Browser Usage Hackathon ⚡ Delhi Edition

Delhi, we are bringing the Browser Usage Hackathon to you. ⚡Spend a Saturday building AI agents that can search, test, monitor, book, shop, and perform useful work on real websites.Come with an idea, join a team, or build solo. No prior experience in browser automation is needed. We will start with a hands-on walkthrough of Browser Agents 101 to get everyone up to speed quickly.🎯 The theme: Delhi EditionBuild an agent that solves a real browser workflow. Choose an area:🧑‍🚀 Personal Assistant: automate repetitive tasks such as scheduling, forms, account management, and recurring web workflows🔎 Research and Intelligence: gather information across multiple websites, compare results, monitor changes, and return structured findings instead of a pile of tabs🧪 Development and Testing: test a product like a real user, reproduce bugs, inspect live interfaces, and turn stable checks into repeatable workflows🛒 Commerce and Reservations: research, compare, prepare carts or bookings, and create secure approval points before payments or other sensitive actions📡 Monitoring and Operations: watch dashboards, lists, prices, availability, or critical business pages and act when something changes🃏 Curiosity: if an agent operating a real browser significantly improves workflow, it belongs here⭐ Build on webcmdwebcmd is a self-learning browser infrastructure for AI agents.Your agent can explore an unknown website, preserve what it learns, and turn stable workflows into deterministic CLI commands with structured output. Instead of reasoning through the same interface on each run, it can reuse a reliable command and return to the browser when something changes.Explore once. Learn the workflow. Reuse the command.Start here:🔹 webcmd on GitHubThe webcmd team will be in the room to assist with setup, browser workflows, adapters, and debugging.🛠️ Bring your favorite stackUse Claude Code, Codex, OpenClaw, Playwright, Browser Usage, Browser MCPs, local models, hosted models, or any API and tools that help your agent complete the task.⚖️ How we judge (100 points)🟢 Live reliability, workflow completed on stage: 30💡 Usefulness, solves a browser task that someone actually wants to automate: 25🧠 Technical depth, how well the agent reasons, recovers, and reuses what it learns: 20✨ Creativity: 15🎤 Demonstration and storytelling: 10🚨 Two strict rulesYour demonstration must be done live or use a screen recording captured from a real execution. We reward agents that truly complete the workflow.Build responsibly. Use your own accounts, respect platform terms, and maintain a human approval step for payments, messages, submissions, deletions, or other sensitive actions unless you are working in a safe environment.⏱️ Format🟠 Saturday, August 8, 2026 · 10:00 AM to 5:00 PM🟠 We will kick off with a 30-minute walkthrough on Browser Agents 101, including a quick demonstration of webcmd👥 Come alone or form a team of up to four🎒 What to bringA laptop, your favorite model or API keys if you already have them, and a browser workflow you would like to stop doing manually.🙌 Who should comeAI agent builders, open source contributors, automation engineers, developers, students, founders, local model enthusiasts, and anyone curious about giving agents useful access to the real web.No prior experience with webcmd or browser automation is necessary. The opening walkthrough covers that.📍 Delhi · Supported by webcmdSeats are limited to keep the room practical and rich in signal. Click RSVP and bring a building friend. 👇