惯性聚合 高效追踪和阅读你感兴趣的博客、新闻、科技资讯
阅读原文 在惯性聚合中打开

推荐订阅源

Google DeepMind News
Google DeepMind News
L
LangChain Blog
H
Help Net Security
博客园_首页
T
Tailwind CSS Blog
Microsoft Security Blog
Microsoft Security Blog
T
The Blog of Author Tim Ferriss
雷峰网
雷峰网
Recent Announcements
Recent Announcements
D
DataBreaches.Net
U
Unit 42
Vercel News
Vercel News
I
InfoQ
Martin Fowler
Martin Fowler
Microsoft Azure Blog
Microsoft Azure Blog
Apple Machine Learning Research
Apple Machine Learning Research
S
SegmentFault 最新的问题
Jina AI
Jina AI
博客园 - 叶小钗
博客园 - 【当耐特】
罗磊的独立博客
OSCHINA 社区最新新闻
OSCHINA 社区最新新闻
月光博客
月光博客
Last Week in AI
Last Week in AI

Hacker News - Newest: "AI"

AI can't read an investor deck AI as an attorney? Student uses ChatGPT, Gemini to sue UW over alleged racial discrimination Hacking MCP Servers in AI Systems – The Rug Pull: Tool Changes After Approval GitHub - MeepCastana/KubeezCut: Free Web based video editor Can AI judge journalism? A Thiel-backed startup says yes, even if it risks chilling whistleblowers Coming soon: 10 Things That Matter in AI Right Now DARPA built an AI to fact-check enemy weapons claims What explains heterogeneity in AI adoption? When AI Meets Muscle: Context-Aware Electrical Stimulation Promises a New Way to Guide Human Movements - Department of Computer Science AI Changed How We Build. It Did Not Change What Matters. Linux rules on using AI-generated code - Copilot is OK, but humans must take 'full responsibility for the… Meta spins up AI version of Mark Zuckerberg to engage with employees Code Mode: Let Your AI Write Programs, Not Just Call Tools | TanStack Blog GitHub - Delavalom/graft: Go framework for building AI agents. Type-safe tools, multi-provider (OpenAI, Anthropic, Gemini, Bedrock), zero vendor SDKs. India's TCS tops estimates, says new AI models did not dent services demand Gen Z's fading AI hype Strong feeling: we are in a folded AI reality GitHub - machinarii/total-recall-catalog: A reference catalog of latest knowledge retrieval, memory & RAG systems GitHub - mensfeld/code-on-incus: Give each AI agent its own isolated machine with root, Docker, and systemd. Active defense detects and stops threats automatically.. Quantization, LoRA, and the 8% Problem: Benchmarking Local LLMs for Production AI Iran war: We spoke to the man making Lego-style AI videos that experts say are powerful propaganda Powell, Bessent discussed Anthropic's Mythos AI cyber threat with major U.S. banks GitHub - immartian/bellamem: Persistent belief-graph memory for AI agents. Retrieves decisive context by importance — not recency, not RAG, not /compact. recursive-mode: The Repo-Native Operating System for AI Engineering After the attack on Sam Altman's home, will AI CEO's go on the offensive? The biggest advance in AI since the LLM Opus 4.6 vs GPT 5.4 One Prompt Unity World Generation Test “AI polls” are fake polls Client Challenge Can AI be a 'child of God'? Inside Anthropic's meeting with Christian leaders
GitHub - Woodman97/lucy-agent: AI agent for writing, rese...
vinny1 · 2026-05-22 · via Hacker News - Newest: "AI"

Pay-per-task AI agent. Send USDC, get work done. No subscriptions, no accounts.

Telegram A2A Protocol MCP x402 Payment


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

  1. Describe your task
  2. Receive a USDC payment quote
  3. Send USDC to the provided address with the memo
  4. 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.