DeepSeek quietly releases official desktop version of Harness GUI agent tool
DeepSeek has released an official desktop version of its Harness GUI agent tool without a formal announcement, as confirmed by a hands-on test. The app lets users log in with a DeepSeek account or API key, select a local workspace, and assign tasks across modes like standard, PTC, minimal, and creative. It includes six built-in plugins, two of which are experimental, and emphasizes an 'Everything is a Plugin' architecture for extensibility.
Coverage timeline
机器之心机器之心
DeepSeek Harness，终于有官方桌面版了？ 这次，DeepSeek 没有发公告，但相关下载链接已经在社交媒体上传开了： 我们打开链接，下载、安装了一下，发现确实能用。 从界面来看，它已经是一套相当完整的 GUI：打开 App，登录 DeepSeek 账号或者添加 API Key，选一个本地文件夹作为工作区，接下来就可以像使用普通桌面 AI 应用一样，直接给 Agent 布置任务。 随后，Harness 会让用户选择自己的使用方向。它把需求粗略分成了办公科研、代码开发等类别。 接下来，它还会询问用户更倾向于哪种工作流程。 DeepSeek 还给 Agent 准备了几种「工作方式」：标准模式、PTC 模式、极简模式、创造模式。 标准模式适合大多数任务，可能也是普通用户最容易理解的 Harness 使用方式。 PTC 就稍微技术一点，允许模型先写一小段程序，再通过程序批量组织和调用工具，特别适合批量处理。 极简模式更加简单粗暴，Agent 只使用终端工具完成任务，这更接近传统 Coding Agent，对于熟悉命令行的开发者来说非常直接。 创造模式允许 Agent 编写插件、添加新功能或界面，也可以组合工具和提示词，创建自己的模式。这和 DeepSeek Harness 从一开始强调的设计理念是一致的 —— 官方把自己的架构概括为 Everything is a Plugin，也就是尽可能把 Harness 的能力设计成可组合、可扩展的插件。 从当前界面来看，DeepSeek Harness 已经内置了 6 个官方插件，包括智能体团队、语音输入、终端、Agent 循环、Subagent 和网页搜索。其中「智能体团队」和「语音输入」目前还标着「实验性」，前者用于开启多 Agent 协作，支持团队工具、成员列表和共享任务看板；后者则可以在本机调用 SenseVoice，把语音直接转成文字，不过首次使用需要额外安装依赖。 另外几个插件，更接近 Harness 的核心能力。终端负责调用本机命令行，并且可以限制单条命令最长运行时间和最大输出；Agent 循环控制 Agent 怎样一轮轮调用工具、继续执行任务；Subagent 则可以设置子 Agent 的递归层级、数量和所使用的模型，相当于允许一个 Agent 再分出多个「小助手」处理子任务；网页搜索则用来配置 Deep
Related stories
US DHS orders federal civilian agencies to remove DeepSeek AI tech
The US Department of Homeland Security has ordered all federal civilian agencies to remove DeepSeek artificial-intelligence technology from their IT systems and prohibits future procurement of its products and services, citing national security concerns. The order also covers third-party services built using DeepSeek's technology.
5 reports · 3 sources578 points · 543 comments
DeepSeek releases V4.1-Flash-1017 open-weight model with faster, cheaper agent tasks
DeepSeek released V4.1-Flash-1017, an open-weight model checkpoint with 763B parameters, now live on its website, app, and API. The update claims stronger benchmark performance, faster task completion, and shorter outputs than its predecessor, achieved via reinforcement learning with self-feedback for end-to-end project development. DeepSeek also opened its Search & Fetch APIs to everyone, priced at $0.75 per 1000 successful requests, and requires DeepSeek Harness v0.2.1-rc.1 or later for optimal use.
9 reports · 6 sources955 points · 717 comments
DeepSeek global outage hits chat and API for nearly 5 hours; token compensation issued
On October 15, 2026, DeepSeek's web chat and API services experienced a global outage starting at 8:11 AM Beijing time, affecting DeepSeek V4 Pro API and V4.1 Flash API. The issue was resolved around 12:50 PM, lasting nearly five hours. As compensation, DeepSeek credited tokens to developers based on their API usage over the past 7 days, with some users reporting credits of over 300 yuan.
2 reports · 2 sources
Hacker News questions industry's muted reaction to DeepSeek 4.1 Flash
A Hacker News discussion questions why the industry is not more alarmed by DeepSeek 4.1 Flash, a notable open-weight model release. The thread highlights the model's significance but notes a lack of widespread concern or excitement.
1 reports · 1 sources1110 points · 976 comments
News updates every hour. Subscribe in your RSS reader to get new stories automatically.
Subscribe