Vai al contenuto principale

Plugin

Sfoglia, filtra e installa i plugin di DeepSeek-Harness.

1219 plugin trovati

L

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.

110 giorni faStrumenti e capacitàMIT
R

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facts from sessions, injects the most relevant ones before each turn using local SQLite FTS5 search, and supersedes outdated facts.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.

1l’altro ieriMemoriaMIT
2

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.

13 giorni faSessioni e messaggiMIT
M

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.

110 giorni faModelli e providerMIT
J

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.

13 giorni faSviluppo e strumenti per pluginMIT
C

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.

19 giorni faMemoriaMIT
L

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.

112 giorni faIntegrazioni e accesso remotoMIT
N

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.

13 mesi faStrumenti e capacitàMIT
L

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.

112 giorni faMemoriaMIT
Q

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).

17 giorni faModelli e providerApache-2.0
L

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.

112 giorni faModelli e providerMIT
K

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+.

114 ore faMiglioramenti UIMIT
X

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.

114 giorni faSessioni e messaggiMIT
A

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.

115 giorni faModelli e providerMIT
F

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.

111 giorni faMemoriaMIT
V

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.

1l’altro ieriModelli e providerMIT
S

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.

126 giorni faIntegrazioni e accesso remoto
X

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.

116 giorni faSicurezza e permessiApache-2.0
E

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.

19 giorni faSicurezza e permessiMIT
T

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.

117 giorni faStrumenti e capacitàMIT
M

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.

116 giorni faUtilizzo e fatturazioneMIT
C

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.

117 giorni faSessioni e messaggiMIT
S

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.

111 giorni faModelli e providerMIT
E

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.

116 giorni faModelli e providerMIT