I am building a command line package manager for AI models. It’ll make installing and running models locally incredibly easy.
Checkout: https://llmpm.co
Ask HN: What Are You Working On? (March 2026)
611–620 of 1001 posts
Re: Ask HN: What Are You Working On? (March 2026)
#612I'm building a distributed key-value store as part of my university project.
Re: Ask HN: What Are You Working On? (March 2026)
#613I'm building a very casual daily price-guessing game for my mum. Every day she gives me feedback, and I'm using it as a chance to de-rust my CSS/React + see how daily games tick.
Re: Ask HN: What Are You Working On? (March 2026)
#614Data extraction: https://simplescraper.io A project that I launched on HN that became a business. Simplescraper rode the no-code wave of a few years back ( 'instant structured data without parsing html' ). Now working on increasing the surface area for AI agents: MCP support, screenshots API, and (experimentally) x402[1] [1] https://simplescraper.io/blog/x402-payment-protocol/
Do you handle captcha and bot detection well? I need a solution for Walmart and Mercado Libre that doesn’t require residential proxies
Re: Ask HN: What Are You Working On? (March 2026)
#615I am building a better console.log, for humans and agents
Re: Ask HN: What Are You Working On? (March 2026)
#616An agent that records Loom-style videos for support, sales, etc
Re: Ask HN: What Are You Working On? (March 2026)
#617AST-based code modifications from LLMs: https://codeplusequalsai.com/
I'm interested in the idea that LLMs writing raw code and doing line-or-diff replacements will not be the future, but that having the LLMs modify the structure of the code may end up being the best.
Also, I think that building LLM-powered webapps should earn the dev per token call; so I've built a margin into token costs where the end user is charged 2x the provider's token costs, and then I get 20% of the remaining and the dev gets 80%.
Re: Ask HN: What Are You Working On? (March 2026)
#618Have been tinkering with a few different projects:
- Tilth: Smart(er) code reading for humans and AI agents. Reduces LLM token use and cost by ~40% (benchmarked) https://github.com/jahala/tilth
- mrkd: Native macOS .md viewer (+preview in Finder) that imports iTerm2 and VSCode themes https://github.com/jahala/mrkd
- O-O: Self-updating articles concept with polyglot (bash/html) files. No server, no database. https://github.com/jahala/o-o
Re: Ask HN: What Are You Working On? (March 2026)
#619https://sauna-assistant.com - sauna master in your pocket
Re: Ask HN: What Are You Working On? (March 2026)
#620PostalAgent - https://PostalAgent.com – direct mail automation for people who've given up on email open rates.
Email averages ~20% open rates on a good day. A postcard sitting on someone's kitchen counter for two weeks is hard to compete with. I've been building out the programmatic side. API, Zapier, and native integrations with Jobber and Zoho so you can trigger physical mail from the same workflows you already use for email.
Shopify integration is almost out the door too, which opens up a lot of interesting abandoned cart and win-back use cases for stores whose customers have opted out of email.
No bulk minimums, no design software needed. If anyone here wants to give it a try, reply or email me and I'll set you up with some free credits to get started.