Prototyping an agent = easy. Running it reliably at scale = the real challenge. We'll build one live @AISummitSeoul — stateful workflows, secure tool execution, sandboxed runtime — with LangGraph + CubeSandbox on OCI Bare Metal. 📅 Aug 19–20 · COEX Grand Ballroom & Exhibition Hall B 👉 @CubeSandbox #TencentCloud# #CubeSandbox# #Oracle# #OCI# #LangGraph# #AISummitSeoul# #AIAgents# #AgentInfrastructure#

Open weights are table stakes now So here's the boring infra nobody wants to tweet about, also open⚡️ Things we've open sourced: — CubeSandbox, per-conversation sandboxes with browser, code, shell and file access, spun up and torn down for you — Agent Memory, a shared memory layer across your agents, and now across your teammates' agents too Things we've upstreamed: — RoCE optimizations for DeepSeek's DeepEP, doubling throughput on commodity networks, with 30% carrying back to InfiniBand — FlexKV, tiered KV cache offloading, now in NVIDIA Dynamo, vLLM and TensorRT-LLM mainlines All four are searchable by name, repos and docs. Pull requests welcome, and so are complaints 🛠️

If your agent executes code, you want to run it in an isolated environment. I learned this the hard way. I also know a couple of people who let OpenClaw go nuts and had to wipe out their laptops after a few days to clean up the mess. Two rules you must always follow: 1. Agent that runs code → isolated environment 2. Agent that controls a browser → isolated environment But that generates a new problem: that environment has to start quickly, use as little memory as possible, and give you enough control to operate it. This is hard to achieve, but you don't need to reinvent the wheel: Cube Sandbox is an open-source MicroVM sandbox developed by Tencent Cloud. Think of it as a production-grade agent infrastructure that you can use to run agents at scale. Cube Sandbox uses RustVMM and KVM to run each sandbox with hardware-level isolation. • It cold-starts in under 60ms • It uses less than 5MB of RAM overhead • You can launch tens of thousands of sandboxes within a minute Here is what you can do with it: 1. Capture, clone, and restore sandbox state with snapshots and rollback 2. Deploy sandbox clusters through Kubernetes 3. Run workloads on ARM infrastructure 4. Observe what happens inside agent executions 5. Govern ingress and egress traffic 6. Persistent volumes and cross-machine pause/resume Here is the GitHub repository: You can inspect the code and try it out with your own agent workflow. #ad#

We just reported our Q2 2026 results, revenue came in at RMB204.8 billion. Sharing a few things from the AI side： Good products and good models pull each other forward, that's where all of this comes from. Three things, not everything: 🔷Hy3 is out in full, and Hy4 lands later this year. What sped things up was the model team and the product team hunting for problems inside real products instead of benchmarks. Turns out model shaped that way get used, top three on OpenRouter since launch. 🔷WorkBuddy is now the most used AI agent on desktop in China, and it's wired into our docs, knowledge bases and meetings, so the agent starts with the context you already have. Users there pick from a lineup of leading models, 60% chose Hy3, and the other 40% keep us honest. 🔷CubeSandbox and Agent Memory exist because production forced them into existence. Agent Memory cut token usage 61%. Both stay open, because this layer works better as a commons than a secret. Still early. Someone in line for the elevator already put it better than we could 👇 (whoever you are, thx)