Plugin
Sfoglia, filtra e installa i plugin di DeepSeek-Harness.
1219 plugin trovati
API-MRI
lee-eee-eee/api-mri
Inspect API latency, streaming output and model-response fingerprints from a native DSH panel, with classic-task previews and public benchmark rankings.
dsh-memory
rosesssss66/dsh-memory
Local long-term memory for DSH: extracts preferences and project facts from sessions, injects the most relevant ones before each turn using local SQLite FTS5 search, and supersedes outdated facts. Requires Node 24+; the offline self-evolution loop needs an OpenAI-compatible LLM endpoint and API key.
dsh-card-tree
2031814001yuyue-tech/dsh-card-tree
Grows a conversation into an editable card tree where each card is one self-contained question and answer, with child cards, same-level branches and in-card follow-ups, and an overview for dragging, re-hanging, cross-referencing or pruning the graph.
dsh-llm-vertex
maryhodges5070-art/dsh-llm-vertex
Google Cloud Vertex AI (Gemini) provider: ADC or service-account credentials, project and region settings, thought-signature replay for tool calls, rate limiting, and a settings page with a live connectivity test.
dsh-tailtransit
jetruan/dsh-tailtransit
Runs a userspace tailscaled for Harness so web fetch, shell, plugin and LLM traffic can each use a Tailscale exit node, leaving routes and DNS untouched. Needs Tailscale's tailscaled installed separately; it starts a second per-user daemon, routes the selected traffic through a loopback proxy and looks up the exit IP through ifconfig.me. An auth key, if you set one, is kept in the plugin config.
alice-memory-llm
cycocyco/alice-memory-llm
Long-term memory for DSH where an LLM decides what to keep: turns pool while the session is idle, then the main chat model distills them into one-line entries in a single batched call; vector dedup runs before insert, so near-duplicates and saturated topics are dropped; recall uses hybrid vector plus FTS5 search over tiered hot, warm and cold storage; ships remember, recall, forget and prune tools. Zero dependencies, Node only.
dsh-galatea (message-channels)
loveandbeepbrother/dsh-galatea
Chat with your Galatea assistant from QQ (official bot) and WeChat: the same conversation, persona and memory as on the desktop, only the paired owner's private chat is accepted, replies go back where you wrote, and more chat apps can be added. Requires the Galatea framework.
dsh-plugin-cas-kb
niuniu-869/dsh-plugin-cas-kb
Chinese accounting and tax knowledge base for DSH agents, served by the hosted Quaesto service at api.accountingllm.site (needs network access; no account or API key, but your queries leave the machine): answers questions on CAS enterprise accounting standards, the small-enterprise accounting standards, CSA auditing standards and tax law with original articles, decision procedures, applicability checks and tax-accounting differences, exposed through 10 MCP tools and a china-accounting-standards skill.
dsh-galatea (framework)
loveandbeepbrother/dsh-galatea
Galatea: shape an AI assistant of your own. One assistant with its own persona and long-term memory (git-versioned plain files); long chats hand off to a fresh conversation without forgetting, and it tidies its memory in the background while you are away. It runs on whatever model DSH is set to and keeps its memory when you switch; every module can be turned off, and other plugins can extend it. Phone chat (QQ, WeChat) and Claude Code sessions come from the separate Galatea channels and agent-sdk plugins. Preview; needs DSH 0.2.2-rc.1 or a later 0.2.x.
dsh-one-gateway
qinyongliang/dsh-one-gateway
OpenAI-compatible gateway for every connected model: groups with failover, aliases, session stickiness, usage charts, API keys and a LAN listener (open to the whole network until you create an API key).
dsh-galatea (agent-sdk)
loveandbeepbrother/dsh-galatea
Run DSH sessions on the local Claude Code (Opus, Sonnet), with Galatea's memory and tools. Pick an auth mode in the profile (Anthropic API key recommended, or your existing Claude Code login). Requires the Galatea framework.
dsh-nextsteps
klaus-2/dsh-nextsteps
Suggested next-step prompts under every finished agent turn in the DeepSeek Harness chat: the model proposes a few followup prompts at the end of each turn, they render as clickable cards under that turn, and clicking one sends it verbatim as your next message. Each card stays attached to the turn that produced it across reloads and restarts, the generation language can be chosen from 15 languages or follow the conversation, and a settings page in the dsh settings covers the language, how many suggestions per turn, the header and the in-app update check. Requires DeepSeek Harness 0.2.x (web profile) and Node.js 20+.
dsh-kb-sync
xinming-chenniang/dsh-kb-sync
Pulls your chat.deepseek.com conversations into a local knowledge base — one Markdown file per conversation, a JSONL transcript and a catalog — and searches them from a control page inside DSH. Daily increments plus a full-history backfill from the official export, an integrity check, and an optional model step that runs through the host llm service and writes only after its JSON passes validation. Reads the web userToken from the DSH credential store and calls chat.deepseek.com only; no install scripts, no runtime dependencies.
dsh-laci-engine
atlantis-la/dsh-laci-engine
Local model scheduler for DSH on Windows 10/11 with DSH Desktop 0.2.x: a bundled console for engine/model import, VRAM estimation, load/close, and an OpenAI-compatible gateway.
dsh-rag (plugin)
fqh22/dsh-rag
Memoria a lungo termine per progetto DeepSeek Harness: pannello per consultare, cercare e modificare conoscenze, più invito dopo il primo messaggio a leggere il pacchetto di passaggio. Archivio in server MCP locale (Python + SQLite) nello stesso repo. Installa il plugin npm, clona il repo e configura MCP dal README; posizione trovata con DSH_RAG_ROOT o percorsi comuni. Base stabile all'inizio, fatti aggiunti in coda per riutilizzare la cache dei prompt.
dsh-ocg-session-head
verneuil/dsh-ocg-session-head
Inserisce x-opencode-session per conversazione nelle route OpenCode Go registrate con provider personalizzato tramite il waterfall ufficiale llm-pi-ai/request-headers. Nessuna dipendenza o patch di fetch; non sovrascrive mai header già impostati.
dsh-wechat-queue
steelunion/dsh-wechat-queue
Canale WeChat con coda sequenziale persistente: i messaggi vengono prima salvati su disco, si risponde uno alla volta e il lavoro incompleto sopravvive al riavvio.
dsh-system-one-plugin
xunzhuo/dsh-system-one-plugin
System Duo per DeepSeek Harness: pensiero rapido e lento. I modelli System One smistano, sorvegliano, proteggono, mascherano e controllano il ciclo accanto a System Two (vllm-sr/auto), con chiave gratuita app.vllm-sr.ai.
dsh-budget-guard-plugin
existence001100/dsh-budget-guard-plugin
Plugin DSH che impone limiti per attività in CNY o token, con blocco automatico contro costi incontrollati.
stockproof (dsh-plugin)
taoqizhang55-code/stockproof
Strumenti di ricerca azionaria per USA, azioni A cinesi e Hong Kong tramite il server MCP stockproof (Python 3.10+; installa con pip install "stockproof\[mcp,cn]"; i dati A/HK richiedono Python 3.11+). Include notizie, risultati e comunicati con fonti, spiegazioni dei movimenti dei prezzi, screening dell’intero mercato A, laboratorio quantitativo per backtest su dati storici puntuali con holdout bloccato, controllo del portafoglio e dashboard web locale; 23 strumenti.
dsh-local-delegate
mythgreenland/dsh-local-delegate
Delega le attività testuali meccaniche (tradurre, riassumere, estrarre, classificare, riscrivere) a un endpoint nativo Ollama o compatibile OpenAI tramite percorso file, così il testo sorgente non entra nel contesto del modello principale. Registra local_transform, local_batch e local_health. I livelli di IA locale per Workspace (none/light/default/high/max) aggiungono il subagente local_worker e una modalità solo pianificazione. L’opzione SlaveAgentTeams rileva le route dei modelli montate, esegue agent figli in parallelo con failover per nodo e registra la catena di endpoint come route llm-pi-ai. Configurazione dalla Web GUI; serve un endpoint raggiungibile.
dsh-plugin-sessiongraph
cc19990113/dsh-plugin-sessiongraph
Bundle per la funzionalità sessiongraph: installa il pacchetto per aggiungere la ricerca locale nella cronologia delle conversazioni a un profilo DeepSeek Harness.
dsh-fine-tune
songrui111/dsh-fine-tune
Fine-tuning LoRA/QLoRA locale nel pannello: importa JSONL, stima VRAM prima dell'addestramento, valuta ed esporta un adapter. Setup venv Python in un clic, ma servono Python 3.10+ proprio e GPU NVIDIA da almeno 6 GB. Verificato end-to-end su Windows 11 con RTX 3060 6 GB. L'installer rifiuta host non Windows; Linux, macOS e altre GPU non sono supportati per ora.
dsh-llm-minimax
elfgzp/dsh-llm-minimax
Aggiunge i modelli della MiniMax Open Platform al selettore DSH: inserisci la chiave API in Settings per renderli selezionabili; le finestre di quota del piano M appaiono accanto al compositore.