All projects

Orbital-Sentinel

Autonomous AI arbitrage agent built on Chainlink CRE - 8 cross-workflow monitors for LINK DeFi ecosystem, with LAA (LINK AI Arbitrage) - a workflow that detects LINK arb opportunities on Curve using AI analysis and executes on them.

CRE & AI DeFi & Tokenization

What it is

Orbital Sentinel is an autonomous AI agent platform that monitors the entire stake.link DeFi ecosystem using 8 Chainlink CRE workflows. The flagship LINK AI Arbitrage (LAA) workflow is live on the CRE mainnet DON, running 7x/day autonomously.

The problem: DeFi arbitrage bots make isolated decisions. They see one pool and one price. But stLINK/LINK arbitrage on Curve depends on Priority Pool queue depth, Morpho lending utilization, CCIP bridge status, oracle prices, and governance activity — data spread across 15+ contracts and external systems. Missing any signal  means leaving money on the table or executing into a trap.

How it works: 8 CRE workflows read live Ethereum mainnet contracts via EVMClient — Curve StableSwap, Chainlink Data Feeds (LINK/USD, ETH/USD), staking pools, Morpho Blue markets, CCIP Router/OnRamp/TokenPool, and 50+ ERC20 balances. After all workflows complete, a composite intelligence layer feeds the full ecosystem context to GPT-5.3-Codex, which produces an ecosystem-aware recommendation that can override  the isolated arbitrage signal. Every decision is backed by a keccak256 proof hash written to SentinelRegistry on Sepolia.

 Real example: The isolated LAA signal says "EXECUTE" (17 bps premium, pool open). But the composite layer reads that Priority Pool queue is 365K LINK deep, stLINK/LINK depeg is at 95 bps, and Morpho utilization is at 89.65% — and overrides to "WAIT" with 0.94 confidence. That decision, with all cross-workflow metrics  encoded, is verifiable on-chain.

 Architecture: Phase 1 runs 8 CRE workflows (LAA on mainnet DON, 7 via local simulate.
Phase 1.5 runs composite AI analysis across all workflow outputs.
Phase 2writes keccak256 proof hashes to SentinelRegistry on Sepolia.
A Next.js dashboard surfaces workflow status, CRE signals, and on-chain proof history with Etherscan links.

How it Works

  • CRE TypeScript SDK (@chainlink/cre-sdk ^1.0.9): all 8 workflows use Runner,  handler, CronCapability, EVMClient, HTTPClient, getNetwork, encodeCallMsg, consensusIdenticalAggregation
     - EVMClient.callContract(): reads 15+ Ethereum mainnet contracts — Curve StableSwap, Priority Pool, Arb Vault, Chainlink staking pools, reward vaults, Morpho Blue markets, ERC4626 vaults, CCIP Router/OnRamp/TokenPool, Chainlink Data Feeds, and 50+ERC20 balances
     - Chainlink Data Feeds: LINK/USD, ETH/USD, POL/USD via AggregatorV3 latestAnswer() on mainnet
     - CCIP monitoring: reads CCIP Router getOnRamp(), OnRamp paused() state, and
     LockReleaseTokenPool rate limiters across 3 destination chains (Arbitrum, Base, Polygon)
     - HTTPClient + consensusIdenticalAggregation: deterministic off-chain fetches for AI analysis (Claude Haiku for treasury risk, GPT-5.3-Codex for arbitrage + composite
     intelligence) and governance data (Snapshot GraphQL)
      SentinelRegistry.sol (Solidity 0.8.19, Foundry): minimal on-chain proof registry  with Ownable2Step, duplicate prevention, input validation. Audited with 31 tests (17 unit + 7 fuzz + 7 deep audit), 80K fuzz iterations
     - Composite Intelligence: cross-workflow AI synthesis reads all workflow snapshots, builds ecosystem context, and calls GPT-5.3-Codex for a recommendation that can override isolated signals
  • viem: on-chain interaction for recordHealth calls and HealthRecorded event log collection
     - Next.js 15 + Drizzle ORM: analytics dashboard surfacing sentinel records from PostgreSQL
     - Bun runtime: all workflow projects use Bun for fast dependency resolution and execution

Links

Created by

  • Avi