
2
2
1 year of experience
Tech builder focused on Web3, AI, and full-stack development. I enjoy turning ideas into real projects β recently built RiddlePay, a riddle-based interactive access system. Formerly at Webcoin Labs where I worked on projects, fundraising, influencer programs, and product execution. Always learning, experimenting, and building meaningful things that solve problems creatively.

OmniClaw Console is a full-stack agentic economy demo that makes machine-to-machine micropayments feel like a conversation. A user types a natural language request β "get the latest tweets from @elonmusk" or "compare ETH and BTC this week" β and the system does the rest autonomously: an LLM planner routes the request to the right paid API skill, OmniClaw's policy engine enforces spending guards (budget, rate limit, recipient allowlist), the selected endpoint is inspected for its x402 payment requirements, Circle Gateway signs an EIP-3009 off-chain authorization and settles the nanopayment on Arc, and the raw API response is streamed back through an LLM that formats it into a clean, readable answer. Every step is visualized in a real-time execution trace in the UI. The project demonstrates why nanopayments are the only viable pricing model for per-action AI commerce. Traditional on-chain gas fees (~$0.005/tx) would consume 40%+ of a sub-cent API call β making it economically impossible. Circle Gateway batches EIP-3009 authorizations into amortized on-chain settlements, cutting effective per-payment overhead to under $0.0001 and unlocking genuine per-query pricing at scale. Skills supported at launch: Twitter Autopilot, Multi-Source Search, YouTube SERP, Crypto Market Data, Prediction Markets, and MarketPulse β all monetized at the API level via x402 on Arc Testnet. The stack is Next.js 15 + React, TypeScript, TailwindCSS, shadcn/ui, and Featherless-hosted Qwen3 for LLM planning and answer synthesis. OmniClaw handles the payment policy engine, Circle Gateway handles nanopayment infrastructure, and Arc is the settlement layer for every transaction.
26 Apr 2026

OmniAgentPay gives AI agents a complete payment infrastructure layer. Think of it as Stripe for AI agents one SDK that lets any autonomous agent handle money safely and instantly. Traditional blockchain SDKs are built for humans with screens and confirmation buttons. Handing an AI agent a private key is a security disaster waiting to happen hallucinations, prompt injection, or simple logic bugs can drain a treasury in seconds. OmniAgentPay solves this. We wrap Circle's developer-controlled USDC wallets in an atomic Safety Kernel that enforces spending rules before any transaction executes. What agents get: Universal pay() Method: One call intelligently routes through direct USDC transfers, x402 pay-per-use APIs, or cross-chain CCTP transfers automatically. Atomic Spending Guards: Budget limits, rate limits, recipient whitelists, and transaction caps enforced atomically, even under high concurrency. Autonomous Cross-Chain: Full Agent-Side CCTP minting to Arc Testnet and other networks no external relayers required. Zero Blockchain Complexity: No ABIs, no gas math, no private keys. Just pay(). We're not building another agent application. We're building the infrastructure any AI agent can plug into to handle money whether it's LangChain, OmniCoreAgent, or a fully custom agent. Built With: Python, Circle Developer-Controlled Wallets, CCTP V2, x402 Protocol, Arc.
24 Jan 2026