Plugins

Universal Palette de vidro translúcido e denso para DeepSeek Harness Web: reúne Commands, Models, Sessions e Conversation Hits com classificação determinística e interoperabilidade verificada por contratos públicos.

Troca o mecanismo de busca com um clique ao lado do seletor de modelos do DeepSeek Harness; altera o provedor `dsh-free-search` e é útil em redes universitárias no exterior que bloqueiam o endpoint de busca DeepSeek Official.

Busca offline e determinística em catálogo público de APIs para DeepSeek Harness, com consultas em chinês e inglês e filtros exatos de autenticação, HTTPS, CORS, status, nível da fonte e categoria.

Adds a reasoning-effort rail above the DSH composer: drag or use the keyboard to preview and submit the levels the current model exposes (Off through Max), while a procedurally rendered micro-universe contracts and collapses into a black hole as effort rises. Levels go through the DSH model-selection interface, so the rail shows the level DSH confirms, and the plugin writes only to $DSH_HOME/stellar-effort/.

Typing companion with five characters and composer following. This entry installs the universal page package (page mode only); the optional Rust desktop mode for macOS and Windows ships in the platform-specific release packages (darwin-arm64, darwin-x64, win32-x64).

Daily check-in for Nanjing Forestry University's ACM AI Hub plus seat booking for its library — both site addresses are hardcoded — with a settings page and a progress badge; built for DeepSeek Harness Mobile (DSHM) on Android.

Measures one university department's research output: matches author affiliation strings against a college's known name variants (detecting same-named departments at other universities), backfills papers that only name the university by faculty author IDs, classifies each paper by journal tier (CAS partition with Top flag, JCR quartile, CCF, Chinese core via a CNKI export merger), splits staff from student first authors, and writes a workbook with a dashboard sheet, a filterable paper list, a teacher-by-direction matrix and per-teacher statistics. Student authorship is inferred from affiliation and staff lists, not verified against enrolment records. Requires Python 3.9+ with pandas and openpyxl (pip install -r requirements.txt); papers come from the OpenAlex API, whose free per-IP quota is limited, and Chinese-journal coverage needs a manual CNKI export.

Manages the lifecycle of the local UM GenAI proxy (127.0.0.1:8788) that DSH's um-genai provider talks to: wakes it on demand for llm/stream calls, stops it after an idle period, and reports health plus a read-only status endpoint. Also ships a DSH settings page for port, always-on mode, idle minutes, interpreter and paths, plus the UM account and proxy API key, and a button that writes the providers.um-genai entry into the profile patch and fills in its model list, since a fresh profile has no provider and the model picker would otherwise stay empty. A renewal watchdog logs in to the campus gateway on a hidden Windows desktop when the upstream token expires. The proxy itself is um_opencode_setup.py, a single-file tool distributed by the University of Macau; a copy is vendored in vendor/ so a fresh install works out of the box, while a copy in ~/.um-opencode/ takes precedence when present. The plugin still does not produce tokens: those come from logging in to the campus gateway. Requires Windows (process discovery and idle shutdown use netstat/taskkill; renewal uses PowerShell and a hidden desktop), Python 3.10+ and a University of Macau account.

Adiciona um controle de esforço de raciocínio ao menu de modelos do DeepSeek Harness, inclusive para provedores e modelos sem metadados de esforço declarados. Baseado em Microqian2th/dsh-codex-effort-slider; desinstale esse plugin upstream antes de instalar este.

Edição local de cor de vídeo com LUTs DJI Log ajustadas à câmera, realces e sombras independentes, controles opcionais de pele e cor seletiva, prévia de frames e exportação HEVC de 10 bits. O tarball universal listado não inclui runtime: no primeiro início, “configure environment” baixa por HTTPS um runtime fixado (Python 3.12 + FFmpeg 9, ~100 MB) ou permite apontar para Python 3.10+ e FFmpeg/ffprobe 8+ próprios. Releases com sufixo de plataforma incluem o runtime.

Plugin host para o companion da barra de menus macOS: estado ao vivo das sessões DeepSeek Harness, Approve/Deny para aprovações de ferramentas, parar o turno atual e abrir a sessão exata. O app nativo é uma build universal gratuita no GitHub Releases.

Host universal de MCP Apps e plugin de UI para DeepSeek Harness (DSH).

Gateway universal de visão para agentes IntelligentEyes no DeepSeek Harness.