I vibe coded a complex trading app
Hey HN, I just released Tradofire, a crypto trading app I built using a lot of cursor chatgpt and claude for over a year. The main idea of the app is very simple - to swipe on pre-prepared trading setups (like tinder) and if you right swipe it opens a position. The execution of this simple idea was much more complex and tbh I could not have done it without AI. Here's a quick rundown of the main features: Swipe-to-Trade UI: Quickly initiate long or short positions with intuitive swipe gestures. Real-Time Trade Signals: Get curated crypto signals from the market delivered proactively, helping…
What it does
In the maker’s words, at launch
Hey HN, I just released Tradofire, a crypto trading app I built using a lot of cursor chatgpt and claude for over a year. The main idea of the app is very simple - to swipe on pre-prepared trading setups (like tinder) and if you right swipe it opens a position. The execution of this simple idea was much more complex and tbh I could not have done it without AI. Here's a quick rundown of the main features: Swipe-to-Trade UI: Quickly initiate long or short positions with intuitive swipe gestures. Real-Time Trade Signals: Get curated crypto signals from the market delivered proactively, helping you spot opportunities early. Built-in Risk Controls: Automated stop-loss and take-profit orders embedded directly into each trade to simplify risk management. Paper Trading Mode: Simulate trades without risk to refine strategies before deploying real capital. Easy Exchange Integration: Seamlessly connect your live trading account when you're ready to go live. The goal was to create a focused tool for traders who want quick access to high-quality trade ideas and minimal friction in execution. I’d love your feedback on the product and the idea itself. You can check it out here: https://tradofire.com Feedback appreciated thanks a lot!
Does the same job
all alternatives →
- IMI'm building a crypto trading bot that you can follow live on Telegram2021 · ▲6
Hi HN! For the last few weeks I've been building an algotrading bot based on the Supertrend indicator. It's a trend-following bot that uses the Supertrend lines as support/resistances to enter long/short trades and it's currently running in simulated mode (not real money) on all Binance futures pairs. I've written a somewhat detailed write-up about the strategy here: https://ailef.tech/2021/05/20/im-building-a-cryptocurrency-trading-bot-that-you-can-follow-live-on-telegram/ The cool thing about the bot is that he reports everything on his Telegram…
- TATrade – A mobile web app for trading stocks with virtual currency2014 · trade.kevinbedi.com · ▲9
- MFMy first game – CryptoEmpire.io :)2018 · ▲13
I know everyone is a bit burned out on blockchain and cryptocurrency related stuff around these parts, but I've been working on as a side project for the last few months and thought you guys might be interested: https://cryptoempire.io/ It's still a bit buggy and incomplete (the mobile ux needs a lot of work, the leaderboard isn't functional yet, etc.), but I've reached a point where I'm not totally ashamed of sharing it :) Any feedback would be most welcome!
- BABenjamin, a bitcoin trading bot & analytics platform2013 · ▲8
https://github.com/mathisonian/benjamin
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 · 17d 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 · 27d ago · cactuscompute.com
Launched alongside, May 2025
the whole month →
- C9
Life & fun · 2025 · felixrieseberg.github.io
