Plugins
Durchsuche, filtere und installiere DeepSeek-Harness-Plugins.
642 Plugins gefunden
dsh-sideband
ishuowang/dsh-sideband
Fokussierten Kontext übergeben, ohne auf den aktiven Agenten zu warten oder ihn zu unterbrechen: begrenzten Session-Snapshot einfrieren, asynchron mit einem isolierten No-Tool-LLM zusammenfassen und eine Provenienz-tragende Kapsel an eine andere Session oder einen autorisierten Room liefern — standardmäßig still für Sessions, mit explizitem Wakeup verfügbar.
dsh-shift-router
green-dalii/dsh-shift-router
Zweistufiger Modell-Router für DeepSeek Harness — LLM-Judge-Routing, Multi-Modell-Fallback-Ketten, Failover mit exponentiellem Backoff und Orchestrierung auf Aufgabenebene (DSH-Anpassung von pi-shift-router)
dsh-find-skill
moximxxx/dsh-find-skill
Bringt das vercel-labs/skills-Ökosystem per Bridge in dsh: LLM-gesteuerte Skill-Suche, -Installation und -Lebenszyklus für temporäre, Projekt- und globale Geltungsbereiche
ai-monitor
winterone-hub/ai-monitor
DeepSeek-Harness-Plugin: fragt AI-Monitor-Guthaben/-Nutzung aus lokalem SQLite ab — kostenbewusster Agent, automatische Buchführung über den AI-Monitor-Proxy.
dsh-llmwiki
chancelu/dsh-llmwiki
Lokales Markdown-Wiki als Langzeitgedächtnis für DeepSeek Harness — portiert von llmwiki
dsh-llm-codebuddy
shatyuka/dsh-llm-codebuddy
Tencent-CodeBuddy-Plugin für DeepSeek Harness (dsh).
pa-dsh
conradlu2740/pa-dsh
ProactiveAgent × DeepSeek-Harness-Plugin-Gruppe: proaktives Gedächtnis + proaktive Vorschläge, angebunden an DSH (Sammel-Bundle, Ein-Klick-Installation über dsh plugin add)
dsh-mcpguard
chenlaoshiyf/dsh-mcpguard
Durchsucht Skills und MCP-Konfigurationen nach Prompt-Injection, Homoglyphen, verstecktem Unicode, gefährlichen Shell-Befehlen und Zugangsdaten-Lecks.
noatmark-dsh-plugin
ylwl1997/noatmark-dsh-plugin
Text-Hygiene als dsh-Plugin: bereinigt nicht vertrauenswürdigen Text, scannt unsichtbare Zeichen, säubert LLM-Formatierung und escaped CSV-Formel-Injektionen.
dsh-session-billing
moesnow/dsh-session-billing
Per-session LLM cost meter for the DeepSeek Harness Web UI: folds provider usage into uncached input / cache read / cache write / output per model and prices it against DeepSeek and Xiaomi MiMo pay-as-you-go rates (DeepSeek peak-idle tiering included).
smart-compaction
joblessjoe/smart-compaction
Lets the model trigger compaction itself at a safe point via a compact_now tool (works mid-turn), plus a context_status tool reporting real token usage against the session's actual context window.
dsh-escalation-review
trentswd/dsh-escalation-review
Escalation-only LLM reviewer: reviews sandbox escapes only, keeps the sandbox, fails closed.
dsh-jev-subagent-dispatch
vitas/dsh-jev-subagent-dispatch
Cut LLM costs: route routine tasks to cheap subagent models (DeepSeek Harness plugin)
dsh-llm-codebuddy-power
pgnqukezrdxmhjso/dsh-llm-codebuddy-power
A full-featured CodeBuddy (WorkBuddy) provider plugin.
dsh-model-relay
leafyezi233/dsh-model-relay
Model relay station for DeepSeek Harness (模型中转站): serve any registered DSH LLM provider (e.g. @tnnevol/dsh-codebuddy) over an OpenAI-compatible /v1 API, so other projects can call those models with a standard OpenAI client.
dsh-remote-retry-llm-plugin
xiazhicheng/dsh-remote-retry-llm-plugin
dsh 插件,主要解决 remote 开发和 LLM 无限重试
chinese-script-policy
ksf1216/chinese-script-policy
Harness-neutral Traditional Chinese enforcer + offline converter (skill, DSH bundle, CLI). One script axis either way + Cantonese/Japanese-only filters. Converts both ways; optional wording preference. Also: an LLM output guard, cp950/GBK console scan.
dsh-opencode-free
x5427876/dsh-opencode-free
Free OpenCode Zen models in DeepSeek Harness through native HTTP requests. No OpenCode installation, login, API key, server, container, or LiteLLM is required.
dsh-paperdesk
shiyan688/dsh-paperdesk
Paper library and reading workbench: arXiv search, a local plain-file library (metadata / PDF / extracted full text), and three-level reading notes (overview / understanding / critique) kept as markdown beside the PDFs; seven model tools plus a web panel.
dsh-slot-health
janpauldahlke/dsh-slot-health
DeepSeek Harness (dsh) plugin: live local LLM endpoint health in the web rightbar. llama.cpp slots (busy/TTFT/wedged, /metrics) + Ollama MODELS (loaded vs empty). Engine fingerprinted by response shape. Installable dsh.bundle.
dsh-model-relay
qilin-zhu/dsh-model-relay
Model relay station for DeepSeek Harness (模型中转站): serve any registered DSH LLM provider (e.g. @tnnevol/dsh-codebuddy) over an OpenAI-compatible /v1 API, so other projects can call those models with a standard OpenAI client.
dsh-llm-gigachat
igrock88/dsh-llm-gigachat
DeepSeek Harness (dsh) plugin that connects Sber GigaChat models: a built-in local OAuth proxy (client-credentials -> OpenAI-compatible endpoint, upstream serialization, legacy tool-calling translation) plus automatic provider-route bootstrap, so GigaChat
dsh-opencode-free-tier
docutee/dsh-opencode-free-tier
Make DSH llm-pi-ai opencode routes pass Zen free-tier gate: opencode User-Agent + canonical ses_ session + bash/read tools. Scoped to opencode.ai only.
dsh-reckoner
curtainsmall/dsh-reckoner
A deterministic calculation engine for DeepSeek Harness, including a preset that guides the LLM to calculate through the engine rather than by text generation.