Plugins
Browse, filter, and install DeepSeek-Harness plugins.
2504 plugins found
dsh-sseye
jhuanxx44/dsh-sseye
LLM debug console for DeepSeek Harness: captures the full content of every model call at the llm/stream waterfall (options, stream chunks, usage, wire protocol) and shows it in a DevTools-style docked panel, with shared-prefix context diffing, wire-JSON reconstruction, JSON export and a runtime-tunable capture policy.
dsh-draft-polish
max-null/dsh-draft-polish
Draft polish for the DSH composer: one-click AI polish of the input draft (sparkles button next to send), with optional conversation context and a configurable model channel.
dsh-voice-input-cn
schumchanvi/dsh-voice-input-cn
China-ready voice input for the composer. Requires a local Python bridge (pip install dashscope websockets, run bridge/voice-bridge.py) — the plugin alone does not work. Browser mic streams 16 kHz PCM to the bridge, which runs Alibaba Cloud DashScope ASR (paraformer-realtime-v2); interim text fills the draft at the cursor, silence auto-stop, optional auto-send.
dsh-project-context
buhuikongpan/dsh-project-context
Turns each DSH workspace into a project: every new session auto-injects a project-workspace convention (read code before acting, empty folder means a brand-new project); a per-session Project toggle in the composer downgrades the session to a plain workspace with an explicit notice, with the state kept in the session log.
dsh-message-outline
chongfengdy-dev/dsh-message-outline
Current-session message outline rail for the DSH web UI — your messages show as slim bars on the left edge; hover to expand the full outline (line number + text), click to jump instantly to that message. Pure frontend, zero external service dependencies, sessions-snapshot driven with zero polling.
pdf-background-gray-codex-skill (dsh-pdf-background-gray)
zjsthmjialin/pdf-background-gray-codex-skill
Registers the remove-pdf-background-gray skill for DSH: whitens gray/off-white scan backgrounds in image-based PDFs while preserving resolution, page geometry, and anti-aliased text edges (lossless Flate write-back), via a single Python script (pypdf + Pillow + numpy).
DSH-dseyes
okkay712/dsh-dseyes
Native image attachments for text-only DeepSeek in the Web GUI: pasted or dropped images appear as thumbnails in the session, and before dispatch the host reads them with the free Zhipu GLM-4V-Flash vision API (glm-4v-flash fallback chain) and substitutes the description, so DeepSeek answers about the image while the original is kept in history.
dsh-quick-toc
lyaxz/dsh-quick-toc
Conversation outline for DeepSeek Harness: the Markdown headings of the whole session, grouped by turn, in a side panel or a full-width curtain; hover previews can be pinned for comparison, bookmarks keep the places you come back to, and a right-click jumps to a section or copies a heading and the levels below it. Six theme colours and a translucent material, title/prompt/full-text/cross-session search, reading-position follow and a Chinese/English interface.
dsh-capability-index
777-zen/dsh-capability-index
Pre-flight plugin-library index for DSH agents: injects per-step trigger-table hints into the runtime context so suitable installed plugins get used predictably instead of opportunistically.
wallpaper-engine-dsh
weilv-d/wallpaper-engine-dsh
Transforms the local Wallpaper Engine library into a live background for DSH, with video and web wallpapers playing for real. An adaptive veil adjusts with picture brightness to keep text readable, while floating surfaces render as liquid glass. Includes a bilingual settings panel featuring framing adjustments, playlist rotation, library search, and real-time resource monitoring. Scene and application wallpapers are not supported.
dsh-tool-generate-image
zcldragon/dsh-tool-generate-image
Model-facing `generate_image` tool for text-only models: the model asks for a picture in natural language, Gemini draws it via the Antigravity CLI, the image is saved to a configurable output directory, and the tool returns the file paths for the model to use in its work.
dsh-codex-migrate
polarskicpl/dsh-codex-migrate
Migrate Codex CLI conversations, MCP servers, memories and project files into DeepSeek Harness sessions, workspaces and MCP registrations. 把 Codex CLI 的对话、MCP、记忆与项目文件迁移为 DSH 会话、工作区与 MCP 注册。
deepseek-harness-forge-plugins (evidence-first)
jinguanghai/deepseek-harness-forge-plugins
Evidence-first guard: warns the agent when it claims success without a matching tool-execution record in recent context.
dsh-fish-tts
mari23333/dsh-fish-tts
Reads assistant replies aloud via Fish Audio API only (bring your own key): per-message read-aloud, auto-read toggle, and a settings page for model, voice reference_id, encrypted API key, and proxy.
dsh-image-vision
xsoc1/dsh-image-vision
Chat image-attachment bridge with a `view_image` tool for any OpenAI-compatible VLM (local Ollama or cloud): pasted/dropped images become `view_image` path markers before reaching text-only DeepSeek models.
dsh-vision-recognizer
kaixinbaba/dsh-vision-recognizer
Vision provider route that transcribes attached images to text through a configurable model (15+ OpenAI-compatible and Anthropic vendors) while DeepSeek keeps answering.
dsh-open-eyes
hyp6666/dsh-open-eyes
Vision bridge for text-only DeepSeek routes that analyzes attached and local images through configurable OpenAI Responses, Chat Completions, or Anthropic Messages endpoints while leaving image-capable routes native.
dsh-deepseek-vision
cheng-cheng9669/dsh-deepseek-vision
Reuses DeepSeek web's built-in vision mode for text-only models: the deepseek_vision tool drives the local deepseek-vision-cli browser automation (manual login helper, deep-think enabled, auto-closes browser) and returns image descriptions as text.
dsh-youreyes
54xkeee/dsh-youreyes
Vision toolkit for text-only DeepSeek: model-invokable `vision` tool, wrapper adapters for deepseek/opencode-go (v4 flash/pro), Antigravity IDE quota (default, flash/pro) / any OpenAI-compatible VLM / Gemini / local Ollama channels, evidence memory with compaction rehydration, content-hash cache, and a bilingual client panel.
dsh-vision (vision-route)
314857493/dsh-vision
Registers a `deepseek-vision` provider route: the Web GUI accepts pasted images and transcribes them to text via the free Zhipu GLM vision API before delegating to the DeepSeek adapter.
dsh-funnel
yuanyuanma03/dsh-funnel
Ingestion-time tool-output curation: keeps error and warning lines plus head and tail, spills the full text to disk with a pointer the model can read back; covers every text tool, small results pass through untouched.
dsh-memory-protocol
baaai123/dsh-memory-protocol
Memory protocol enforcement plugin: bridges the opencode-memory MCP server, forces memory_weave before tool calls, auto-ingests turns, and injects memory context into agent steps.
dsh-codex-meter
chriszhangwg/dsh-codex-meter
Adds a Settings Usage dashboard for DeepSeek API balance, official token and cost analysis, trends, context warnings, and live API activity.
dsh-file-mount
acefun29/dsh-file-mount
Incremental file mounting with read dedupe: mounted line ranges are never re-sent to the model, on-disk changes invalidate and remount, with a Mounted Files tab and token-savings accounting.