OpenClaw is an AI-powered trading agent designed for automated, low-latency execution on the Hyperliquid decentralized exchange. It leverages Large Language Models (LLMs) to analyze real-time market data, generate trading decisions, and manage positions with integrated risk controls, targeting users seeking automated strategy experimentation and execution.

How It Works

The agent operates on a continuous trading loop, integrating LLMs for decision-making, TAAPI for real-time technical analysis (supporting custom indicators via tool-calling), and Hyperliquid's API for automated trade execution. This approach aims to enhance execution speed, alpha discovery, and trade accuracy by combining AI insights with a high-performance trading stack.

Quick Start & Requirements

• Primary Command: poetry run python src/main.py --assets BTC ETH --interval 1h
• Prerequisites: Requires environment variables for API keys (TAAPI_API_KEY, HYPERLIQUID_PRIVATE_KEY, OPENROUTER_API_KEY). Optional OPENROUTER_BASE_URL and API_PORT.
• Recommended Stack: High-performance infrastructure including low-latency VPS, and tools like Axiom Trade, Odin Bot, Bloom, GMGN, and Padre are recommended for optimal performance.
• Links:
  • Architecture Docs: docs/ARCHITECTURE.md
  • Architecture Diagram: https://github.com/user-attachments/assets/d8f5110a-6401-42bd-b5f5-b154c7b0a418
  • EigenCloud Deployment Script: https://eigenx-scripts.s3.us-east-1.amazonaws.com/install-eigenx.sh
  • Local API endpoints for logs and trade history are available.

Highlighted Details

• LLM-driven trading decisions with multi-model support.
• Real-time technical analysis via TAAPI, enabling dynamic indicator queries.
• Automated trade execution on Hyperliquid with built-in Take Profit (TP) / Stop Loss (SL) logic.
• Optional deployment within a Trusted Execution Environment (TEE) using EigenCloud for enhanced key security.

Maintenance & Community

No specific details regarding maintainers, community channels (e.g., Discord, Slack), or roadmap were found in the provided README.

Licensing & Compatibility

The license type is not specified in the README. This omission requires further investigation for commercial use or integration into closed-source projects.

Limitations & Caveats

This project is explicitly labeled as experimental and unaudited, with no guarantee of profitability. Users are advised to proceed at their own risk. Performance is contingent on network latency and the quality of trading strategies employed.