🤓 Latest Submissions
.png&w=828&q=75)
DroneOS - AI-Powered Autonomous Fleet Dispatch
DroneOS is an autonomous drone control framework built on PX4 Autopilot and ROS2. At its core is drone_core, a custom C++ SDK that exposes high-level flight control as ROS2 services — arm, takeoff, position commands, land. An OpenClaw AI agent runs on a Vultr VPS and acts as the fleet dispatcher. When emergency incidents come in through the dispatch service, they're routed to the agent via a bridge over WebSocket. The agent evaluates incident priority, checks drone availability and location, then sends flight commands through ROS2 to dispatch drones autonomously. The architecture is two servers connected over Tailscale VPN. The Vultr VPS runs the OpenClaw gateway, dispatch service, communication bridge, and React frontend. A separate simulation server runs PX4 SITL with Gazebo, dual drone_core nodes, rosbridge, and camera feeds. This is the same split you'd have in production — cloud command center talking to drones over VPN, except the drones are simulated. The frontend is a real-time dashboard connected to rosbridge over WebSocket. It shows the incident queue with priority levels, a map with drone positions, live camera feeds from both drones with picture-in-picture toggle, and an AI activity log showing every decision the agent makes. Operators see what the AI is doing and can override with natural language commands through the same OpenClaw agent. The dispatch service simulates a 911 CAD system generating incidents — medical emergencies, fires, property damage — each with priority levels and coordinates. The AI doesn't follow scripts. It decides which drone to send based on priority, proximity, and availability. The framework supports real hardware. Production Docker configs exist for Raspberry Pi companion computers communicating with Pixhawk flight controllers over serial. The simulation runs the same software stack. Live demo: http://207.148.9.142:3000 Source: https://github.com/ortegarod/drone-os
15 Feb 2026
Arc Merchant - Autonomous x402 Micropayments
Arc Merchant demonstrates autonomous AI agent payments using x402 protocol, Circle Wallets, and Arc blockchain. Built as a reference implementation and toolkit for developers and merchants, showing how agents can autonomously pay for paywalled content across multiple AI frameworks. ## What It Does Shows a complete autonomous payment flow: AI agent requests paywalled content → receives 402 Payment Required → signs USDC payment via Circle Wallets → retries with proof → gets content. No wallet popups, no human intervention. Includes adapters for Claude MCP, Vercel AI SDK, and Google GenAI to demonstrate the same payment tools working across different frameworks. ## How It Works 1. Agent requests paywalled content 2. Receives 402 Payment Required with price + merchant address 3. Signs USDC payment via Circle Wallets 4. Retries request with payment proof 5. Gets content — fully autonomous Merchant side: facilitator verifies payments on-chain, dashboard shows real-time revenue on Arc. ## Circle Product Feedback **Products Used:** Arc Testnet, Circle Developer-Controlled Wallets, USDC, Circle Developer Console **Why Chosen:** Arc's EVM compatibility made deployment straightforward given my Ethereum experience. **What Worked Well:** Arc Testnet impressed with very fast transaction finality and instant block explorer refresh. Circle's wallet structure is similar to Coinbase's CDP — same API key pattern and custody model, so implementation was straightforward. USDC as native gas simplified payments. **What Could Be Improved:** Transaction confirmation required custom polling logic since the SDK doesn't provide a built-in helper. While Circle supports webhooks for production, a simple waitForTransaction() utility would streamline development without requiring webhook setup. **Recommendations:** Include SDK examples for AI agent use cases.
24 Jan 2026
