Kong 发布 Volcano 云平台,为长时间运行的 AI Agent 提供托管
Kong 这个 Volcano 是专门给 AI Agent 用的云平台,Claude Code、Cursor 都能在上面部署,Postgres、沙箱这些基础设施都配好了。最妙的是 LavaFlow 能自己查故障、通过 GitHub 提交补丁,省掉翻日志的时间。长期跑 Agent 的开发者可以试试。
Kong 推出面向 AI Agent 的云平台 Volcano,针对传统托管按秒级请求设计、而 Agent 往往运行数小时并可能中途失败的痛点。开发者可以在 Volcano 上用 Claude Code、Cursor 或 Codex 构建 AI Agent,平台内置托管、Postgres、登录体系、存储、沙箱和长时间运行的工作流支持。
核心技术组件是 LavaFlow:它监控线上应用和代码库,定位故障原因,并通过 GitHub 提交修复,给开发者返回建议补丁而非让开发者自行翻日志。
这类基础设施把 Agent 开发从自拼工具链变成开箱即用,对需要在生产环境长期运行 Agent 的团队是直接可用的部署选项。
Most hosting was built for requests that finish in seconds. Agents run for hours, wait on a person, and sometimes fail halfway through.
@kong has released Volcano, a new cloud where Claude Code, Cursor or Codex can build an AI agent and deploy it with hosting, Postgres, logins, storage, sandboxes and long-running workflows already in place.
The really interesting piece is LavaFlow: it watches the live app and codebase, finds why something broke and submits the fix through GitHub, so developers get a proposed patch instead of digging through logs.
This report is categorized under AITOP's "Products" desk, focusing on US frontier AI labs and Silicon Valley technology leaders. Within our cross-regional analytical framework, it directly maps to AI developer toolchains, coding agents, and engineering workflows and US-China foundation model benchmarks and commercialization comparison. Key entities and technical topics under continuous tracking include Kong, Volcano, Claude Code, Cursor.
Source attribution: curated from rohanpaul_ai (@rohanpaul_ai). Cross-source corroboration: 11 independent sources have covered this development (including LangChain, TestingCatalog, openclaw), confirming industry-wide signal strength.