Futures
Access hundreds of perpetual contracts
TradFi
Gold
One platform for global traditional assets
Options
Hot
Trade European-style vanilla options
Unified Account
Maximize your capital efficiency
Demo Trading
Futures Kickoff
Get prepared for your futures trading
Futures Events
Join events to earn rewards
Demo Trading
Use virtual funds to experience 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
Launchpad
Be early to the next big token project
Alpha Points
Trade on-chain assets and earn airdrops
Futures Points
Earn futures points and claim airdrop rewards
Xiaomi Mobile AI Agent "Xiaomi miclaw" begins limited closed beta testing
Odaily Planet Daily reports that the AI interaction testing product Xiaomi miclaw, built on the Xiaomi MiMo large model, has begun a limited closed beta test today. The testing is invitation-only and not open for public recruitment.
Xiaomi miclaw operates as a system application, encapsulating over 50 system-level tools and ecosystem services. It uses a reasoning-execution cycle engine, where the model autonomously determines the order of tool calls and parameters. The product focuses on verifying the execution capabilities of large models within Xiaomi’s “Smart Ecosystem” covering vehicles, homes, and people. It features a four-layer capability architecture: system-level core abilities, personal context understanding, ecosystem connectivity, and self-evolution.
In terms of ecosystem connectivity, Xiaomi miclaw has implemented a complete MiJia protocol client, allowing control of connected IoT devices within MiJia with user authorization. It also supports MCP protocol and third-party application SDK integration. For self-evolution, the product has four meta-capabilities: file-level memory, sub-agent creation, MCP service configuration, and sandbox script execution. It can autonomously build memory systems and expand its toolset.
Xiaomi notes that the product is still being optimized for stability, power consumption, and success rate in complex scenarios. Users are advised to back up data beforehand and conduct tests in controlled environments.