DSH插件商店

dsh-context-mode

pharaohnie

DSH 原生 Cordis 插件：知识库(FTS5)、路由强制、会话记忆、沙箱执行(Think-in-Code)——context-window 减负

dsh-plugin-voice-input

porcelaintech

Voice input plugin for DeepSeek Harness: a minimal mic control in the composer with continuous bilingual recognition, context-aware term correction, punctuation, and a live waveform

dsh-auto-paste

sakuraqqq

A DeepSeek Harness plugin that auto-saves large pasted text as attachment files

dsh-plugin-multimodal

shinjiyu

Vision sidecar for DeepSeek Harness: accept pasted images on text-only models.

DeepSeek-harness-lark

sliverp

Feishu and Lark text and image channel plugin for DeepSeek Harness

dsh-session-handoff

snow-The

Session handoff & context management for DeepSeek Harness: structured handoff docs (export/resume/status) + active context pruning (acp_* via official compaction API) + optional OpenViking/archify enhancers

dsh-search-enhance

umineko987

提供 Grok-compatible 网页搜索、保留来源分页、Context7 与 Exa 文档检索、有界网页提取、站点映射、离线研究计划和只读诊断。

dsh-hold-to-talk

wangzhanchao883

Hold-to-talk voice input for the DeepSeek Harness web composer: hold the mouse on the input box, speak, release to insert the text into the draft. Local SenseVoice ASR via sherpa-onnx: no API key, offline, audio never leaves the machine. | DSH 长按说话语音输入插件:输入框上按住鼠标说话,浮层边说边出字,松手把文字写进输入框,上滑取消;识别在本机跑,免密钥、离线、音频不出本机。

dsh-ds-attach

wqx-txdsyl

chat.deepseek.com-style attachments for DeepSeek Harness: paperclip upload, DS-style file cards, drag-drop, text extraction (PDF/DOCX/XLSX/TXT), attachment cards in transcript

dsh-magic-context

xiaohj233

Magic Context — community port to DeepSeek Harness (DSH). Shared SQLite memory across harnesses, harness='dsh' row isolation.

dsh-vision-imagen

xuxun-oss

DeepSeek Harness all-in-one: no model switching — regular DeepSeek auto-routes to vision & image gen. Multi-backend: Gemini + any OpenAI-compatible (GPT-4o, Qwen-VL, GLM-4V, gpt-image, DALL-E, Flux, OpenRouter). gemini_vision/gemini_generate_image/gemini_optimize_image with vision self-check. Better than modlens.

dsh-file-panel

yu2025-luo

Right-side file panel for DeepSeek Harness — auto-popup when the agent creates or downloads files, with image/text preview, reveal-in-folder and open actions. Bilingual · MIT

dsh-multi-selection-comments

yuanc1204

Codex-style multiple independent selection comments for DeepSeek Harness (DSH).

dsh-song-ui

yunfei07

The light palette combines silk-paper surfaces, warm ink text, Ru-celadon interactions, and cinnabar error states. The dark palette uses night-ink surfaces with a brighter celadon accent. Display headings prefer installed Song and CJK serif fonts; body text keeps the Harness sans-serif stack.

dsh-comfyui

zeroa234

ComfyUI 驱动器（AI-first 合同制）：模型只见合同槽、不见工作流 JSON。文生图/图生图/文生视频/图生视频模板，双重预检防幻觉，官方/自定义节点活体判定。

dsh-context-provenance

030611

Observe-only provenance ledger over public DeepSeek Harness runtime evidence

dsh-context-lens

1014029855

Inspect, measure, search, and compare the exact provider-neutral context assembled by DeepSeek Harness.

dsh-memory-toolkit

123caiji

Memory and token-optimization plugin toolkit for DeepSeek Harness: cross-session knowledge graph memory + five-layer token-saving orchestration.

dsh-plugin-nlbi

1byteone

该仓库暂未提供项目说明。

dsh-vision

314857493

Free GLM vision for text-only DeepSeek Harness: paste images in the GUI (auto-transcribe route) + vision tool + skill

dsh-deepseek-vision

Argonaut790

Image understanding, OCR, and persistent visual evidence for text-only DeepSeek Harness models

session-reader-plugin

Artificialwhale

Allow agent to acquire context from other sessions.

dsh-cyber-pet

BorisShaw6

A “Cyber Whale” pet designed for DeepSeek Harness: a whale that hovers on the web page, can be fed, and changes color, providing real-time updates on token usage, limits, context usage, interaction counts, and the number of dialog boxes—complete with three built-in chat backends, growth levels, an emotion system, and milestone celebration features.

deepseek-harness-voice-context

CharlesLiuZC

DeepSeek Harness with Voice Context speech-to-text integration