Search community plugins for DeepSeek Harness. Compare capabilities, installation instructions and compatibility to find extensions for your AI workflow.
Say what kind of profile you want; the agent writes it and puts it up. Generates nickname/bio/taglines with the host model, picks or composes an avatar from local assets, then fills the profile page and uploads the picture - dry-run by default.
Agent collaboration
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:7gzgn/dsh-profile-stylist
Floating water-ball progress indicator for DSH web GUI: watches heartbeat/dircount/dirsize progress files, renders a draggable glass ball with metric-colored halo, silver-highlight thresholds and grab-lift drag UX. v4.9.0 adds the memory-cleaner page (memlist/memkill routes, CleanMyMac-style per-process kill) reached by clicking the memory meter in the panel footer.
Windows always-on-top task progress overlay for DeepSeek Harness (DSH): live phase, tool or command, real todo step progress, multi-task list, and approvals answered from the overlay.
Interface extensions
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:jtt0001/dsh-progress-overlay
Find the right plugin, then get started
Search by task
Use a feature keyword or category, then sort by recent updates or GitHub stars.
Explore capabilities
Read the description, AI analysis and original README to understand what a plugin does.
Check and install
Review compatibility, dependency ranges and instructions, then copy the available install command.
Questions about DSH Hub
What is DSH Hub?
DSH Hub is a community plugin directory for DeepSeek Harness, bringing together descriptions, source links and installation instructions to help you discover and compare extensions.
Does inclusion mean a plugin is tested and compatible?
No. Detail pages show recorded compatibility and dependency ranges. Unknown does not mean compatible; check the project documentation before installing.
How do I install a plugin?
Open its detail page and check the installation section. Copy the command into your Harness environment when available, or follow the project README.