Futures
Access hundreds of perpetual contracts
CFD
Gold
One platform for global traditional assets
Options
Hot
Trade European-style vanilla options
Unified Account
Maximize your capital efficiency
Demo Trading
Introduction to Futures Trading
Learn the basics of futures trading
Futures Events
Join events to earn rewards
Demo Trading
Use virtual funds to practice risk-free trading
Launch
CandyDrop
Collect candies to earn airdrops
Launchpool
Quick staking, earn potential new tokens
HODLer Airdrop
Hold GT and get massive airdrops for free
Pre-IPOs
Unlock full access to global stock IPOs
Alpha Points
Trade on-chain assets and earn airdrops
Futures Points
Earn futures points and claim airdrop rewards
Promotions
AI
Gate AI
Your all-in-one conversational AI partner
Gate AI Bot
Use Gate AI directly in your social App
GateClaw
Gate Blue Lobster, ready to go
Gate for AI Agent
AI infrastructure, Gate MCP, Skills, and CLI
Gate Skills Hub
10K+ Skills
From office tasks to trading, the all-in-one skill hub makes AI even more useful.
GateRouter
Smartly choose from 40+ AI models, with 0% extra fees
I found an open-source project that truly allows AI to "use its hands" to work
cua, 16.7k stars, not a chat robot, but the infrastructure that enables AI to directly control a computer
The core idea is simple: provide AI with a sandbox environment where it can click the mouse, type on the keyboard, and see the screen, allowing it to operate software like a human
Several subprojects have clear divisions of labor:
✅ Cua Driver: macOS background operation driver, AI clicks buttons and types without stealing your cursor, doesn't switch your window, silently works in the background
✅ Cua Sandbox: unified API control for Linux/macOS/Windows/Android, runs in the cloud or locally
✅ CuaBot: provides sandbox environments for coding agents like Claude Code and Cursor, ready to use out of the box
✅ Cua-Bench: benchmark tests to evaluate agent operation capabilities, runs datasets like OSWorld and ScreenSpot
✅ Lume: runs macOS virtual machines on Apple Silicon, performance close to native
Looking at the code, it's a mix of Rust, Swift, and Python, with a pretty hardcore architecture. If you're interested in agent automation, desktop task orchestration, or just curious about "how AI uses computers," this is worth checking out the source code
The project link is in the comment section 👇