Live data from Hacker News

Ask HN: What Are You Working On? (Nov 2025)

news.ycombinator.com

661–670 of 1001 posts

Re: Ask HN: What Are You Working On? (Nov 2025)

#665
An AI-powered social media management tool that creates, schedules, and publishes content automatically across Twitter/X, LinkedIn, Facebook, Instagram, and Threads.

https://postsam.ai

*The problem:* As a solo founder, I was spending hours each week on social media - writing posts, scheduling them, managing multiple accounts. I wanted something that could handle the entire workflow automatically while still letting me stay in control.

*What PostSam does:* - AI generates content tailored to your brand voice (you provide initial brand info) - Creates full content campaigns with posting schedules - Calendar interface to review, edit, or reschedule posts before they go live - Auto-publishes to all connected accounts - Learns from your edits to improve future content

*Current status:* Live and working. Seeing good engagement rates from users who set it up once and let it run. The AI content quality has been surprisingly good - it adapts well to different brand voices.

Re: Ask HN: What Are You Working On? (Nov 2025)

#669
I’ve built two AI agents that curate personalized news:

- Market Pulse Agent — analyzes the last 24 hours of global and US market news to generate actionable stock-trading signals.

- TechPulse Agent — tracks emerging tech trends and surfaces interesting GitHub projects and engineering updates.

Both are live on my site: https://kryptunes.com

Still iterating, but the goal is to build a fully automated, AI-powered research companion for traders and tech enthusiasts.

Re: Ask HN: What Are You Working On? (Nov 2025)

#670
Working on Strot - an AI agent that reverse-engineers website APIs for scraping.

Instead of DOM scraping, it intercepts AJAX calls and figures out which API endpoint gives you the data you need. Uses visual analysis + fuzzy matching to identify the right call.

The use case: scraping product reviews, paginated listing data (products), etc. Existing AI scrapers either didn't work or were very slow and costly. A product with 1000 reviews takes 10+ minutes with Playwright, costs $10 with LLM scrapers. With Strot? 10 seconds via direct API calls.

Being used in production by a couple of clients. Would love feedback!

Blog: https://blog.vertexcover.io/strot-is-a-api-scraper GitHub: https://github.com/vertexcover-io/strot

Post reply on HN