We turned accounting into a CLI command
Hi HN, We replaced accounting workflows with a CLI. Scan a receipt → it’s parsed, categorized (VAT, etc.), and ready to book: scan → parse → confirm → BOOKED What used to be: PDFs + emails + manual entry + dashboards is now: one command. No UI. No forms. No backoffice. Try it: npx norman-ai-cli@latest If you’ve ever tried to automate accounting or taxes, curious if this feels like a better abstraction.
Does the same job
all alternatives →
- ANA ncurses CRM system (and accounting)2017 · ▲95
I've been building a CRM/accounting system for my personal small company. It's still in an early stage and is lacking a few features. But it is finally usable. https://asciinema.org/a/0g9f8c00mrkm018p10r8p8km3 Please share your thoughts
- IBI built a simple app to create PDF invoice2024 · invoicepdf.dev · ▲8
Hey HN, I had to create many invoices recently, it was pretty annoying doing the same things over and over. So i created this small tool that work well to create invoice and save them as template for re-usage. the ui is very easy and simple. I hope this tool will be helpful to you as it it to me. ps: you can move around without account Dorian
More ai this month
the category →
I trained a 125M-parameter transformer to autocomplete piano performances in real time (~108 notes/sec on an iPhone 15). The idea is basically GitHub Copilot or Tabnine, except instead of prompting it with code, you prompt it by playing a few notes on a MIDI piano. The model then continues what you played, entirely on-device. The app is free if anyone wants to try it. Happy to answer questions about the model, training, Core ML, or the many things that didn't work.
AI · 16d ago · simedw.com
Astute▲585Automate your B2B brand going viral, with new media creators
AI · 18d ago · company-app.joinastute.com
Hey HN, Henry from Cactus here! We previously released Cactus Needle, a 14MB agentic LLM for tool call, device use, and structured extraction for phones, wearables, smart homes, small robots and microcontrollers. We got really great feedback here, and have now incorporated the suggestions to release Needle 2. The whole model is a single 14MB binary that runs a full session in 28MB of RAM; 45m parameters at 2bit compression. Needle hits 500 tokens/sec decode speed on a Raspberry Pi 5, sits between 400-1,500 tokens/sec on VR devices like Meta Quest 3S and Apple Vision Pro, and ranges…
AI · 26d ago · cactuscompute.com
Launched alongside, March 2026
the whole month →
Switch from ChatGPT to Claude with import memory feature
AI · Mar 2026 · claude.com
