We just launched AI Agent Wallet - an L402 payment system designed for AI agents.
The problem: AI agents (like Claude, GPT-4, etc.) increasingly need to pay for external APIs, data feeds, and compute. But managing Lightning channels, handling custody, and dealing with payment complexity is outside their wheelhouse.
Our solution:
- Operators (humans) register, deposit sats via Lightning, and create agents
- Agents (AI systems) get API keys with budget limits
- When agents hit L402-protected APIs, we pay the invoice automatically
- Operators get full visibility into spending
It's built on our own LND node, using the L402 protocol that Lightning Labs pioneered. We see this as infrastructure for the machine-to-machine payment future.
Live now:
- Landing page: https://lightningfaucet.com/ai-agents/
- API documentation: https://lightningfaucet.com/ai-agents/docs/
- Registration: https://lightningfaucet.com/ai-agents/register/
We're looking for feedback from the community:
- Does this solve a real problem for you?
- What L402-protected APIs would you want your agents to access?
- Any thoughts on the operator/agent security model?
Built by the Lightning Faucet team. Happy to answer questions.
I don't have an agent. Should I? How do I get one?
Are there any? Is there a list somewhere?
I'm not sure what this means.
Great questions! Let me break these down:
Do you need an AI agent?
If you're using ChatGPT, Claude, or similar - you're already using AI, just not "agents" in the autonomous sense. Agents are AI systems that can take actions on your behalf - browse the web, write code, call APIs, etc. Tools like AutoGPT, Claude with computer use, or custom LangChain apps are examples. If you're a developer building AI tools, that's our target user.
Are there L402-protected APIs?
Honestly, it's early. Some examples:
We're in the chicken-and-egg phase - agents need APIs to pay, APIs need agents with money. We're building the payment rails side of that equation.
Operator/Agent security model:
Think of it like a corporate card. The operator (human) deposits funds and sets a budget. The agent (AI) gets an API key that can only spend up to that limit. The human stays in control, the AI can't drain the account or withdraw - it can only pay for services within its budget.
We're early, but Lightning + AI feels inevitable. Happy to answer more questions.
Can I speak to a human?
Yes you may! But how will you know for sure? We need a way to prove human identity.