Skillget

openclaw-trading-agent

agent
Security Audit
Warn
Health Warn
  • No license — Repository has no license file
  • Description — Repository has a description
  • Active repo — Last push 0 days ago
  • Community trust — 442 GitHub stars
Code Pass
  • Code scan — Scanned 12 files during light audit, no dangerous patterns found
Permissions Pass
  • Permissions — No dangerous permissions requested
Purpose
This tool is an AI-powered autonomous trading agent that analyzes real-time cryptocurrency market data and automatically executes buy, sell, and hold trades on the Hyperliquid decentralized exchange.

Security Assessment
Overall Risk: Medium. The code scan did not find hardcoded secrets, dangerous permissions, or malicious code execution patterns. However, because this is a financial agent, it inherently interacts with sensitive data. It requires API keys and cryptocurrency wallet private keys to function, and makes continuous external network requests to market data providers (like TAAPI) and the Hyperliquid blockchain. While the code itself is safe, improperly configuring or running this agent carries a direct financial risk, as it can autonomously spend or lose your funds.

Quality Assessment
The project is active and well-regarded by the community, boasting 442 GitHub stars and receiving updates as recently as today. However, it lacks a formal software license, which means there are no explicit legal terms regarding how you can use, modify, or distribute the code. Furthermore, the developers explicitly state in the README that the code has not been audited and comes with no guarantees of returns.

Verdict
Use with caution. While the code is clean and actively maintained, the absence of a license, lack of a professional financial audit, and the autonomous nature of crypto trading present significant legal and financial risks. Only use funds you are entirely willing to lose.
SUMMARY

trading agent

README.md

Nocturne: AI Trading Agent on Hyperliquid

This project implements an AI-powered trading agent that leverages LLM models to analyze real-time market data from TAAPI, make informed trading decisions, and execute trades on the Hyperliquid decentralized exchange. The agent runs in a continuous loop, monitoring specified cryptocurrency assets at configurable intervals, using technical indicators to decide on buy/sell/hold actions, and manages positions with take-profit and stop-loss orders.

Table of Contents

Disclaimer

There is no guarantee of any returns. This code has not been audited. Please use at your own risk.

Architecture

See the full Architecture Documentation for subsystems, data flow, and design principles.

Architecture Diagram

Nocturne Live Agents

Trading tools & infrastructure

💡 Trading Tools & Infrastructure (Recommended Stack)

This bot is designed to work alongside a high-performance trading stack including Solana trading bots, MEV tools, smart money trackers, and low-latency infrastructure.

Using the right tools can significantly improve execution speed, alpha detection, and profitability.

⚡ Some links include fee discounts or access benefits.

⚡ Execution Layer (Fastest Trading Tools)

Axiom Trade — solana trading bot / fast execution / low fees

  • Optimized for on-chain trading & sniping
  • 10–30% lower trading fees
  • Reliable for high-frequency execution
    → Start using Axiom

Odin Bot — automated trading bot / strategy execution

  • Fully automated trading strategies
  • Low-latency execution engine
    → Access Odin Bot

Bloom (Telegram Bot) — ultra-fast solana trading bot

  • Lightweight + extremely fast execution
  • Ideal for mobile + quick trades
    → Launch Bloom

📊 Alpha & Analytics (Edge Tools)

GMGN — smart money tracker / early token discovery

  • Track whales & insider activity
  • Discover tokens before they trend
    → Explore GMGN

🧠 Advanced Trading Platforms

Padre — advanced trading interface / pro tools

  • Enhanced execution controls
  • Additional trading utilities
    → Open Padre

Polymarket — prediction market / trading signals

  • Trade on real-world outcomes
  • Useful for sentiment-driven strategies
    → Try Polymarket

🖥️ Low-Latency Infrastructure (Critical for MEV)

Recommended VPS Setup — low latency trading server / solana bot hosting

For best performance, run the bot on a New York-based VPS (close to major trading infrastructure):
→ Try Tradingvps.io

  • ⚡ Lower latency = faster execution
  • 🔁 More reliable transaction inclusion
  • 🧩 Better performance for MEV / sniping strategies

📈 Why This Stack Matters

Using this setup improves:

  • Transaction speed (critical for sniping)
  • Fill rates & execution reliability
  • Access to early opportunities (alpha)

⚠️ Disclaimer

  • These tools are optional and not required to run the bot
  • Always test strategies before scaling
  • Trading involves risk

Structure

  • src/main.py: Entry point, handles user input and main trading loop.
  • src/agent/decision_maker.py: LLM logic for trade decisions (OpenRouter with tool calling for TAAPI indicators).
  • src/indicators/taapi_client.py: Fetches indicators from TAAPI.
  • src/trading/hyperliquid_api.py: Executes trades on Hyperliquid.
  • src/config_loader.py: Centralized config loaded from .env.

Env Configuration

Populate .env (use .env.example as reference):

  • TAAPI_API_KEY
  • HYPERLIQUID_PRIVATE_KEY (or LIGHTER_PRIVATE_KEY)
  • OPENROUTER_API_KEY
  • LLM_MODEL
  • Optional: OPENROUTER_BASE_URL (https://openrouter.ai/api/v1), OPENROUTER_REFERER, OPENROUTER_APP_TITLE

Obtaining API Keys

  • TAAPI_API_KEY: Sign up at TAAPI.io and generate an API key from your dashboard.
  • HYPERLIQUID_PRIVATE_KEY: Generate an Ethereum-compatible private key for Hyperliquid. Use tools like MetaMask or eth_account library. For security, never share this key.
  • OPENROUTER_API_KEY: Create an account at OpenRouter.ai, then generate an API key in your account settings.
  • LLM_MODEL: No key needed; specify a model name like "x-ai/grok-4" (see OpenRouter models list).

Usage

Run: poetry run python src/main.py --assets BTC ETH --interval 1h

Local API Endpoints

When the agent runs, it also serves a minimal API:

  • GET /diary?limit=200 — returns recent JSONL diary entries as JSON.
  • GET /logs?path=llm_requests.log&limit=2000 — tails the specified log file.

Configure bind host/port via env:

  • API_HOST (default 0.0.0.0)
  • API_PORT or APP_PORT (default 3000)

Docker:

docker build --platform linux/amd64 -t trading-agent .
docker run --rm -p 3000:3000 --env-file .env trading-agent
# Now: curl http://localhost:3000/diary

Tool Calling

The agent can dynamically fetch any TAAPI indicator (e.g., EMA, RSI) via tool calls. See TAAPI Indicators and EMA Example for details.

Deployment to EigenCloud

EigenCloud (via EigenX CLI) allows deploying this trading agent in a Trusted Execution Environment (TEE) with secure key management.

Prerequisites

  • Allowlisted Ethereum account (Sepolia for testnet). Request onboarding at EigenCloud Onboarding.
  • Docker installed.
  • Sepolia ETH for deployments.

Installation

macOS/Linux

curl -fsSL https://eigenx-scripts.s3.us-east-1.amazonaws.com/install-eigenx.sh | bash

Windows

curl -fsSL https://eigenx-scripts.s3.us-east-1.amazonaws.com/install-eigenx.ps1 | powershell -

Initial Setup

docker login
eigenx auth login  # Or eigenx auth generate --store (if you don't have a eth account, keep this account separate from your trading account)

Deploy the Agent

From the project directory:

cp .env.example .env
# Edit .env: set ASSETS, INTERVAL, API keys
eigenx app deploy

Monitoring

eigenx app info --watch
eigenx app logs --watch

Updates

Edit code or .env, then:

eigenx app upgrade <app-name>

For full CLI reference, see the EigenX Documentation.

Reviews (0)

No results found