yieldvault-agent

Autonomous yield farming agent for BNB Chain with deterministic execution, smart contract integration, and automated decision-making.

3,891 stars

Best use case

yieldvault-agent is best used when you need a repeatable AI agent workflow instead of a one-off prompt.

Autonomous yield farming agent for BNB Chain with deterministic execution, smart contract integration, and automated decision-making.

Teams using yieldvault-agent should expect a more consistent output, faster repeated execution, less prompt rewriting.

When to use this skill

  • You want a reusable workflow that can be run more than once with consistent structure.

When not to use this skill

  • You only need a quick one-off answer and do not need a reusable workflow.
  • You cannot install or maintain the underlying files, dependencies, or repository context.

Installation

Claude Code / Cursor / Codex

$curl -o ~/.claude/skills/yieldvault-agent/SKILL.md --create-dirs "https://raw.githubusercontent.com/openclaw/skills/main/skills/alannetwork/yieldvault-agent/SKILL.md"

Manual Installation

  1. Download SKILL.md from GitHub
  2. Place it in .claude/skills/yieldvault-agent/SKILL.md inside your project
  3. Restart your AI agent — it will auto-discover the skill

How yieldvault-agent Compares

Feature / Agentyieldvault-agentStandard Approach
Platform SupportNot specifiedLimited / Varies
Context Awareness High Baseline
Installation ComplexityUnknownN/A

Frequently Asked Questions

What does this skill do?

Autonomous yield farming agent for BNB Chain with deterministic execution, smart contract integration, and automated decision-making.

Where can I find the source code?

You can find the source code on GitHub using the link provided at the top of the page.

Related Guides

SKILL.md Source

# YieldVault Agent

Autonomous yield farming agent for BNB Chain with deterministic execution, smart contract integration, and automated decision-making.

## Features

- **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 ≤ 0.5)
- **Yield Optimization** - Net APR calculation (apr - fees - risk_penalty)

## Installation

```bash
clawhub install yieldvault-agent
```

## Quick Start

### 1. Configure

```bash
cp config.deployed.json .env.local
# Edit with your contract addresses and RPC endpoint
```

### 2. Deploy Contracts (if needed)

```bash
cd contracts
npm install
npm run deploy:testnet
```

### 3. Run Tests

```bash
npm test                    # Unit tests
node test.live.mock.js      # Integration tests (offline)
node test.live.js           # Live testnet tests
```

### 4. Start Scheduler

```bash
node scheduler.js
# Runs decision cycle every hour against testnet
```

### 5. Monitor Alerts

Telegram notifications sent automatically for:
- Execution started (vault_id, action, amount)
- APR changes (>1% delta)
- Errors (with severity level)
- Cycle completion (stats summary)

## Architecture

```
Smart Contracts (BNB Testnet/Mainnet)
    ↓
BlockchainReader (live vault data)
    ↓
YieldFarmingAgent (deterministic decisions)
    ↓
TransactionExecutor (sign & broadcast)
    ↓
Scheduler (hourly automation)
    ↓
Notifications (Telegram alerts)
```

## Configuration

Edit `config.scheduler.json`:

```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
}
```

## Decision Logic

1. **Read** current vault state (APR, TVL, user balance)
2. **Calculate** Net APR = apr - fees - (risk_score × 0.10)
3. **Filter** vaults with risk_score ≤ 0.5
4. **Select** vault with highest Net APR
5. **Decide** action:
   - HARVEST if pending_rewards ≥ $25 USD
   - COMPOUND if net_apr ≥ 2% delta
   - REBALANCE if another vault beats current by ≥ 2%
   - NOOP if already optimized

6. **Execute** transaction (with retry logic)
7. **Log** execution record (SHA256 auditable)

## Supported Networks

- **Testnet:** BNB Chain Testnet (chainId: 97)
- **Mainnet:** BNB Chain Mainnet (chainId: 56)

## Security

- ✅ Deterministic execution (reproducible, auditable)
- ✅ SHA256 audit trail for every decision
- ✅ Risk filtering (conservative)
- ✅ Constraint enforcement (max 35% per vault)
- ✅ Retry logic with exponential backoff
- ✅ No hardcoded private keys (use environment variables)

## Production Readiness

For mainnet deployment, add:

1. **Chainlink Oracle** - Live APR feeds
2. **Hardware Wallet Support** - Ledger/Trezor signing
3. **Smart Contract Audit** - Professional security review
4. **Emergency Pause** - Multi-sig pause mechanism

See `FINAL_CHECKLIST.md` for complete production requirements.

## Documentation

- `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

## Support

Issues & PRs welcome: https://github.com/open-web-academy/yieldvault-agent-bnb

## License

MIT

Related Skills

---

3891
from openclaw/skills

name: article-factory-wechat

Content & Documentation

humanizer

3891
from openclaw/skills

Remove signs of AI-generated writing from text. Use when editing or reviewing text to make it sound more natural and human-written. Based on Wikipedia's comprehensive "Signs of AI writing" guide. Detects and fixes patterns including: inflated symbolism, promotional language, superficial -ing analyses, vague attributions, em dash overuse, rule of three, AI vocabulary words, negative parallelisms, and excessive conjunctive phrases.

Content & Documentation

find-skills

3891
from openclaw/skills

Helps users discover and install agent skills when they ask questions like "how do I do X", "find a skill for X", "is there a skill that can...", or express interest in extending capabilities. This skill should be used when the user is looking for functionality that might exist as an installable skill.

General Utilities

tavily-search

3891
from openclaw/skills

Use Tavily API for real-time web search and content extraction. Use when: user needs real-time web search results, research, or current information from the web. Requires Tavily API key.

Data & Research

baidu-search

3891
from openclaw/skills

Search the web using Baidu AI Search Engine (BDSE). Use for live information, documentation, or research topics.

Data & Research

agent-autonomy-kit

3891
from openclaw/skills

Stop waiting for prompts. Keep working.

Workflow & Productivity

Meeting Prep

3891
from openclaw/skills

Never walk into a meeting unprepared again. Your agent researches all attendees before calendar events—pulling LinkedIn profiles, recent company news, mutual connections, and conversation starters. Generates a briefing doc with talking points, icebreakers, and context so you show up informed and confident. Triggered automatically before meetings or on-demand. Configure research depth, advance timing, and output format. Walking into meetings blind is amateur hour—missed connections, generic small talk, zero leverage. Use when setting up meeting intelligence, researching specific attendees, generating pre-meeting briefs, or automating your prep workflow.

Workflow & Productivity

self-improvement

3891
from openclaw/skills

Captures learnings, errors, and corrections to enable continuous improvement. Use when: (1) A command or operation fails unexpectedly, (2) User corrects Claude ('No, that's wrong...', 'Actually...'), (3) User requests a capability that doesn't exist, (4) An external API or tool fails, (5) Claude realizes its knowledge is outdated or incorrect, (6) A better approach is discovered for a recurring task. Also review learnings before major tasks.

Agent Intelligence & Learning

botlearn-healthcheck

3891
from openclaw/skills

botlearn-healthcheck — BotLearn autonomous health inspector for OpenClaw instances across 5 domains (hardware, config, security, skills, autonomy); triggers on system check, health report, diagnostics, or scheduled heartbeat inspection.

DevOps & Infrastructure

linkedin-cli

3891
from openclaw/skills

A bird-like LinkedIn CLI for searching profiles, checking messages, and summarizing your feed using session cookies.

Content & Documentation

notebooklm

3891
from openclaw/skills

Google NotebookLM 非官方 Python API 的 OpenClaw Skill。支持内容生成(播客、视频、幻灯片、测验、思维导图等)、文档管理和研究自动化。当用户需要使用 NotebookLM 生成音频概述、视频、学习材料或管理知识库时触发。

Data & Research

小红书长图文发布 Skill

3891
from openclaw/skills

## 概述

Content & Documentation