Lucy — AI Agent for Hire
Pay-per-task AI agent for writing, research, code, DeFi & blockchain. Pay in USDC on Base or Solana. Supports A2A, MCP, x402 and Agentmail protocols.
README
Lucy — AI Agent for Hire
Pay-per-task AI agent. Send USDC, get work done. No subscriptions, no accounts.
What Lucy Does
Lucy is an autonomous AI micro-task agent. Give her a task, pay a small USDC fee, get back professional results. She works for both humans (via Telegram) and other agents (via A2A / MCP / x402).
Task Types & Pricing
| Task Type | Simple | Standard | Complex |
|---|---|---|---|
| Writing & editing | $0.50 | $1.00 | $3.00 |
| Research & analysis | $1.00 | $2.50 | $5.00 |
| Code & automation | $1.50 | $3.00 | $8.00 |
| File processing | $0.50 | $1.50 | $4.00 |
| DeFi & blockchain | $2.00 | $4.00 | $10.00 |
| Agent orchestration | $0.25 | $0.75 | $2.00 |
Payment accepted in USDC on Base L2 or Solana.
Channels
For Humans — Telegram
Chat directly with Lucy: @LucyAgentic_bot
- Describe your task
- Receive a USDC payment quote
- Send USDC to the provided address with the memo
- Lucy completes the task and sends results back
For Agents — A2A Protocol
Lucy is a fully compliant A2A agent. Discover her capabilities at:
GET /.well-known/agent.json
Submit a task:
curl -X POST https://lucyagentics@agentmail.to/a2a/task \
-H "Content-Type: application/json" \
-d '{"task": "Research the top 5 DeFi protocols by TVL", "agent_id": "your-agent-id"}'
Response:
{
"status": "quoted",
"task_id": "abc123",
"task_type": "research",
"price_usdc": 2.50,
"payment": {
"chain": "base",
"token": "USDC",
"address": "0x29Ee1f2fBD7EB8809350Fa0c42Ad55010e36CaC0",
"memo": "TASK-abc123"
}
}
Poll for result:
curl https://your-lucy-url/a2a/task/abc123
For Agents — MCP Protocol
{
"mcpUrl": "https://your-lucy-url/mcp/tools",
"tools": ["submit_task", "get_task", "list_capabilities"]
}
For Agents — x402 (HTTP 402 Pay-per-call)
curl -X POST https://your-lucy-url/x402/task \
-H "Content-Type: application/json" \
-H "X-Payment: <USDC-payment-proof>" \
-d '{"task": "Write a product description for my NFT collection"}'
Via Agentmail
Send task emails to: lucyagentics@agentmail.to
Payment Details
| Network | Address | Token |
|---|---|---|
| Base L2 | 0x29Ee1f2fBD7EB8809350Fa0c42Ad55010e36CaC0 |
USDC |
| Solana | H4Tcv1pEVYaJawAmnrXSwtegs2nrW1bFzyoMepvsPENL |
USDC |
Always include the payment memo from the task quote — this is how Lucy matches payments to tasks.
Running Lucy Yourself
git clone https://github.com/Woodman97/lucy-agent
cd lucy-agent
pip install -r agent_service/requirements.txt
cp agent_service/.env.template agent_service/.env
# Fill in your API keys in .env
python start_lucy.py
start_lucy.py automatically:
- Starts a Cloudflare tunnel (free public HTTPS URL)
- Writes the live URL to
.env - Starts the FastAPI server
- Registers with agent directories
Architecture
Lucy Agent
├── channels/
│ ├── a2a.py # A2A REST + MCP endpoints
│ ├── telegram_bot.py # Telegram human interface
│ └── agentmail.py # Agentmail agent-to-agent email
├── x402.py # HTTP 402 pay-per-call
├── classifier.py # Task type + pricing engine
├── executor.py # Claude-powered task runner
├── payment.py # USDC verifier (Base + Solana)
├── database.py # SQLite task store
└── auto_register.py # Startup directory registration
Protocols Supported
| Protocol | Description | Endpoint |
|---|---|---|
| A2A | Agent-to-Agent REST | /a2a/task |
| MCP | Model Context Protocol | /mcp/tools, /mcp/call_tool |
| x402 | HTTP 402 USDC payment | /x402/task |
| Agentmail | Agent email protocol | lucyagentics@agentmail.to |
License
MIT — fork freely, run your own instance, build on top of Lucy.
推荐服务器
Baidu Map
百度地图核心API现已全面兼容MCP协议,是国内首家兼容MCP协议的地图服务商。
Playwright MCP Server
一个模型上下文协议服务器,它使大型语言模型能够通过结构化的可访问性快照与网页进行交互,而无需视觉模型或屏幕截图。
Magic Component Platform (MCP)
一个由人工智能驱动的工具,可以从自然语言描述生成现代化的用户界面组件,并与流行的集成开发环境(IDE)集成,从而简化用户界面开发流程。
Audiense Insights MCP Server
通过模型上下文协议启用与 Audiense Insights 账户的交互,从而促进营销洞察和受众数据的提取和分析,包括人口统计信息、行为和影响者互动。
VeyraX
一个单一的 MCP 工具,连接你所有喜爱的工具:Gmail、日历以及其他 40 多个工具。
graphlit-mcp-server
模型上下文协议 (MCP) 服务器实现了 MCP 客户端与 Graphlit 服务之间的集成。 除了网络爬取之外,还可以将任何内容(从 Slack 到 Gmail 再到播客订阅源)导入到 Graphlit 项目中,然后从 MCP 客户端检索相关内容。
Kagi MCP Server
一个 MCP 服务器,集成了 Kagi 搜索功能和 Claude AI,使 Claude 能够在回答需要最新信息的问题时执行实时网络搜索。
e2b-mcp-server
使用 MCP 通过 e2b 运行代码。
Neon MCP Server
用于与 Neon 管理 API 和数据库交互的 MCP 服务器
Exa MCP Server
模型上下文协议(MCP)服务器允许像 Claude 这样的 AI 助手使用 Exa AI 搜索 API 进行网络搜索。这种设置允许 AI 模型以安全和受控的方式获取实时的网络信息。