hackquest logo

ArbiSense

Autonomous AI agent monitoring Arbitrum DeFi (DeFiLlama, Uniswap v3, Aave v3), producing a 0-100 sentiment score and recording each report immutably on-chain via a Solidity contract.

Pila tecnológica

Solidity
Web3
Python

Descripción

ArbiSense is an autonomous AI agent that continuously monitors Arbitrum DeFi protocols and records market intelligence on-chain — with zero human intervention.

How It Works

  1. Collect: Fetches live data from DeFiLlama (Arbitrum chain TVL), Uniswap v3 (volume & TVL), and Aave v3 (pool utilization rates) using public APIs.

  2. Analyze: Produces a 0–100 sentiment score — TVL momentum 40%, Uniswap volume/TVL ratio 30%, Aave avg utilization 30%.

  3. Record: Calls submitReport() on the deployed SentinelRegistry Solidity contract, storing each report immutably on Arbitrum Sepolia.

Why It Matters

DeFi participants need timely, unbiased, on-chain intelligence. ArbiSense removes the human bottleneck — operating 24/7 and writing structured reports directly to the blockchain without any manual trigger.

Tech Stack

Python · web3.py · Solidity 0.8.20 · Hardhat · DeFiLlama API · Arbitrum Sepolia

Progreso del hackathon

Built ArbiSense from scratch during the hackathon:

  • Designed three data collectors (DeFiLlama, Uniswap v3, Aave v3) using public APIs

  • Built weighted sentiment scoring engine (0–100 scale, configurable weights)

  • Wrote and compiled SentinelRegistry.sol (Solidity 0.8.20) with submitReport(), onlyAgent access control, and full report history

  • Integrated web3.py for on-chain transaction signing and submission

  • Created CLI with run-once, run-loop, reports, onchain-status commands

  • Validated full dry-run: Score 35/100 (Fear), Arbitrum TVL $1.72B, UniV3 TVL $223M

  • Published to GitHub: github.com/Steffdarz/arbisense

Estado de recaudación de fondos

Not fundraising. ArbiSense is an open-source hackathon project. Seeking ecosystem grant from Arbitrum Foundation.

Líder del equipo
SSteffen Darwin
Enlace del proyecto
Desplegar ecosistema
Arbitrum OneArbitrum One