dshpluginsdshplugins.cc

alvinunreal/openpets#dsh

Bridges DeepSeek Harness lifecycle status, errors, and approval requests to a locally running OpenPets desktop companion.

notify
10Health score
Install · dsh CLI
github$ dsh plugin --profile web add github:alvinunreal/openpets/tree/main/packages/dsh

Health breakdown

10 / 100
License0 / 25
Repo verified0 / 15
Documentation10 / 15
Adoption · stars0 / 20
Community · forks0 / 10
Distribution · downloads0 / 15

Score reflects license, community signals, documentation and distribution. It is not a code audit — review the source before installing.

Security

License
Risk disclosurepartial — review the source
Network callsnone
Credentialsno
Manifestdeclared

Key metrics

Downloads / mo0
Star trend0
past week
Stars
0
Forks
0
Listed
Aug 18, 2026
Last updated
Aug 18, 2026

Related

Related plugins

liustack/modsearch80

Models like DeepSeek-V4-Flash have no web access, or a weak one. ModSearch is a plug-in that greatly strengthens the model's web search, X search, and single-page fetch.

5.6k 115
shaobeichen/dsh-pocket55

Remote phone access to the DSH Web UI: scan a QR code for LAN or public (cloudflared tunnel) access with real-time sync, a mobile-adaptive layout, and a settings tab.

4.4k 82
FuzzySoul/dsh-free-vision59

A free vision plugin for DeepSeek Harness (dsh): gives text-only models the ability to read images — screenshots, code errors, UI layouts, documents, OCR — powered by free-tier vision models, with a built-in settings UI and zero MCP configuration.

2.1k 2
luzhengyangtx/dsh-telegram-duty80

Turn DeepSeek Harness (DSH) into your always-on pocket duty office: message a Telegram bot from your phone, the duty agent gets to work, and the result comes back to your phone. Idle cost is zero tokens — the plugin long-polls getUpdates and only wakes an agent when a message arrives.

1.6k 2
xiaoshihou514/dsh-weixin57

npm i -g @deepseek-ai/dsh dsh plugin --profile web add "github:xiaoshihou514/dsh-weixin#main"

1.0k 2
gloryxpnv/dsh-tool-vision80

Local-first structured vision for text-only agents: images go to a local OpenAI-compatible VLM and come back as JSON evidence (summary, verbatim OCR, layout regions, entities/relations, colors, explicit uncertainty), with anti-hallucination fallback and an optional paste/upload bridge; zero cloud cost, images never leave the machine.

703 1