Plugins

Media and vision workspace for DeepSeek Harness: image, video and speech generation, image Q&A and element locating, long-image OCR, pixel diff, HTML-screenshot verification and video summarization, with DashScope and OpenAI-compatible providers, model pools and a workbench client.

A vision-language gateway provider route: pasted images are described by a configurable VL model (Qwen-VL by default) before the DeepSeek wire.

Vision for text-only DeepSeek via Doubao Web by default (zero-cost, no API key — drives your logged-in Chrome through a Windows CDP bridge), with Antigravity IDE quota (flash/pro) or Gemini fallback; auto detail escalation, vision evidence memory with compaction rehydration, content-hash cache, and a bilingual client panel.

Multi-account Google Gemini provider: picks the account with the most remaining quota, fails over on 429 with exponential cooldown, probes disabled accounts in the background, and ships a Chinese/English settings page.

Let text-only models see images: when a picture arrives with a placeholder like \[image omitted because this model accepts text only], the model calls the vision_describe tool and the plugin forwards the image reference plus the question to a multimodal model, retrying with a fallback model on failure. Configured in the settings page and persisted via the official settings API.

Controls the Chrome you are already logged into: the model clicks, types, fills in forms, reads pages, takes screenshots and downloads files in your real tabs, including inside same-origin iframes. Runs on macOS, Windows and Linux; needs Chrome 116+ and Node 18+. Works over native messaging and chrome.debugger instead of a listening port. Ships 12 browser_* tools and a cb CLI, dispatches real CDP input events, draws an on-page cursor that also appears in screenshots, and adds a toolbar panel with live status, the controlled tabs and a pause switch. browser_download saves a link, an element's target or a URL with the site's login cookies (following redirects, keeping the server's file name) to the Downloads folder or the session's working directory; cross-origin iframes are named in the snapshot but not entered. The native host and the MV3 extension travel inside this tarball: on first load the plugin copies them into place and writes the native-messaging registration itself, so there is no clone, no install.sh and no python3 - the one step left is adding the extension to Chrome: install DSH Bridge from the Chrome Web Store (https://chromewebstore.google.com/detail/bippcbbbipppmhjkjomgdnjbooecbimo, no Developer mode), or load the bundled unpacked copy at chrome://extensions (the plugin opens that page and puts the folder on the clipboard for you). Until then the tools fail loudly with those steps. On Windows the registration goes into the registry (for Chrome and Edge) and the host talks over a named pipe. A daily CI run on GitHub's macOS, Windows and Linux machines installs the plugin, loads the extension into a real Chrome and reads a page through the browser_* tools.

Omni-modal workstation for DSH: analyze_image over an ordered multi-card VLM failover chain, a six-tool vision toolkit (zoom, colour sampling, pixel diff, OCR, element detection, inline display) sharing the same image resolver, generate_image over OpenAI/DashScope/ComfyUI protocols, multi-card async generate_video with a /build-video-tool builder, and speak/clone_voice TTS over seven providers, all driven by one auto-saving settings page.

On-demand vision for text-only DSH sessions: images become markers, and a vision_describe tool sends only image + question to an OpenAI-compatible vision model

Digimon-style raising game: hatch an egg that feeds on real work (turns, tool calls, errors) and evolves along four branching lines shaped by how you work; zero tokens, invisible to the model.

MiniMax-powered multimodal plugin: real-time voice call mode (streaming conversation, floating dock UI), voice mode and mic voice input, plus image/video/music/speech generation and vision inspection tools.

Drag-and-drop / paste / upload files and images; on non-multimodal models images are auto-described by a configured VLM.

LLM adapter plugin for locally deployed Qwen models behind a vLLM OpenAI-compatible endpoint, with per-model multimodal switch, fully configurable reasoning efforts, and a web settings page for editing the deployment from the frontend.

Adds an input-modality selector to custom model settings in the DeepSeek Harness Web UI.

DeepSeek Harness 原生视觉 Bundle：粘贴或拖入图片，通过托管的 deepseek-vision-mcp 调用 OpenAI 兼容视觉模型。

Renders pasted/uploaded images inline in the DSH Web chat and gives text-only models vision: the model-invokable visual_review tool calls any OpenAI-compatible multimodal API first, falling back to a local Qwen3-VL worker.

Vision MCP and DSH bundle for text-only DeepSeek: analyze_image, analyze_clipboard, compare_images and vision_status tools, a visual settings page, free GLM-4.6V-Flash by default, result caching and rate-limit tolerance; keys stay out of logs.

DeepEye vision plugin for DeepSeek Harness (DSH): image description, OCR, VQA, UI layout, and clipboard analysis.

一个可以让ai自动调用VLM(多模态模型)进行视觉分析的dsh插件。A dsh plugin that allows AI to automatically invoke VLMs (multimodal models) for visual analysis.

Unofficial fork of dougen/dsh-deepseek-usage (baseline v0.16.0): sidebar balance and quota card for the active model provider, covering DeepSeek, Moonshot, Z.ai, OpenRouter, Kimi, MiniMax and OpenCode, plus Alibaba Cloud voucher balance for qwen-token-plan (BSS OpenAPI with AccessKey) and Xiaomi MiMo console balance with token-plan usage (console cookie). Ships a provider query-status page and per-token unit prices. Do not install it alongside upstream dsh-deepseek-usage: both render the same sidebar card.

All-media (video/audio/image) sibling of liustack/modlens: turns local media into structured evidence (timeline / transcript / layout regions) injected into the conversation so text-only models can cite concrete frames, seconds and speakers — Evidence, not imagination. One failover chain per media, recorded hop-by-hop in meta.attempts (a fallback is never silent): host-registered multimodal models first, then a configured OpenAI-compatible endpoint (comma-separated multi-key rotation), then local ffmpeg frame-sampling / a local ASR CLI, degrading to metadata-only as a last resort. Absorbs modlens battle-tested rules — cooldown keyed only on auth/quota failures and softened to chain-tail (never dropped), redact-before-clip error text, magic-byte sniff that never trusts file extensions. Optional vision-bridge registers a media-lens wrapper into the host model selector so a pure-text model gains image/audio/video sight. Registering / authenticating multimodal models and true inline audio-video upload lean on two companion plugins, declared as optional peers (absence auto-degrades, never errors): dsh-thinking-levels fronts the model config / registration surface, dsh-llm-openai-completions takes over the OpenAI-compatible transport that serializes file blocks into video_url / input_audio. Privacy: media goes to remote providers by default; strictLocalOnly keeps content on-machine. Prerequisites not shipped with the package: ffmpeg/ffprobe on PATH (frame sampling / reencode / duration probe; degrades to metadata when missing) and a user-configured local ASR CLI for the audio fallback. Hosts 0.1.7 / 0.2.0 / 0.2.1 (6 rc, exact engines.dsh enum). npm: dsh-media-lens.

Multi-provider quota & balance glass card for the DSH sidebar footer (11 providers incl. StepFun / Xiaomi MiMo / Claude with one-click browser login; Step Plan credit). Installable from the dsh-plugin marketplace (GitHub topic "dsh-plugin") or via file: l

Unofficial FreeCodeGo for DeepSeek Harness: DeepSeek, Codex and Claude engines over one session and toolchain, with a 0-token free access channel for deepseek-v4.1-flash, deepseek-v4-pro, deepseek-v4-flash-free, glm-5.3-flash, grok-4.6, kimi-k3, nemotron-3-ultra-free, muse-spark-1.3, Qwen 3.8 Flash and mimo-v2.6-flash-free, plus a keyless private-key gateway.

Competition math (IMO/Putnam/USAMO/AIME) solved with a pure-reasoning pass, an adversarial verifier in a fresh subagent context, and calibrated confidence output (high / medium / honest "no confident solution"); optional LaTeX-to-PDF rendering.

Analyzes conversation images through mode-specific prompts (caption, UI, document, grounding, topology, etc.) and injects structured evidence with coordinate primitives (boxes, points, refs) as text, with session-level caching for reuse across replay and compaction.