Plugins
Durchsuche, filtere und installiere DeepSeek-Harness-Plugins.
1219 Plugins gefunden
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facts from sessions, injects the most relevant ones before each turn using local SQLite FTS5 search, and supersedes outdated facts.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
Projektbezogenes Langzeitgedächtnis für DeepSeek Harness: Panel zum Durchsuchen, Suchen und Bearbeiten des Wissens; nach der ersten Nutzernachricht Hinweis auf das Übergabepaket. Speicher ist ein lokaler MCP-Server (Python + SQLite) im selben Repository. Plugin per npm installieren, Repository klonen und MCP laut README einrichten; Erkennung über DSH_RAG_ROOT oder übliche Pfade. Stabile Basis zuerst, neue Fakten hinten für Prompt-Cache-Wiederverwendung.
dsh-ocg-session-head
verneuil/dsh-ocg-session-head
Fügt über den offiziellen llm-pi-ai/request-headers-Waterfall gesprächsspezifische x-opencode-session-Header für OpenCode-Go-Routen unter eigenen Anbieternamen ein. Keine Abhängigkeiten, kein fetch-Patching; bestehende Header werden nie überschrieben.
dsh-wechat-queue
steelunion/dsh-wechat-queue
WeChat-Kanal mit dauerhafter serieller Warteschlange: Nachrichten landen zuerst auf der Festplatte, Antworten erfolgen einzeln und offene Aufgaben bleiben nach einem Neustart erhalten.
dsh-system-one-plugin
xunzhuo/dsh-system-one-plugin
System Duo für DeepSeek Harness: schnelles und langsames Denken. System-One-Entscheidungsmodelle sortieren, überwachen, schützen, maskieren und prüfen die Schleife neben System Two (vllm-sr/auto), mit kostenlosem app.vllm-sr.ai-Schlüssel.
dsh-budget-guard-plugin
existence001100/dsh-budget-guard-plugin
DSH-Plugin mit verbindlichen Aufgabenlimits in CNY oder Tokens und automatischer Sperre gegen ausufernde Agentenkosten.
stockproof (dsh-plugin)
taoqizhang55-code/stockproof
Aktienanalyse für US-Werte, chinesische A-Aktien und Hongkong über den stockproof-MCP-Server (Python 3.10+; Installation mit pip install "stockproof\[mcp,cn]"; A-/HK-Daten benötigen Python 3.11+). Mit quellenbasierten Nachrichten, Ergebnissen und Meldungen, Erklärungen für Kursbewegungen, A-Aktien-Gesamtmarktsuche, Quant-Labor für Backtests mit zeitpunktbezogener Historie und gesperrtem Holdout, Portfolio-Check und lokalem Web-Dashboard; 23 Tools.
dsh-local-delegate
mythgreenland/dsh-local-delegate
Lagert mechanische Textaufgaben (Übersetzen, Zusammenfassen, Extrahieren, Klassifizieren, Umschreiben) über Dateipfade an einen Ollama-nativen oder OpenAI-kompatiblen Endpunkt aus, damit der Quelltext nicht in den Kontext des Hauptmodells gelangt. Registriert local_transform, local_batch und local_health. Workspace-spezifische lokale KI-Stufen (none/light/default/high/max) ergänzen den Subagenten local_worker und einen Nur-Planungsmodus. Der optionale Schalter SlaveAgentTeams erkennt eingebundene Modellrouten, startet parallele Kindagenten mit Failover je Knoten und registriert die Endpunktkette als llm-pi-ai-Routen. Einrichtung über die Web GUI; ein erreichbarer Endpunkt ist erforderlich.
dsh-plugin-sessiongraph
cc19990113/dsh-plugin-sessiongraph
Bundle für die sessiongraph-Funktion: Installiert dieses Paket, um einem DeepSeek-Harness-Profil die lokale Suche im Gesprächsverlauf hinzuzufügen.
dsh-fine-tune
songrui111/dsh-fine-tune
Lokales LoRA-/QLoRA-Finetuning im Panel: JSONL importieren, VRAM-Schätzung vor Trainingsstart ansehen, evaluieren und Adapter exportieren. Python-venv-Einrichtung per Klick; eigenes Python 3.10+ und NVIDIA-GPU mit mindestens 6 GB nötig. Ende-zu-Ende unter Windows 11 mit RTX 3060 6 GB geprüft. Installer verweigert Nicht-Windows-Hosts; Linux, macOS und andere GPUs werden derzeit nicht unterstützt.
dsh-llm-minimax
elfgzp/dsh-llm-minimax
Fügt Modelle der MiniMax Open Platform zur DSH-Modellauswahl hinzu: API-Schlüssel in Settings einfügen, dann sind MiniMax-Modelle auswählbar; die M-Plan-Quotenzeiträume erscheinen neben dem Eingabefeld.