<p>Hey Product Hunt 👋 Kitty here, product lead for Tencent EdgeOne Makers. </p><p></p><p>Over the past year, I've watched more and more people—including myself—start building their own AI Agents.Today, building an Agent has never been easier. A solid idea and a few hours gets you a working demo. But the real work starts after the demo ships.</p><p></p><p>Suddenly, you're hit with a wall of production questions: How do you manage memory? How do you run tools securely in sandboxed environments? How do you trace and debug execution paths? How do you scale when a hundred users hit it at once? And how do you deploy it globally so it's actually fast?</p><p>Most builders end up choosing between two painful paths: spend weeks building all of this boilerplate infrastructure from scratch, or lock themselves into a restrictive platform that dictates which framework, language, or model they have to use.</p><p></p><p>We wanted a third option. That's why we built Tencent EdgeOne Makers<strong>.</strong></p><p>Tencent EdgeOne Makers is an edge platform for modern web apps and AI Agents. It fits into the workflows developers already know, with familiar CLI, Git, and CI/CD support. You get Agent runtime, sandboxed tools, memory, observability, model gateway support, serverless functions, and storage built in, without having to stitch together complex infrastructure yourself. In other words, you can deploy AI Agents the same way you deploy web apps.</p><p> </p><p>We kept the platform completely open. No vendor lock-in, no framework constraints:</p><ul><li><p><strong>Framework agnostic: </strong>Works out of the box with Claude SDK, OpenAI SDK, LangGraph, CrewAI, and more.</p></li><li><p><strong>Polyglot: </strong>Full support for both JavaScript and Python.</p></li><li><p><strong>Flexibility: </strong>Use whatever model or tech stack makes sense for your application.</p></li></ul><p><strong> </strong></p><p>Whether you’re looking to plug an Agent into an existing SaaS, website, or e-commerce flow, or you're building a brand-new AI application from scratch (like an AI recruiter, sales rep, data analyst, or fitness coach)—Tencent EdgeOne Makers is designed to let you spend your time on your product, not the plumbing.</p><p>We're excited to share this with the Product Hunt community today. Give it a spin, ask us any tough questions, and let us know what you think! Feel free to join our <a href="https://discord.gg/QGvqkBT9K9" target="_blank" rel="nofollow noopener noreferrer">Discord</a> to chat with us.</p><p></p><p>Thanks so much for the support!</p>
<p>🚀 Huge congrats on the PH launch, Kitty <a href="https://www.producthunt.com/@kitty_lee1" data-node-type="mention" data-mention-type="user" data-mention-id="kitty_lee1" target="_blank" rel="nofollow noopener noreferrer">@kitty_lee1</a> & team! "Deploy AI agents like web apps" – that tagline alone made me click. As someone who spent way too long stitching together LangGraph + memory + sandboxed tools, I feel personally attacked by your "third option" pitch 😂</p><p>What I genuinely love:</p><ul><li><p><strong>Framework-agnostic + polyglot</strong> – no vendor lock-in, no forcing me into a specific stack. Huge win.</p></li><li><p><strong>Built-in observability & model gateway</strong> – these are production must-haves, and you just ship them out of the box. Respect.</p></li></ul><p>One actionable suggestion: since you support CLI/Git workflows, how about adding a <strong>"Deploy from GitHub template"</strong> one-click flow (like Vercel does)? Let newcomers fork a pre-built agent template and have it live in 30 seconds – that would be an absolute conversion magnet.</p><p>And a quick question for you: what's the default timeout and resource limit for sandboxed tools? Is it configurable per agent? Didn't spot it in the docs – would love to know.</p><p>Definitely spinning this up tonight. Congrats again! 🔥</p>
<p>Congrats on the launch! <br>For framework-agnostic support, does the sandboxed tool execution behave the same across Claude SDK, LangGraph, and CrewAI, or do some frameworks get more native support than others?</p>
<p>Congrats on the great product! The edge angle is the interesting bet. Edge runtimes are usually tuned for short requests, but agents that actually do work run long, with memory and retries between steps. How do you guys handle an agent that runs for minutes or picks up a scheduled task later?</p>
