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
Hermes releases v0.14: fully native integration with Grok, official rollout of C-end subscription to API proxy
According to Beating Monitoring, NousResearch released a major update to the multi-platform intelligent agent framework Hermes Agent v0.14.0. This iteration incorporated over 800 commits, with the core action of elevating the xAI system to native foundational capabilities and attempting to take over users’ major AI membership subscriptions.
Grok received the highest level of support. The new version introduces SuperGrok subscription support, allowing users to call models without applying for an API Key, with the accompanying grok-4.3 model context window increased to 1 million tokens. Previously relying on external implementations, the x_search tweet search has also been converted into a native built-in tool, integrating X OAuth authorization.
The official built-in local interface proxy. The newly added hermes proxy command can directly convert Claude Pro, ChatGPT Pro, and SuperGrok web authorization into standard OpenAI format local interfaces. This feature theoretically can replace various third-party reverse proxy tools.
The agent execution flow introduces hardcore validation. The new version adds seamless model switching commands with context handoff. In code editing scenarios, the system enforces LSP semantic diagnostics and adds validation layers after writing files, directly addressing hallucination issues where large models claim to modify but do not actually write changes.
Additionally, due to the lazy loading mode for heavy dependencies such as audio/video and some platform interactions, the framework’s cold start time has been reduced by nearly 19 seconds.