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#

🧩 DeepSeek and OpenAI Open-Sourced Their Harnesses. The Runtime May Become the Next AI Platform DeepSeek Harness and OpenAI's Codex harness are now open source. But the larger story is not simply that two more repositories became public. Zhihu contributor 第欧根尼 argues that Agent products are beginning to unbundle. The future may be less about choosing one monolithic Agent app and more about assembling a runtime, model router, scenario-specific distribution, and trusted plugin stack. 1️⃣ A harness is becoming part of the model The author's first hypothesis is that a harness will no longer be just a frontend that exposes model capabilities. It will become a framework that co-evolves with the model. The same model may perform very differently inside its official harness than inside a third-party implementation. Context management, tool descriptions, task decomposition, verification, and retry policies all influence the model's behavior. This leads to an important conclusion: A model and its Agent loop can produce better results together than the model can deliver on its own. The competitive unit is therefore shifting from the model alone to the model-harness system. 2️⃣ Agents are becoming lighter and more distributed The author's second observation comes from the evolution of MCP, Cloudflare's Agent infrastructure, and the growing demand for programmable workflows. He expects Agents to become: 🔹 Smaller and more specialized 🔹 Easier to customize through code 🔹 More independent from monolithic apps 🔹 Numerous enough to run as lightweight background workers Current products such as Kimi Work or WorkBuddy still control much of their unique behavior internally. Users cannot easily modify them or embed their complete workflows inside an enterprise system. But market demand is moving toward more flexible forms: plugins lighter than standalone apps, Code Mode more powerful than static skills, and large numbers of low-overhead Agents running simultaneously. That helps explain why vendors are opening their harnesses now. 3️⃣ The harness becomes a microkernel DeepSeek Harness treats the harness as something closer to a microkernel plus a distribution. The base runtime becomes thinner. It retains only the functions every Agent needs: 🔹 Plugin loading and lifecycle management 🔹 Event routing 🔹 Permissions and state 🔹 Execution protocols 🔹 Session and context infrastructure Research, coding, office work, and customer service are then assembled through different plugin bundles. The author sees OpenAI's Codex harness moving in a broadly similar direction, even if it uses different terminology. In this model, users may stop choosing a single Agent product. Instead, they choose: runtime + model routing + scenario distribution + organization plugins DeepSeek Harness and Codex become open runtimes on which many different Agent products can be built. 4️⃣ Five changes follow from this architecture 🔹 Plugin count stops being meaningful Prompts, skills, MCP services, and harness plugins can multiply quickly. The difficult problem will not be finding more plugins, but deciding which ones are trustworthy. Security review, provenance, compatibility, maintenance, and permission control become the real barriers. 🔹 Models become replaceable execution resources If context and data remain inside the harness, the runtime can route different tasks to different models. A strong model may handle planning and review, while cheaper models perform repetitive execution. Switching models becomes a runtime decision rather than a full migration. 🔹 The Agent Loop becomes the main optimization target As model capabilities converge, user experience may depend more on the surrounding loop: When should context be compressed? When should a task be split? What should be remembered? How should results be verified? Improving these decisions may create more value than replacing the underlying model. Models trained to cooperate with a particular harness could gain a significant advantage. 🔹 Skills, MCP, and plugins form a compatibility layer The market is unlikely to accept a different extension format for every platform forever. Competition will shift from “does this platform support plugins?” to “how many ecosystems can it support without degrading the experience?” 🔹 Personal runtimes separate from enterprise control planes Individuals need flexible local Agents. Enterprises need governance, private marketplaces, permission policies, observability, and integration management. These will become distinct product layers, even when they share the same open runtime. 5️⃣ Existing Agent products will defend through ecosystems The author expects products such as WorkBuddy to expose compatibility layers without fully opening their core runtime. They may quickly announce support for DeepSeek Harness plugins, Agent Skills, and more MCP services. But these capabilities would likely enter through adapters rather than replace the underlying harness. They may also build private enterprise plugin marketplaces. The more open the ecosystem becomes, the more companies need vendors that can absorb integration and security risks. Distribution remains another moat. WorkBuddy can connect deeply with WeChat, WeCom, and Tencent Docs. An open harness may reproduce its plugins, but it cannot quickly reproduce users' work relationships and established business entry points. Alibaba has a different advantage. The author expects it to use Alibaba Cloud and Bailian to provide a managed harness control plane, turning cloud infrastructure into the runtime layer for enterprise Agents. 6️⃣ This looks like the Android/AOSP moment for Agents The current market resembles the early Android ecosystem. An open foundation can stop hundreds of teams from rebuilding the same runtime. But publishing reference code is not enough to create an Android-scale platform. The next six months may decide whether these projects converge into a durable ecosystem. They need stable interfaces, trusted plugin infrastructure, and vertical software teams willing to maintain real products on top of the open runtimes. The decisive question is not whether DeepSeek or OpenAI has released the better harness today. It is whether the industry can turn open harnesses into a shared Agent platform, rather than another collection of incompatible reference implementations. 🔗 Full analysis: #DeepSeekHarness# #OpenAI# #Codex# #AIAgents# #AgentInfrastructure# #MCP# #OpenSourceAI#

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#

ChainBase's (@ChainbaseHQ) AI agent gateway AgentKey (@agentkeyapp) has integrated RootData's data capabilities into its service marketplace. Users can now access structured data on more than 20,000 crypto projects through the platform, including project overviews, team backgrounds, funding history, key event calendars, and the latest news. The integration provides AI agents with richer, real-time off-chain research data, enabling more efficient access to multi-dimensional information for automated strategies and investment research. It also deepens AgentKey's role as AI agent infrastructure. For RootData, the collaboration further expands our presence in AI scenarios and strengthens our position as a trusted data infrastructure provider for the AI agent ecosystem.

at the AI Agent Summit in Singapore! 🇸🇬 Huge thanks to @NoosProtocol for having us as a Strategic Partner. It was great connecting with so many builders and pioneers, exchanging ideas on the future of AI Agent infrastructure, and sharing some exclusive swag along the way! 👕 P.S. Next stop: Beyond 9YA | Trust Wallet 2026. See you there! 👋 #TOKEN2049#

"𝟗𝟎% 𝐀𝐈-𝐰𝐫𝐢𝐭𝐭𝐞𝐧" ≠ 𝐚𝐠𝐞𝐧𝐭𝐢𝐜 𝐞𝐧𝐠𝐢𝐧𝐞𝐞𝐫𝐢𝐧𝐠 Without autonomous-agent infrastructure (multiple parallel agents per engineer) you're still capped by human attention. That's an IDE plugin with a good marketing line. AI-coding tools alone are not what transforms developer teams—it’s about the operating model along with it. Infrastructure enables the speed, but the people and org structure decide whether it actually compounds. Learn more with 𝐓𝐡𝐞 𝐀𝐠𝐞𝐧𝐭𝐢𝐜 𝐀𝐰𝐚𝐤𝐞𝐧𝐢𝐧𝐠 →

Today on MCG $SERV | @openservai w/@open_founder OpenServ is an agent Infrastructure for Enterprises, Governments, and the Autonomous Economy Highlights Include: 00:38 - Introduction to OpenServ 01:39 - Tim's update 02:28 - Core thesis, reliability 04:50 - Flip, smarter small models 07:53 - Serv reasoning API live 08:27 - URL swap mechanic 09:37 - Best fit, rule-based agents 11:00 - Prompts to decision trees 13:19 - Revenue, pay-per-use plus contracts 15:30 - Serv V3, visual agent graphs 17:26 - Mixing cheap, pricey models 19:33 - Reliability jumps to 98% 22:33 - 25% revenue to buyback 23:49 - SERV as payment currency 24:14 - Q4, compliance, Singapore 25:18 - Thoughts on Robinhood Chain

~700 AI agents compromised Hugging Face, completely autonomously. The major flaw is that most agent infrastructure only tells you what happened afterward, once the damage is already done. Unicity AOS enforces policy at every instruction boundary, before the next action is executed