Agent Forge Hackathon: Build OpenClaw AI Assistant 🦞
Building OpenClaw AI Assistants
The era of simple chatbots is over. Real AI applications need to access live data, write their own code, autonomously manage their own state, and run reliably in the cloud.
The Building OpenClaw AI Assistants hackathon provides the ultimate stack to ship production-ready agents in one day. This is a solo competition. You will be building, testing, and deploying your solution independently—proving you have what it takes to build full-stack AI single-handedly. We are moving beyond local prototypes—if it doesn't deploy and manage real data, it doesn't count.
The Challenge
Build an autonomous OpenClaw assistant or data-driven application that solves a real-world problem.
Unlike standard hackathons where you build UI shells, this event focuses on functionality, live data, and true autonomy. Your OpenClaw agent should be able to gather intelligence (Scraping), autonomously spin up and manage its own database (Storage), process the information, and live on the web (Deployment).
The Stack (Your Arsenal)
You will have access to premium credits and tools from our innovation partners to build your OpenClaw solution. Follow this workflow to assemble your production-ready AI assistant:
Step 1 — Zeabur (The Launchpad): Start by deploying your OpenClaw instance to the cloud. Ship your backend, APIs, and web interfaces with a single click, ensuring your project is live, accessible, and scalable from the start—no DevOps friction required.
Step 2 — Agnes AI (The Brains): Install the purpose-built Agnes-Claw or Agnes-Claw-Pro models as your primary LLM backend. They deliver high-quality, low-cost reasoning and advanced tool-calling capabilities specifically optimized for powering the decision-making loops of OpenClaw agents.
Step 3 — Bright Data (The Eyes): Give your assistant the ability to browse the web. Install Bright Data OpenClaw skills to enable web search capabilities, allowing your agent to fetch real-time data, monitor trends, or aggregate research automatically using reliable, large-scale infrastructure.
Step 4 — TiDB Cloud Zero (The State): Add structured data persistence to your agent. With zero sign-up, zero config, and zero friction, your OpenClaw agents can provision fully functional, disposable distributed SQL databases using just a single line of curl to effortlessly and autonomously manage their own state.
Step 5 — mem9 (The Memory): Equip your OpenClaw assistants with long-term memory and contextual awareness. Use mem9 to seamlessly store, embed, and retrieve past interactions and user preferences, allowing your OpenClaw agents to remember who you are and retain context across infinite sessions.
Step 6 — QoderWork (The Workspace): Extract all your OpenClaw features and unique selling points into a document and send it to QoderWork. This agentic desktop assistant will help you rapidly produce the final presentation, PowerPoint for submission to showcase your build.
The Goal: Build OpenClaw agents that autonomously browse the web, collect data, spin up their own storage to hold it, and make decisions. You're encouraged to come up with your own ideas; also here are some example ideas for your reference:
Market Watcher: An OpenClaw agent that scrapes competitor pricing across 50 e-commerce sites, provisions a TiDB Cloud Zero database to store historical pricing, and adjusts your own pricing database via API.
News Synth: An OpenClaw app that aggregates breaking news from specific niche forums, indexes the content into an agent-provisioned database, and summarizes them into a daily briefing.
Real Estate Hunter: An OpenClaw agent that monitors listing sites for specific criteria, stores historical trends in its own SQL database, and alerts users instantly when a deal appears.
The Workshops
We will host hands-on sessions to get you up to speed with the tech stacks.
🏆 Prizes
Sponsored Hackathon Prizes 🚀
All winning participants will earn a share of exclusive hackathon prizes, including sponsored credits and tools from our partners to keep building and scaling their solo projects.
⚡ Agenda
10:00 AM - Kickoff & Introduction
10:30 AM - Technical Workshops
11:30 AM - Project Setup & Hacking Begins
12:30 PM - Lunch
4:30 PM - Hacking Ends / Live Demos
5:30 PM - Winners Announced + Networking
6:00 PM - Close
Who should come?
✅ You want to build OpenClaw AI that accesses the real internet, not just static datasets.
✅ You want your AI to have actual memory and autonomously manage its own databases.
✅ You want to deploy something live, not just run it on localhost.
✅ You want to connect with the SMU AI community and the AI Builders network.
Community Partner:
AI Builders: A premier community of AI builders, developers, and innovators in Singapore, Tokyo, and San Francisco Bay Area.
Special Thanks:
SMU AI (SMU Artificial Intelligence Club): A student-led initiative proudly supported by the Singapore Management University Institute of Innovation and Entrepreneurship (SMU IIE)
⚠️ Limited spots available. Register now.