Tencent EdgeOne
Deliver Fastest and Most Secure Performance at the Edge
1.3K followers
Deliver Fastest and Most Secure Performance at the Edge
1.3K followers
Tencent EdgeOne is a cutting-edge global edge network platform engineered to optimize traffic routing, accelerate content delivery, and strengthen security across distributed environments. By seamlessly integrating CDN, DNS, WAF, DDoS protection, and intelligent route optimization, it delivers comprehensive security safeguards, superior network and application acceleration, advanced edge computing capabilities, and robust monitoring and operational analytics.
This is the 2nd launch from Tencent EdgeOne. View more
Tencent EdgeOne Makers
Launched this week
Tencent EdgeOne Makers is an edge platform for modern web apps and AI agents. Build with your preferred frameworks and deploy through familiar CLI, Git, and CI/CD workflows. Get built-in agent runtime, sandboxed tools, memory, observability, model gateway support, serverless functions, and storage—without stitching together complex infrastructure. Add AI agents to existing products or launch new AI applications in minutes. Deploy AI agents like web apps.
Free
Launch Team / Built With
Tencent EdgeOne
Hey Product Hunt 👋 Kitty here, product lead for Tencent EdgeOne Makers.
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.
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?
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.
We wanted a third option. That's why we built Tencent EdgeOne Makers.
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.
We kept the platform completely open. No vendor lock-in, no framework constraints:
Framework agnostic: Works out of the box with Claude SDK, OpenAI SDK, LangGraph, CrewAI, and more.
Polyglot: Full support for both JavaScript and Python.
Flexibility: Use whatever model or tech stack makes sense for your application.
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.
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 Discord to chat with us.
Thanks so much for the support!
@kitty_lee1 Congrats on the launch. Quick question; for Agents that need to interact with external APIs and user data, what best practices or built-in safeguards does Tencent EdgeOne Makers provide to prevent data leakage and ensure least-privilege access across sandboxed tools, third-party integrations, and persisted memory?
@kitty_lee1 @swati_paliwal You can use the authentication middleware provided by our platform to handle authorization and protect Agent invocations. For details, please refer to: https://pages.edgeone.ai/document/agents-authentication.
The sandbox tools run on isolated instances, so they do not affect one another.
Tencent EdgeOne
Would love to hear more about the use case you're thinking of. Different agent workflows tend to have very different expectations around permissions, memory, and external access.
@kitty_lee1 Congrats on the launch!
Surgeflow
🚀 Huge congrats on the PH launch, Kitty @kitty_lee1 & 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 😂
What I genuinely love:
Framework-agnostic + polyglot – no vendor lock-in, no forcing me into a specific stack. Huge win.
Built-in observability & model gateway – these are production must-haves, and you just ship them out of the box. Respect.
One actionable suggestion: since you support CLI/Git workflows, how about adding a "Deploy from GitHub template" 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.
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.
Definitely spinning this up tonight. Congrats again! 🔥
@kitty_lee1 @rocsheh Thanks for your support!
We support direct deployment from GitHub repositories, similar to how Vercel works.
As for the sandbox, the current limits are:
A total monthly memory-time quota of 100,000 GB-seconds.
A maximum runtime of 1 hour per instance.
These settings can be configured on a per-Agent basis. If you require higher quotas, feel free to contact us to request allowlist access for increased limits.
For a complete list of limits and quotas, please refer to:
https://pages.edgeone.ai/document/limits-and-quotas
Tencent EdgeOne
Really appreciate the thoughtful feedback. The GitHub template idea is a good one — anything that gets people from "I have an idea" to "it's live" faster is worth paying attention to.
And if you do spin something up, we'd genuinely love to hear how it goes!
Tencent EdgeOne
@rocsheh The "third option = personal attack" line genuinely made my day 😂 — hand-stitching LangGraph + memory + sandboxed tools is the exact pain we couldn't unsee, so it means a lot that it resonates.
Really appreciate the GitHub one-click template idea too — "fork to live in 30 seconds" is exactly the kind of moment we obsess over on the growth side, so this is great signal for us. And on your timeout/resource-limit question, looks like the team already jumped in with the details below 🙏
Enjoy spinning it up tonight — would love to hear how the first deploy feels. That early feedback is gold for us. 🔥
Deploying agents like web apps is the right mental model. The part I’d pressure-test is the boundary per customer or workspace: which secrets/tools the agent gets, which writes need approval, and what receipt survives after the run.
Do those permissions live with each deployed agent, or with the app/project around it?
@blah_mad In our platform, an agent is treated as a project. Access control for agent invocations can be managed through our middleware layer. Regarding tools, each agent explicitly registers the subset of tools it is permitted to use within the framework.
Triforce Todos
Congrats on the launch!
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?
Tencent EdgeOne
@abod_rehman Thanks! The key design choice here is that sandboxed tool execution lives at the runtime layer, not inside any specific framework — so it behaves consistently whether you're on Claude SDK, LangGraph, or CrewAI. The framework handles your agent logic; the sandbox, isolation and tool execution sit underneath and work the same for all of them. That said, we do ship starter templates for each so you get a smooth zero-config start.
Tencent EdgeOne
@abod_rehman
Where framework-awareness kicks in is at the tool interface layer (context.tools) and memory layer (context.store). Both adapt automatically based on a framework field in edgeone.json — so Claude SDK, LangGraph, and CrewAI each get their tools and conversation history pre-wrapped in the format they natively expect, without any glue code on your side.
Tencent EdgeOne
@abod_rehman Same execution across all of them — one sandbox, same atomic tools. The only per-framework difference is the binding format, and Claude SDK / LangGraph / CrewAI are all first-class (OpenAI Agents SDK too). You set framework in edgeone.json and context.tools hands you objects already shaped for it — no glue code.
Since this is polyglot (JS + Python), can a single agent mix both, or is it one language per deployment?
Tencent EdgeOne
@boyuan_deng1 Great question! Today it's one language per deployment — each agent runs in either a JS or Python runtime. But since Web and agents share the same project, you can absolutely have, say, a Python agent and a JS service running side by side and talking to each other. Mixing both within a single agent isn't supported yet — curious, what's the use case you had in mind? It'd help us think about where to take this.
Tencent EdgeOne
Curious what scenario would require mixing both 🤔 would love to hear more.
Tencent EdgeOne
@boyuan_deng1 One language per agent — a single agent runs as one runtime (JS or Python), not both in the same process. But the project is polyglot: you can run JS and Python agents/functions side by side in one deployment, routed by file and sharing the same domain + env. Need both? Split them into separate routes and call between them.
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?
Tencent EdgeOne
@artstavenka1 Great question — and you're right that edge V8 is tuned for short requests. So we don't run agents on the edge.
Agents run on a dedicated cloud runtime built for long, stateful work: a single run goes up to1 hour, also with a sandbox (for tools/code) up to 1 hour.
Runs for minutes → sticky-routed by conversation_id, so in-memory state is reused, plus built-in conversation memory that persists across runs (native to Claude / OpenAI Agents / LangGraph / CrewAI). Step retries live in your framework loop.
Picked up later → native cron (schedules in edgeone.json) can trigger an agent on a schedule, and since state is keyed by conversation_id, it resumes from the prior context.
The edge bet is really about distribution + the fast path — the heavy work runs where it should. Curious what you're building!
Tencent EdgeOne
Love this question.The edge + long-running agent tradeoff is something we spent a lot of time thinking about when building Makers. Thanks for digging into the details.
Voquill
Congrats on the launch! Interesting direction. What does debugging look like when multi-step agent workflows fail across tools and runtimes in production?
@henry_habib We inject OpenInference-based instrumentation before your code loads, so every LLM call and tool invocation automatically becomes a structured span — with timing, inputs/outputs, token usage, and errors — without you adding any decorators or SDK imports.
Traces are viewable in both the cloud console and the local dev panel with the same UI. When a multi-step workflow breaks, just open the trace, walk the span tree to the failing step, and see exactly what went in and what came out.
Tencent EdgeOne
Great question. In our experience, the hardest bugs are rarely in a single model call — they're usually somewhere between multiple steps, tools, and retries. That's why this area got a lot of attention from us. Appreciate you digging into it.
Tencent EdgeOne
@henry_habib Great question — debugging failures across a multi-step workflow is exactly where most setups fall apart, so we made observability a first-class part of the platform instead of an afterthought. Happy to connect you with the team for the deeper technical details. What does your workflow look like?