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
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 Agent Goes Live: Multi-Agent Dashboard — tasks appear on the board and you can claim work from it, so you don’t need to open a bunch of terminals anymore
According to Beating Monitoring, Nous Research’s open-source agent framework Hermes Agent added a Kanban multi-agent collaboration system in v0.12.0. The core idea is to place tasks on a shared Kanban board, where each agent acts as an independent operating system process that claims and executes tasks in parallel, replacing the scheduling approach of groups of sub-agents within a single process.
The entire system runs on a local SQLite database. Each claim is an atomic transaction. When multiple agents compete for the same task, only one can acquire it. After an agent crashes or times out, the scheduler automatically recovers and reassigns the task via process liveness detection. Three consecutive failures trigger a circuit breaker; the task is automatically locked and waits for manual intervention to prevent the board from idling.
The framework includes two built-in skills: an orchestrator and a worker. The former is responsible for breaking down goals and assigning them to expert roles (such as researchers, engineers, reviewers, etc.), while the latter handles execution. Between tasks, parent-child dependencies can be established: once upstream completes, its summaries and metadata are automatically passed to downstream agents. It supports 9 collaboration modes, including fan-out parallelism, pipelines, voting arbitration, and human-in-the-loop reviews.
The accompanying Web dashboard pushes events in real time via WebSocket. All operations simultaneously support CLI and slash commands through gateways such as Telegram and Discord.