DeepSeek Releases Harness v0.2 Preview For macOS And Windows With In-App Plugin Creation
In Brief
DeepSeek launches Harness v0.2 preview with desktop apps for macOS and Windows, featuring a plugin manager, scheduled automation tasks and in-app plugin creation.
DeepSeek has released version 0.2 of DeepSeek Harness (DSH), its open-source agent harness, in public preview. Announced on September 29, the update marks the first time the framework is offered as ready-to-run desktop installers, available for macOS on Apple silicon and 64-bit Windows through the official Harness website. The release follows the initial v0.1 developer preview launched on August 13 and comes after preview builds of an Electron-based app were spotted circulating from DeepSeek’s update server earlier in the week, ahead of any formal announcement.
Built on Cordis’s “everything is a plugin” architecture, DeepSeek Harness can function either as a desktop application or as a web interface launched from code, requiring only Node.js for the latter option. The framework is designed as a ready-to-use environment for running AI agents across several domains: everyday office tasks such as organizing files, analyzing data, drafting documents and creating presentations; software development work including repository exploration, bug fixing and test execution; research tasks with source verification; and background jobs such as batch processing. DeepSeek positions Harness as the most widely used coding agent among users of its official model API, measured by daily active users and sessions, while acknowledging the product remains at an early stage.
What’s New: Plugin Management, Automation and Reworked File Handling
The centerpiece of v0.2 is a dedicated plugin installation and management page. Previously, extending Harness required command-line work; users can now install plugins by entering an npm package name, as well as disable, uninstall and inspect each plugin’s description and source from a single interface. Alongside the six official plugins — Agent Teams, voice input, Shell, Agent Loop, Subagent and Web Search — the update ships an experimental Creation mode, in which users describe a desired plugin in conversation and Harness writes or modifies it automatically. Newly created plugins take effect immediately and appear in the manager. Notably, DeepSeek reports that roughly 60% of Harness users running third-party plugins, and the company plans to introduce an official plugin marketplace alongside a more stable plugin API with fewer breaking changes.
Version 0.2 also adds a built-in automation tasks plugin, enabled from the plugin page, which converts repetitive work into scheduled tasks with run history, adjustable frequency and editable instructions. According to a hands-on review by tech outlet ifanr, scheduled tasks continue running even after the application is closed. The plugin page lists four experimental features in total: agent teams, automatic authorization review, automation tasks and voice input — the latter downloading a roughly 1 GB local speech-recognition package based on SenseVoice.
Beyond packaging, the release substantially reworks how files, content previews and code changes are displayed. Users can hand Harness documents, spreadsheets or PDFs for analysis and chart generation, or request project modifications with code execution; generated files and each round of code changes are collected within the conversation, while a side panel previews files and diffs and results can be opened in local applications. Users can also control how much of the agent’s working process is visible.
Looking ahead, DeepSeek’s roadmap includes a stronger sandbox with improved security, enhanced agent teams, personalized long-term memory, browser and GUI automation, remote and mobile access, and session sharing with multi-user collaboration. The company also indicated it will tune future models specifically for performance within the Harness environment.
Disclaimer
In line with the Trust Project guidelines, please note that the information provided on this page is not intended to be and should not be interpreted as legal, tax, investment, financial, or any other form of advice. It is important to only invest what you can afford to lose and to seek independent financial advice if you have any doubts. For further information, we suggest referring to the terms and conditions as well as the help and support pages provided by the issuer or advertiser. MetaversePost is committed to accurate, unbiased reporting, but market conditions are subject to change without notice.
About The Author
Alisa, a dedicated journalist at the MPost, specializes in crypto, AI, investments, and the expansive realm of Web3. With a keen eye for emerging trends and technologies, she delivers comprehensive coverage to inform and engage readers in the ever-evolving landscape of digital finance.
More articles
Alisa, a dedicated journalist at the MPost, specializes in crypto, AI, investments, and the expansive realm of Web3. With a keen eye for emerging trends and technologies, she delivers comprehensive coverage to inform and engage readers in the ever-evolving landscape of digital finance.
