实时扫描最新社区关于 DeepSeek Harness 发布的插件

Application-level Vision-Language-Model (VLM) analyzer for DeepSeek Harness: analyze_image tool with primary/backup OpenAI-compatible endpoints, automatic failover, and an auto-saving web settings page.

Give text-only models eyes: an analyze_image tool for DeepSeek Harness, backed by free Chinese vision APIs (GLM-4V-Flash / Qwen-VL) or any OpenAI-compatible vision endpoint. 给纯文本模型装上眼睛。

Let image-incapable LLM models receive image messages in DeepSeek Harness (dsh): replace image blocks with text placeholders + local paths, then describe via a vision script (qwen)

Image-generation tool plugin for DeepSeek Harness: qwen-image-3.0 (Aliyun MaaS) and doubao-seedream (Volcano Ark) providers

Give DeepSeek Harness agents the ability to read images directly: a model-facing read_image tool that answers questions about an image through any OpenAI-compatible vision endpoint.

image_gen and image_vision model tools for the DeepSeek Harness, powered by the ChatGPT subscription (no API key).

对话内联图片:LLM 回复中输出的本地图片路径直接在消息正文内渲染为图片,支持 9 种格式、点击放大灯箱、可调尺寸

Jina AI tools for DeepSeek Harness: search (incl. arxiv/ssrn academic domains), read, screenshot, embed, rerank, classify, pdf, expand, datetime, primer — with a settings-page API key UI.

Kimi WebBridge for DeepSeek Harness: drive the user's real browser (navigate, click, fill, snapshot, screenshot, evaluate, network, upload, PDF) through the local Kimi WebBridge daemon

KoboldCpp for DeepSeek Harness - a tool plugin that lets the harness online model hand repetitive text and vision (OCR) labor to a local KoboldCpp (llama.cpp) server.

DSH plugin: auto-route to a multimodal model when messages contain images, stay on the cheap model otherwise.

Native macOS OCR and Vision tools for DeepSeek Harness

Free image reading (vision) and image generation skills for DeepSeek Harness — Zhipu GLM-4V-Flash for reading, SiliconFlow Kolors for generation.

MiniMax multimodal capability hub for DeepSeek Harness (DSH). One mmx_multimodal tool covers describe/image/video/speech/music/cover/search/quota; optional web_search takeover; built-in client enhancement renders inline players in the Web GUI.

A session-aware workspace file tree, text and media preview, and Git status panel for DeepSeek Harness.

DeepSeek Harness native plugin: give text-only LLMs (e.g. DeepSeek) vision via free Gemini / GLM vision APIs — describe images, OCR, VQA, screenshots, charts.

Bridge QQ official bot private messages (C2C) into DeepSeek Harness (dsh) agent sessions

Qwen-MM-Plugins integration for DeepSeek Harness: 12 MCP multimodal tools (vision/OCR/grounding/ASR/AV), a Web settings page (paste a Qwen API Key), bundled skills, and a one-command installer.

DSH bundle: Qwen multimodal bridge — vision (qwen3-vl), speech-to-text (qwen3-asr), text-to-image (qwen-image), via the deepseek-vision skill scripts

DSH plugin: free web search tool (DuckDuckGo via ddg-kit with system-proxy support, automatic Bing fallback) + front-loaded vision understanding tool (vision_understand: understand images via a vision-capable model configured in DSH when the conversation model has no image modality) + composer-level paste-image capture (paste/drop an image in the conversation input → vision model → description, bypassing DSH's image gate on text-only models). Official bundle plugin, install: dsh plugin --profile web add github:LingyeSoul/dsh-rider#main。DSH 插件：免费网络搜索（duckduckgo_search 工具）+ 前置视觉理解（vision_understand 工具）+ 对话输入框粘贴图片捕获（粘贴/拖入图片 → 视觉模型 → 描述，绕开 DSH 对纯文本模型的图片拦截）。

Agent-to-user image display for the DeepSeek Harness WebUI: a show_image tool whose results render as an inline image card in the conversation (via embedded presentation data), never entering model history — safe for text-only LLMs.

Customizable skinning tool for the DeepSeek Harness Web UI — presets, image wallpapers, translucency, and accent colors, all persisted in user settings

测试工作台 Profile for DeepSeek Harness — 组装 UI 验证、会话分析、视觉路由为一体的 QA Agent。

DSH plugin: describe_image tool + paste-image-to-text browser half, bridging image understanding to text-only models via DashScope qwen-vl