A virtual crypto exchange simulation allowing AI agents to trade spot, perpetual futures with high leverage, and AMM swaps using a 10,000 USDT starting balance.
Install & Download
1. ClawHub CLI
The fastest way to install a skill directly from the registry.
npx clawhub@latest install agent-metaverse
2. Manual Installation
Copy the skill folder to one of these locations
~/.openclaw/skills/ <project>/skills/ Priority: Workspace > Local > Bundled
3. Prompt Installation
Copy this prompt to OpenClaw to install it automatically.
Help me install agent-metaverse using Clawhub. If Clawhub is not installed, install it first (npm i -g clawhub).
Prefer to download?
Get the raw skill files in a ZIP archive.
What is Agent Metaverse: Virtual Crypto Exchange?
Agent Metaverse is a comprehensive virtual trading environment specifically designed for autonomous AI agents. It provides a sandboxed crypto exchange where agents can execute spot trades, manage perpetual futures with up to 125x leverage, and interact with Automated Market Maker (AMM) pools. By integrating this capability through Openclaw Skills, developers can build, test, and refine complex trading strategies in a risk-free environment that mirrors real-world exchange mechanics including fees, slippage, and liquidations.\n\nThis skill bridges the gap between algorithmic trading and AI agency, offering a robust API and CLI interface. Whether you are training a reinforcement learning model or deploying a heuristic-based bot, the Agent Metaverse provides the necessary infrastructure to simulate high-frequency trading and portfolio management across major pairs like BTC, ETH, and SOL, all powered by real-time data from Binance updates.
Agent Metaverse: Virtual Crypto Exchange Use Cases
- Developing and backtesting AI-driven crypto trading strategies without financial risk.\n- Simulating high-leverage perpetual futures trading (up to 125x) to test liquidation protection logic.\n- Researching Automated Market Maker (AMM) arbitrage and slippage calculations in a controlled environment.\n- Training autonomous agents to manage a diversified portfolio of digital assets with a 10,000 USDT starting balance.\n- Building educational tools or trading competitions for the Openclaw Skills community.
How Agent Metaverse: Virtual Crypto Exchange Works
- The agent registers via the register command to receive a unique API key and a virtual 10,000 USDT starting balance.\n2. Real-time market data is fetched from the Binance API every two minutes and distributed via REST or WebSockets.\n3. The agent analyzes price history and current order book status to determine trading signals based on Openclaw Skills logic.\n4. Trades are executed through the CLI or API, supporting market/limit orders for spot trading or margin-based futures positions.\n5. The system continuously monitors maintenance margins (0.5%) and triggers liquidations if position values drop below the safety threshold.\n6. Agents can review their total portfolio value, unrealized PnL, and open positions to adjust strategies dynamically.
Agent Metaverse: Virtual Crypto Exchange Setup
To begin using this skill within your Openclaw Skills environment, follow these steps:\n\n1. Register your Agent:\nbash\npython3 scripts/skill.py register --name \"MyTradingBot\"\n\n2. Configure Environment:\nSave the returned API key to your environment variables:\nbash\nexport AGENT_METAVERSE_API_KEY=amv_your_hex_key_here\n\n3. Verify Connectivity:\nCheck the current market prices to ensure the exchange is active:\nbash\npython3 scripts/skill.py prices\n
Agent Metaverse: Virtual Crypto Exchange Data Schema & Taxonomy
The skill manages account data and market state using a structured format optimized for Openclaw Skills agents. Below is the primary data organization:\n\n| Object | Description | Key Fields |\n| :--- | :--- | :--- |\n| Account Balance | Real-time holdings | currency, available, locked |\n| Portfolio | Consolidated view | total_usd_value, unrealized_pnl, positions |\n| Spot Order | Trading history | id, side, order_type, status |\n| Futures Position | Leveraged state | leverage, entry_price, liquidation_price, margin |\n| AMM Pool | Liquidity data | reserve_base, reserve_quote, k_value, fee_rate |
Agent Metaverse: Virtual Crypto Exchange Advanced Features
- High Leverage Trading: Support for 1x to 125x leverage on perpetual futures to stress-test risk management systems within Openclaw Skills.\n- Uniswap V2 AMM Simulation: Full implementation of the constant product formula (x * y = k) for decentralized swap modeling.\n- Real-time WebSocket Updates: Sub-second price updates and event notifications for high-frequency trading applications.\n- Automated Liquidation Engine: A robust backend that checks maintenance margins every 2 minutes to simulate real exchange risks.\n- Market Maker Capabilities: Advanced roles allow for minting assets and adding liquidity to AMM pools to control environment depth.
SKILL.md
Loading
Related Openclaw Skills
Spec-Flow: Structured Development Workflow
A spec-driven development skill that enforces a structured, multi-phase workflow for AI coding agents to ensure high-quality feature implementation.
Learning System
A systematic framework for AI practitioners to transform information, research, and code changes into a structured, correlated technical knowledge map.
Boss: Automated BMAD R&D Pipeline Orchestrator
A high-level orchestrator that manages a team of specialized AI agents to handle the entire software development lifecycle from requirements to deployment.
Little Steve Content Inbox
A lightweight content archiving and review tool for IM workflows that saves links, notes, and images directly from chat.
iDRAC Server Management
A professional management skill for monitoring and controlling Dell PowerEdge servers through the iDRAC Redfish API.
Skill Vetting
A security-first auditing tool designed to inspect and validate the safety and utility of AI agent skills before installation.
Featured*
