Requirements
- Target platform
- OpenClaw
- Install method
- Manual import
- Extraction
- Extract archive
- Prerequisites
- OpenClaw
- Primary doc
- SKILL.md
Autonomous yield farming agent for BNB Chain with deterministic execution, smart contract integration, and automated decision-making.
Autonomous yield farming agent for BNB Chain with deterministic execution, smart contract integration, and automated decision-making.
Hand the extracted package to your coding agent with a concrete install brief instead of figuring it out manually.
I downloaded a skill package from Yavira. Read SKILL.md from the extracted folder and install it by following the included instructions. Tell me what you changed and call out any manual steps you could not complete.
I downloaded an updated skill package from Yavira. Read SKILL.md from the extracted folder, compare it with my current installation, and upgrade it while preserving any custom configuration unless the package docs explicitly say otherwise. Summarize what changed and any follow-up checks I should run.
Autonomous yield farming agent for BNB Chain with deterministic execution, smart contract integration, and automated decision-making.
Deterministic Decision Engine - Same input always produces same output (auditable) Smart Contract Integration - Interact with YieldVault contracts on BNB testnet/mainnet Autonomous Scheduler - Run farming decisions hourly without manual intervention Transaction Executor - Automatic DEPOSIT, WITHDRAW, HARVEST, COMPOUND, REBALANCE actions Telegram Alerts - Real-time notifications for executions, APR changes, and errors Risk Management - Conservative risk filtering (only vaults with risk_score β€ 0.5) Yield Optimization - Net APR calculation (apr - fees - risk_penalty)
clawhub install yieldvault-agent
cp config.deployed.json .env.local # Edit with your contract addresses and RPC endpoint
cd contracts npm install npm run deploy:testnet
npm test # Unit tests node test.live.mock.js # Integration tests (offline) node test.live.js # Live testnet tests
node scheduler.js # Runs decision cycle every hour against testnet
Telegram notifications sent automatically for: Execution started (vault_id, action, amount) APR changes (>1% delta) Errors (with severity level) Cycle completion (stats summary)
Smart Contracts (BNB Testnet/Mainnet) β BlockchainReader (live vault data) β YieldFarmingAgent (deterministic decisions) β TransactionExecutor (sign & broadcast) β Scheduler (hourly automation) β Notifications (Telegram alerts)
Edit config.scheduler.json: { "chainId": 97, "interval_minutes": 60, "harvest_threshold_usd": 25, "rebalance_apr_delta": 0.02, "max_allocation_percent": 0.35, "risk_score_threshold": 0.5 }
Read current vault state (APR, TVL, user balance) Calculate Net APR = apr - fees - (risk_score Γ 0.10) Filter vaults with risk_score β€ 0.5 Select vault with highest Net APR Decide action: HARVEST if pending_rewards β₯ $25 USD COMPOUND if net_apr β₯ 2% delta REBALANCE if another vault beats current by β₯ 2% NOOP if already optimized Execute transaction (with retry logic) Log execution record (SHA256 auditable)
Testnet: BNB Chain Testnet (chainId: 97) Mainnet: BNB Chain Mainnet (chainId: 56)
β Deterministic execution (reproducible, auditable) β SHA256 audit trail for every decision β Risk filtering (conservative) β Constraint enforcement (max 35% per vault) β Retry logic with exponential backoff β No hardcoded private keys (use environment variables)
For mainnet deployment, add: Chainlink Oracle - Live APR feeds Hardware Wallet Support - Ledger/Trezor signing Smart Contract Audit - Professional security review Emergency Pause - Multi-sig pause mechanism See FINAL_CHECKLIST.md for complete production requirements.
README.md - Full user guide SKILL.md - This file FINAL_CHECKLIST.md - Production requirements INTEGRATION_GUIDE.md - Smart contract integration EXAMPLES.md - Usage examples RESPUESTAS_PREGUNTAS.md - FAQ & architecture
Issues & PRs welcome: https://github.com/open-web-academy/yieldvault-agent-bnb
MIT
Agent frameworks, memory systems, reasoning layers, and model-native orchestration.
Largest current source with strong distribution and engagement signals.