I built a 1.8MB native app with self-built UI, vision and AI libraries
Details
- External ID
- 46108892
- Source
- HN
- Company
- —
- Product
- I built a 1.8MB native app with self-built UI, vision and AI libraries
- Website domain
- github.com
- Launched
- Dec. 1, 2025
- Cohort
- —
- Upvotes
- 15
- Upvotes percentile
- 0.6040076335877863
- Tags
- —
- Fetched at
- Sept. 7, 2026, 9:25 p.m.
- Updated at
- Sept. 7, 2026, 9:25 p.m.
Enrichment
- Theme
- systems tools and desktop utilities
- Vertical
- Horizontal
- Function
- Dev tools
- Audience
- Developer
- AI stance
- AI feature
- Project type
- Hobby / open-source project
- Normalized one-liner
- native app with vision and ai
- Manually corrected
- False
Could you build this?
No Hand-rolling a custom UI engine, computer vision library, and AI inference runtime into a 1.8MB native binary requires extreme low-level systems engineering, math, and binary size optimization.
What it would actually take: This architecture requires C/C++ or Zig with custom software rendering (or direct bare-metal GPU shaders via Metal/Vulkan), handwritten matrix math routines, and custom quantized neural net kernels without third-party frameworks like PyTorch or OpenCV. The hardest part is stripping standard runtime bloat while implementing custom convolution, rasterization, and tensor graph execution. It requires rare, elite expertise in embedded systems, graphics programming, and compiler-level binary optimization.
Discussion
20 comments analyzed.
Concerns raised: No source code published, only JPGs, readme, and Google Drive link - unverifiable claims, VirusTotal flagged file as malicious (1/69 security vendors), Suspicious TCP/UDP traffic on non-standard ports and unknown server IP, Untrusted Windows executable download barrier without video demonstration, Downloaded from unauthorized source without official store distribution
Feature requests: Publish source code to demonstrate skills and build trust, Create video demonstrating the project functionality, Distribute through official storefronts instead of direct downloads
Competitors
Other products that read as similar to this one — 718 launches clear the similarity bar, closest 8 shown.
Attention rank: #315 of 719 (itself plus its competitors, highest first — normalized so YC and Product Hunt are compared fairly).
Launched 33 days after the earliest competitor.
- I built a museum of AI interfaces · hn · 2026-08-24 · 6 upvotes · similarity 0.51
- I run a vision model on every screenshot, locally, on a 4GB GPU · hn · 2026-06-13 · 36 upvotes · similarity 0.50
- interfaces-that-think · github · 2026-09-28 · 13 upvotes · similarity 0.47
- Epic-Package · github · 2026-09-22 · 9 upvotes · similarity 0.46
- I built a native app for coding agents with Rust and GPUI · hn · 2026-08-16 · 39 upvotes · similarity 0.46
- lean-launcher · github · 2026-09-15 · 15 upvotes · similarity 0.46
- I built an Android OS in the browser · hn · 2026-05-30 · 28 upvotes · similarity 0.46
- I built an app for vibe-coding games · hn · 2025-12-18 · 5 upvotes · similarity 0.46
Other launches for this product
- No other launches for this product.
Same idea, different domain
Nobody's really built a dev tools tool for Sales yet.