DeepSeek Harness Plugins
DeepSeek Harness PluginManifest Valid

dsh-desk-pet

An always-on-top native macOS desk pet and skill that visually reflects DeepSeek Harness agent states.

VisionUI & ProductivityTerminal & TUIDeveloper ToolsSecurity & Policy
5GitHub Stars0ForksUpdated2026-08-20

Install

$ dsh plugin --profile web add deepseek-desk-pet

Plugin Overview & Capabilities

AI-assisted organization based on the public repository snapshot. The content must be grounded in source evidence and does not replace compatibility or security verification.

source-grounded
dsh-desk-pet (published on npm as deepseek-desk-pet) is a native macOS desktop pet for DeepSeek Harness. It runs as an always-on-top overlay that reflects agent activity across six distinct states (idle, working, waiting for confirmation, failed, completed, and sleeping). It includes five built-in animated skins and bundles an agent skill for generating custom skins from an image using local tools.

Key Capabilities

  • Displays a floating, always-on-top native macOS desktop pet overlay
  • Automatically reflects real-time DSH agent states: idle, working, waiting, failed, completed, and sleeping
  • Provides an interactive context menu and click-to-view active DSH session list
  • Includes five preconfigured animated themes (DeepSeek Whale, Blue Whale, Thread Core, Nautilus, Jellyfish)
  • Bundles a DSH skill to generate 18-frame custom skins from single reference images
  • Operates using macOS system Python with zero external npm dependencies or binary compilation required

Useful For

  • Monitoring background DSH agent progress and status without switching away from fullscreen apps
  • Getting immediate visual alerts when an agent requires approval or user input
  • Customizing desktop agent appearance with DIY image-generated skins

Who It Fits

  • macOS developers running DeepSeek Harness agent workflows
  • Users who want non-intrusive, visual status indicators for ongoing agent sessions

Documented Limitations

  • macOS only (requires darwin OS and system Python3; Windows and Linux are not supported)
  • Transparent padding around the pet intercepts mouse clicks without pass-through to background windows
  • Lacks a dedicated GUI settings window and edge-docked mini mode in current versions
  • Skin generation progress is not visualized in the pet UI and must be tracked via agent console output

DSH Compatibility

Version-specific runtime evidence collected by DSH Plugin. A missing result means we have not tested that combination yet.

Not tested yetNo runtime compatibility tests have been published yet.

Security Signals

Objective signals discovered from package metadata and source inspection. These are not a guarantee that a plugin is safe.

Dependency Counts

package.json declares 0 runtime, 0 development, 0 peer, and 0 optional dependencies.

info
Dsh Bundle Declared

package.json declares DSH bundle metadata.

info
License Declared

GitHub reports the repository license as MIT.

info
Package Manifest Available

A root package.json was captured and can be inspected by the registry.

info
Source Available

Public GitHub source metadata is available for this registry snapshot.

info

Source & Registry Notes

Public provenance, Registry classification, and the latest source check for this entry, kept separate from runtime verification.

Source repository
anneheartrecord/dsh-desk-pet
Registry source
GitHub · dsh-plugin topic
Registry classification
Plugin Bundle
Source checked
18bfb38 · 2026-09-12

This project is independently indexed from public source information. DSH Plugin is not affiliated with DeepSeek or the plugin author. Always check the author repository before installation.

Repository Activity

GitHub stars
5GitHub stars
Forks
0
Open issues
1
Last commit
2026-08-20
Last release
2026-08-19
For maintainers

Maintaining this plugin?

This listing is generated from public repository data. If you maintain this project, you can review the information and share this listing with your users if you find it useful.

Add to README
Listed on DSHPlugin.app