TEAMZ AI Hackathon | Build OpenClaw AI Assistant 🦞

🚀 Build Your Own AI Assistant From Scratch Join us for a hands-on workshop where you'll build "OpenClaw" — your own customizable AI assistant powered by production-ready models and tools. No black boxes, no vendor lock-in. Just you, the code, and production-ready infrastructure. AI Builders is partnering with TEAMZ for a full-day hackathon in Tokyo — build, test, and deploy a working OpenClaw solution together. What You'll Build Over the course of this workshop, you'll assemble a fully functional AI assistant by integrating best-in-class components: Step 1 — Zeabur (The Launchpad): Spin up a dedicated server on Zeabur to deploy OpenClaw, meaning there's absolutely no security risk at all. Deploy your OpenClaw backend, APIs, and web interfaces with a single click, ensuring your project is live, accessible, and scalable. Step 2 — Agnes Claw (The Brains): Use the purpose-built Agnes-Claw and Agnes-Claw-Pro models as your primary LLM backend. They deliver high-quality, low-cost reasoning and advanced tool-calling capabilities specifically optimized for OpenClaw agents. Step 3 — Nosana (The Muscle): Supercharge your compute with Nosana's decentralized GPUs to run specialized AI models. Use them to run tasks, process heavy data workloads, or host custom local models for your assistant affordably. Step 4 — Bright Data (The Eyes): Give your assistant the ability to browse the web. Build custom web-scraping "skills" into your OpenClaw agents to fetch real-time data, monitor trends, or aggregate research automatically using reliable, large-scale infrastructure. 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 retain context across infinite sessions. Step 6 — TiDB Cloud (The State): The database built for AI Agents. With zero operational config, and zero fees until you hit scale, TiDB Cloud Serverless provides fully functional, disposable distributed SQL databases using just a single line of curl to effortlessly and autonomously manage their own state. Step 7 — QoderWork (The Workspace): Use this AI-native desktop assistant to build your code. QoderWork plans and executes complex tasks, writes and sandboxes code, helping you rapidly develop your OpenClaw logic, design custom MCPs (Model Context Protocol), and test your workflows locally before shipping. Claim Your Zeabur Credits Every participant gets free Zeabur credits to spin up a dedicated server to run OpenClaw. Select at least a 4 vCPU / 8GB RAM configuration. Tutorial New to the stack? Walk through the step-by-step guide to understand how each product works together before the hackathon: OpenClaw Tutorial Who Should Attend Agenda Judges Judging Criteria What to Bring Prizes Winning teams will receive credits from our sponsors to continue building and scaling their OpenClaw projects. More details to be announced. Hackathon Submission Submit your project before 4:30 PM: Submit your project Online Chat Group Connect with other participants, find teammates, and share ideas: Join the chat group Why Join This isn't a tutorial — it's a build session. You'll leave with a working AI assistant, production-tested integration patterns, and connections to fellow builders who ship. Walk away ready to customize, extend, and deploy your own OpenClaw variants. Build the future of AI assistants. Together.