Tencent EdgeOne Makers - Ship AI agents like web apps, in minutes.
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.
Replies
How do you handle cold starts for agents that haven't been invoked in a while — is there a warm-up penalty on the first request, and does that differ between the JS and Python runtimes?
Tencent EdgeOne
If you try it out, would love to hear how the first-request latency feels on your side.😊
@kassy_kane Will do! I'll definitely report back on the first-request latency once I've had a chance to try it out. Thanks!
This sounds very important like Cloudflare. I wish it was clearer whether the AI agents can use EdgeOne through a CLI! Congrats on the launch :>
Tencent EdgeOne
That's really helpful feedback 😊
Yes, agents can be built and deployed through our CLI. We'll take a look at making that more obvious in the product messaging.
You can find the quick start guide here:
https://pages.edgeone.ai/document/agents-quick-start
Tencent EdgeOne
@xichiwoo Thanks! Yes — there's a full CLI. npm i -g edgeone, then edgeone makers dev runs your agent locally for debugging, and you deploy straight from the CLI too. Agents are first-class there, same as web apps. :)
Tencent EdgeOne
@xichiwoo Thanks! And yeah — CLI is fully supported. You can deploy agents straight from the command line with our CLI, fits right into your existing dev workflow. Appreciate the feedback on making that clearer though, we'll make sure it's more visible on the page!
For teams migrating an existing LangGraph setup that's already deployed elsewhere, how much of the agent code needs to change vs just the deployment config?
Tencent EdgeOne
That's exactly the experience we were aiming for. The less time spent adapting code to a platform, the more time you can spend improving the agent itself.
Congrats on the launch!
Is "sandbox" referring to the browser's sandbox environment?
Tencent EdgeOne
Easy misunderstanding. When we say "sandbox," we're talking about an isolated execution environment for agent actions, rather than the browser sandbox most people are familiar with.
Gro
Coming from stitching together a bunch of cloud services, having this as one coherent thing is refreshing.
Tencent EdgeOne
@lily_liu8 Appreciate that 😊 We've definitely felt that pain ourselves, which is a big part of why Makers exists in the first place.
Tencent EdgeOne
@lily_liu8 Right? Stitching five services together just to get one agent live is exhausting — and then you're maintaining all of them. Having it as one coherent stack is the whole point. Glad it feels that way, thanks!
Multi-user isolation out of the box is a big deal for anyone serving real customers, not just demos.
Tencent EdgeOne
@xiao_zhang9 That’s exactly where things start to matter. A lot of setups work fine in single-user or demo mode, but once you move to real customers, isolation and predictable behavior become essential pretty quickly.😊
Tencent EdgeOne
@xiao_zhang9 100%. The moment you go from demo to real customers, isolation stops being optional — it's table stakes. We made it a default so you don't have to build that layer yourself. Thanks for calling it out!
BiRead
nice product, nice team
Tencent EdgeOne
@ll_wen Thanks! 🙌 glad you like it
Tencent EdgeOne
@ll_wen Thanks, really appreciate that! Great team makes all the difference.
Magicam
Congrats on the launch!
Tencent EdgeOne
@arthur_winston3 Thanks! ❤️
Tencent EdgeOne
@arthur_winston3 Thank you! 🙏
DeckSpeed
Most "agent platforms" stop at the build step. Seeing one that actually owns the run-and-serve part is what makes this stand out.
Tencent EdgeOne
@hanzhizhang0405 Thanks — that’s a really good way to put it 😊 We’ve seen that the real friction usually starts after the first working version, when you need to actually run it reliably for users, not just build it.
Tencent EdgeOne
@hanzhizhang0405 That's exactly the gap we saw — tons of tools help you build an agent, very few actually help you run it for real users. We wanted to own that "run and serve" part so you don't have to piece it together yourself. Appreciate you seeing the distinction!
Tencent EdgeOne
@kitty_lee1 @tehreem_fatima5 Just to add on the multi-agent side: CrewAI is auto-instrumented, so sub-agent handoffs and node transitions get traced with zero code changes — each run becomes a full trace tree, not flattened logs.
For tool latency, every tool span carries its own timing, inputs, and outputs, and you can filter by conversation_id to follow a whole multi-turn session.