← All articles

Top LLM & AI Tools on Hacker News
Week of May 18 – May 24, 2026, 2026

📅 May 22, 2026 🔬 22 tools reviewed ⏱ Auto-tested in Docker 📊 Scored on 11 criteria

Every day we scrape Hacker News for new LLM and AI tool submissions, spin up a Docker container, install and run each app, then score it across 11 weighted criteria. This week we reviewed 22 tools. These are the 5 that scored highest.

#1
👀 Worth Watching
Reviewed 2026-05-21
Overall
75/100

This app demonstrates a novel approach to reverse-engineering Apple's video wallpapers, as indicated by its uniqueness and the lack of similar projects, with 332 HN points and 30 comments analyzed.

novelty
8/10
community
6/10
ease of use
7/10
differentiation
8/10
#2
👀 Worth Watching
Reviewed 2026-05-18
Overall
68/100

The app's ability to automate opt-outs for 500 data broker sites is a unique approach, as seen in the page title and web page signals, with a detected version of 1.1 and no direct equivalent found.

novelty
8/10
community
6/10
ease of use
2/10
differentiation
7/10
Overall
67/100

The app is a unique tactical map-based WWII submarine simulator, which is a new approach in the gaming industry, and there are no similar tools with the same level of authenticity and historical detail, such as SubWar.

novelty
8/10
community
6/10
ease of use
4/10
differentiation
8/10
#4
👀 Worth Watching
Reviewed 2026-05-18
Overall
66/100

GenCAD is a unique tool that offers a web-based CAD system with features for easy design management and sharing, with potential applications in generating pseudo-code for LLMs to produce specific CAD commands, which is a novel approach with 1 test passing out of 2, indicating som…

novelty
8/10
community
7/10
ease of use
5/10
differentiation
8/10
#5
👀 Worth Watching
Reviewed 2026-05-19
Overall
66/100

Nim-Presto is a unique REST API framework for the Nim language, with no direct equivalent, scoring 8 for novelty.

novelty
8/10
community
3/10
ease of use
6/10
differentiation
9/10

How we score

Every submission is tested in an isolated Docker container. We install and run each app, then score across 11 weighted criteria: novelty, functionality, UX/DX, differentiation, performance, documentation, security, monetization potential, community fit, maintenance signals, and technical depth.

Thresholds: ⭐ Strong candidate (≥78, novelty ≥7) · 👀 Worth watching (≥57) · 🔍 Niche (35–56) · ⏭ Skip (<35)

Browse all daily reviews → · More articles → · View source →