Plugin
Sfoglia, filtra e installa i plugin di DeepSeek-Harness.
397 plugin trovati
dsh-openai-provider
therealchickenlegs/dsh-openai-provider
Connect multiple OpenAI-compatible providers to DeepSeek Harness: discover their models, pick the ones to expose, and generate images and videos with them from a DSH session.
dsh-codex-ws
kiritoko1029/dsh-codex-ws
Switch OpenAI models between Codex-style Responses WebSocket transport and SSE from the composer, inheriting DSH provider settings with an optional priority-tier toggle.
dsh-prompt-tips
yuna78/dsh-prompt-tips
A desktop pet living in the corner of DSH: every hour it brings one official prompt technique from OpenAI or Anthropic — verbatim copy-ready EN template, 1:1 Chinese translation, personalised rationale, and 9 switchable skins.
dsh-oneshotNiko-widget
wickcrisp/dsh-oneshotniko-widget
A OneShot-themed desktop pet (World Machine) with the original game-style dialogue window, per-turn token usage , an optional OpenAI-compatible chat API, lightweight memory and a customizable persona card.
dsh-fanwork
gothepharnayadlsos-cyber/dsh-fanwork
Logic-risk review before rewriting: audit the source, decide each fix, generate several drafts in parallel, and export with a per-draft audit report. Bring your own OpenAI-compatible API endpoint and key - the plugin ships no model and returns 403 until one is configured.
codex-collab
0xyxy/codex-collab
Skill bundle that installs the codex-collab skill for driving the local OpenAI Codex CLI as a vendor instead of a consultant: every delegation carries acceptance criteria and a self-test script, the result is verified by running those tests locally, and a failure is handed back with its original error output; batch delegation runs sequentially (parallel subprocesses are not usable locally) and multi-turn continuation stays inside one session. Requires the local Codex CLI and PowerShell 7+; the helper scripts are Windows-native and only partially work on macOS/Linux.
emotion-state-portrait
333yyy-bit/emotion-state-portrait
Emotion, energy and per-user portrait engine for AI characters: a 303-word emotion library scored in two steps (pick one of 6 categories first, then choose within it), novelty reward and same-word cooldown for diversity, a spirit meter with easter-egg state transitions (excited / suppressed / angry), and per-user portraits. File mode works with any AI; the optional OneBot mode reads friend message history from a OneBot 11 endpoint such as NapCat. Requires your own OpenAI-compatible LLM endpoint and API key (EMOTION_LLM_KEY or emotion/config.json).
dsh-web-proxy
keb-ght/dsh-web-proxy
Turn a logged-in DeepSeek web account into an OpenAI and Anthropic compatible endpoint, with tool calling, image input, an account pool and a local admin console. First use needs a one-time `node scripts/fetch-assets.mjs` in the installed plugin directory to download DeepSeek's PoW runtime from the vendor CDN; without it the proxy starts but every upstream request fails.
dsh-speed
jakehemmerle/dsh-speed
Adds a Speed setting (Standard, Fast, Ultrafast) for OpenAI and Codex models on a patched dsh build: the pinned dsh 0.2.1-alpha.2 web client needs the Model / Effort child-slot patch, the host pi-ai must be 0.87.1 or 1.1.0 (other versions refuse to load), and the terminal controls need a patched dsh-TUI. Then it appears in the Model / Effort menu; in dst /speed opens a picker or sets the speed directly, and the current speed shows in the bottom bar. The choice is kept per session, provider and model and is sent as the request service tier.
dsh-plugins (dsh-grok3ai)
cc1104666/dsh-plugins
Talks to the two public Hugging Face Spaces (MiniMax-VL-01 and Llama-2-7B-Chat) that grok3ai.org only embeds in an iframe, presenting them as OpenAI-compatible models.
dsh-plugins (dsh-grok-online)
cc1104666/dsh-plugins
Runs a local OpenAI-compatible relay that forwards DSH chat requests to grok.online, exposing its two chat models in the model picker without an API key.
dsh-early-stop-guard
pf-sjtu/dsh-early-stop-guard
Keeps a DSH agent turn open when the model ends it by narrating work it has not done: on agent/turn-stopping the guard replays the turn log and classifies the trailing message with regexes — in the default mode wait / ask / done / gray end the turn with no model call, and only a promise of pending work reaches the judge — then has a judge chain of four dialect kinds (System One three-question noul, OpenAI-compatible, OpenAI Decisions, or the session LLM) rule on whether the turn is really over, and steers the same turn with agent.steer when it is not.
dsh-flavor-memory
lishicheng2054/dsh-flavor-memory
Livello di memoria per chat di personaggi: separa persona, voce e stato della relazione dai riepiloghi e archivia ogni messaggio grezzo per recuperarlo. Include un importatore di schede SillyTavern e un gateway compatibile con OpenAI.
dsh-codex-chrome
brucezhang1993/dsh-codex-chrome
Controlla il tuo Chrome (o Edge/Brave/Vivaldi/Opera) da DeepSeek Harness riutilizzando il runtime browser del plugin `chrome` di OpenAI Codex: schede, sessioni con accesso, alberi di accessibilità, screenshot e input, esposti come strumenti MCP nativi di DSH.
dsh-custom-vision
lightingha/dsh-custom-vision
Usa un proprio modello vision compatibile OpenAI in DeepSeek Harness: descrive le immagini prima che il modello principale veda la richiesta e offre `image_understand` per leggere grafici, screenshot, UI e OCR.
dsh-nanobot-subagent-link
2025bigeye/dsh-nanobot-subagent-link
Esegue l’agente CLI nanobot locale come subagent DSH tramite `nanobot_run`: ogni chiamata riceve un compito autonomo e restituisce solo la risposta finale dell’agente, in un nuovo processo o tramite un server persistente compatibile con OpenAI.
dsh-hf-spaces
dev-bravelo/dsh-hf-spaces
Aggiunge al selettore i modelli del proprio Space Hugging Face con GPU, avvia lo Space all’invio di un messaggio, mostra l’avanzamento e lo mette in pausa se inattivo o al limite di tempo. Richiede un account Hugging Face, uno Space GPU con API compatibile con OpenAI, un token salvato nel vault DSH come HF_TOKEN e un piano a pagamento per l’hardware GPU. Hugging Face addebita il tempo GPU.
dsh-plugin-openai-quota
pythoner1984/dsh-plugin-openai-quota
Avviso su una riga in cima alla finestra DSH con saldo DeepSeek, quote residue e reset ChatGPT/Codex a 5 ore e settimanali, più numero di carte reset rimaste e scadenza più vicina. La sezione carte apre la pagina utilizzo ChatGPT nel browser.
dsh-openai-auth
solstice621/dsh-openai-auth
Collega un login locale Codex ChatGPT a DSH Desktop con controlli account, snapshot della quota, sincronizzazione automatica dei modelli e selezione.
dsh-model-routes
kinocode-jp/dsh-model-routes
Plugin di gestione delle route dei modelli multi-provider per DeepSeek Harness. Registra separatamente abbonamenti OAuth e chiavi API (Claude, OpenAI, Gemini ecc.) e ne controlla la visibilità nell’elenco dei modelli.
dsh-plugin-cohere
cn47mp/dsh-plugin-cohere
Provider modelli Cohere per DSH: wire compatibile OpenAI come predefinito, canale nativo Cohere v2 per citazioni/RAG/budget di ragionamento. Adattatore diretto, senza proxy.
dsh-kiro-proxy
liujiesmart/dsh-kiro-proxy
Route provider Kiro (AWS CodeWhisperer/Amazon Q) e reverse proxy OpenAI/Anthropic per DeepSeek Harness. Riutilizza l’accesso Kiro IDE/CLI esistente.
dsh-codex-memory
rocco623/dsh-codex-memory
Port del flusso memoria V2 di OpenAI Codex in DeepSeek Harness: un agente in background estrae ogni sessione inattiva; il consolidamento riunisce le estrazioni in `memory_summary.md` dietro un diff rispetto a una baseline Git. Le nuove sessioni ricevono il riepilogo e le memorie citate tornano come conteggi d’uso. La pagina Impostazioni sceglie modello, intensità di ragionamento per fase e limiti di inattività, anzianità, concorrenza e timeout.
dsh-cot-translator-plus
sodapopper-pixel/dsh-cot-translator-plus
Traduzione del ragionamento per DSH Web UI: siti di traduzione HTTP tramite modelli o percorso modello attraverso un provider registrato in Harness o un provider OpenAI compatibile personalizzato dichiarato nel plugin.