for compression. So I tried converting text into QR codes, then encoding those as video frames, letting H.264/H.265 handle the compression magic.

The results surprised me. 10,000 PDFs compressed down to a 1.4GB video file. Search latency came in around 900ms compared to Pinecone’s 820ms, so about 10% slower. But RAM usage dropped from 8GB+ to just 200MB, and it works completely offline with no API keys or monthly bills.

The technical approach is simple: each document chunk gets encoded into QR codes which become video frames. Video compression handles redundancy between similar documents remarkably well. Search works by decoding relevant frame ranges based on a lightweight index.

You get a vector database that’s just a video file you can copy anywhere.

https://github.com/Olow304/memvid

Comments URL: https://news.ycombinator.com/item?id=44123033

Points: 15

# Comments: 3