Skip to content
dsh.fish

Browse

1021 results

Bundle

harness-pet

Harness Pet is an unofficial community project. Not affiliated with, endorsed by, or maintained by DeepSeek. A tiny whale for DeepSeek Harness.

cakeni5
Bundle

@superfish058/dsh-llm-proxy

DSH 模型代理插件：按模型走代理（Clash 等）+ 失败自动重试，设置页实时生效。

superfish0585
Bundle

dsh-notify-on-complete

Desktop notifications for DeepSeek Harness (dsh): run completion, model questions, and approval requests. Zero runtime dependencies — all peers provided by the dsh CLI.

pitetow5
Bundle

dsh-agent-arena

Interactive multi-agent council and prompt arena for DeepSeek Harness

Tikzen5
Bundle

dsh-notion-mcp

Connect DeepSeek Harness (dsh) to Notion via the official Notion MCP (OAuth + PKCE)

mingzeng215
Bundle

@f1star/dsh-research

A DeepSeek Harness research workspace with archived PDF reading, optional OCR, human review, cited reports, and recoverable research tasks.

F1star5
Bundle

dsh-mcp-bridge

Curated, verified MCP server bundle for DeepSeek Harness (dsh): one install brings demo, memory, filesystem, GitHub, Playwright and remote HTTP MCP servers, with a connectivity verifier and CI checks.

Edge-Echo5
Bundle

dsh-plugin-proxy

Global proxy for DeepSeek Harness: route agent tools, model requests and web fetches through the Windows system proxy or a custom proxy with one persistent toggle, an editable settings card, agent-visible status and a bypass-aware prompt section

LucienLL5
Bundle

dsh-plugin-omoslim

DeepSeek Harness bundle: oh-my-opencode-slim style Orchestrator agent preset with model-pinned specialist subagents (explorer/oracle/librarian/designer/fixer/council).

tevenfeng5
Bundle

@fakechris/dsh-track

Track Bridge: embedded task-management engine for DeepSeek Harness — decision-point protocol, capture wall, and Linear-shaped issue store over session events + storage KV

fakechris45
Bundle

dph-endfield-theme

Unofficial industrial Endfield-inspired theme bundle for DeepSeek Harness Web.

thjyy4
Bundle

dsh-thinking-levels-settings

Persistent per-model thinking-level settings for custom DSH providers (official dsh client-plugin form)

blackteaYES4
Bundle

dsh-yogacara

A Yogācāra (唯识) self-model plugin for DeepSeek Harness — eight consciousnesses, the 51 mental factors, a perfumed seed store, and a measurable self-grasping meter, rendered back to the agent as first-person state.

tancheng334
Bundle

@xmoon76/dsh-subagent-router

DSH model-facing delegation tool that routes continuable/one-shot subagents to a model-selected LLM provider and model

XMoon4
Bundle

dsh-ds-attach

chat.deepseek.com-style attachments for DeepSeek Harness: official upload icon, DS-style file cards (240x64, 16px radius), drag-drop, text extraction (PDF/DOCX/XLSX/TXT) injected into the message

wqx-txdsyl4
Bundle

dsh-client-ui-aqua-unofficial

Aqua: a highly customizable glassmorphism theme for the DeepSeek Harness Web UI — blur, frost, fluid or video wallpaper, unified corners, and motion. Unofficial community fork, not affiliated with DeepSeek.

afrel10244
Bundle

dsh-adaptive-context

Adaptive Context Plane core bundle: Evidence Ledger + Governance + Context Composer + User Model (explicit)

Icstick4
Bundle

dsh-annotation

Inline annotations for DeepSeek Harness Session messages, submitted through the official composer

ruisenbai4
Bundle

dsh-live2d-pet

Live2D companion for DeepSeek Harness: render a Cubism model (e.g. the official Haru sample) in the web UI with state-driven expressions and mouse tracking. · DSH 桌宠的 Live2D 渲染插件

ankesu4
Bundle

dsh-gauge

Accurate cache-hit rate, token usage, and cost estimates for the DeepSeek Harness Web UI: one-decimal hit rate, bucket breakdown, peak/off-peak pricing with auto price-switch, and a session usage panel.

noone89A4
Bundle

@mimichunterz/agent-compact

Context compression tool (context_compact): the agent writes the replacement checkpoint itself and hands it to the host compaction engine, which skips the LLM summarizer call; automatic compaction stays on the official engine.

MimicHunterZ4
Bundle

dsh-auto-evolve

Self-evolving plugin for DeepSeek Harness: observes agent behavior, proposes improvements to its own skills/policies via LLM, validates them in a sandboxed trial agent, and applies versioned mutations with rollback.

lispking4