Protocol Bank
Your AI trades. You keep control.
What it does
An AI agent trades Hyperliquid perpetuals for you 24/7 — fully non-custodial. The agent has trading-only permissions and physically cannot withdraw: funds stay in your own wallet, and your maximum loss is the budget you approve, shown on screen. Every trade is explained in plain language ("Opened BTC long, momentum z=1.6"), with per-trade stop-loss, max position caps, and daily circuit breakers enforced before each order. Try it free on real market data in paper mode — zero risk.
Connect your wallet and let an AI agent trade for you on Hyperliquid. Non-custodial, transparent, with one-click control and profit sweep.
Connect your wallet, fund a trading wallet, and let the agent work real markets around the clock. Watch every trade in plain language, sweep profits anytime, and stop it with one click. Paper mode uses real market data with simulated money. Zero risk, full experience. No strategy configuration, no trading knowledge required. Set a budget, and the agent handles the rest. Sign in with MetaMask or any EVM wallet. Your keys never leave your device. Move the amount you're comfortable risking into the AI trading wallet. That's your maximum loss — never more. The agent scans markets 24/7, opens and closes positions, and reports every move in plain language. Every dollar the AI can trade is a…from protocolbanks.com
Does the same job
all alternatives →
- ATAlgorithmic trading for everyone2022 · justfor.fund · ▲122
Hi there. I built a company that makes algorithmic trading strategies for its users to invest with. --> https://justfor.fund Advice and feedback are very much welcomed! Disclaimer: New born business with its first beta version (12 users) currently live. Details: - I'm the sole developer and founder - I applied to YC S22 batch on the last day - Currently facing a big KYC compliance wall (code and protocols) - My priority right now is obtaining funds to cover minimal operational cost's. Need to pay for broker partnership costs too. - I have essentially no funds to cover cost's right…
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, August 2026
the whole month →- TL
Life & fun · 10d ago · louisabraham.github.io
- SA
Hello HN! I found that picking out plausible but diverse skin tones for my digital art and game development projects was kind of difficult, and I got curious about if there was a way to define a color space that made it easy. I've built a color picker and procedural generation algorithm based on the space as well as a bunch of other fun js features and demos throughout the page that use the equations. If you find it interesting, I have lots of explanations of how I built it and what properties the space has. The methodology might be a bit shaky, but hopefully the result is as helpful for…
Life & fun · Aug 2026 · toneyalexander.github.io
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