xby-pic: DeepSeek Harness Image Toolkit
xby-pic is an image processing toolkit plugin for DeepSeek Harness. It requires no local deployment and provides various visual capabilities through external API calls. The plugin supports configuring an API key and integrates multiple interfaces, including OCR, ID document recognition, object detection, and biological scene recognition, covering text, license plates, bank cards, various identity documents, and everyday items. Before installation, users should review the source code and configure the API key. It accepts image URLs, BASE64-encoded data, or file paths as input, aiming to provide developers with convenient visual integration capabilities.
Read Moredsh-browser-vision: DeepSeek Harness Browser Vision Plugin
`dsh-browser-vision` is a browser vision plugin for DeepSeek Harness, designed to address visual elements that cannot be captured by DOM parsing. It drives a real Chrome browser through CDP and uses a vision model to read Canvas text, charts, and rendered content. The plugin supports page driving, schema-based structured JSON extraction, Markdown output, and cost tracking. Installation requires configuring the Python engine, environment variables, and Chrome, and it provides tools such as `browser_vision_task` and `browser_vision_extract`. When using it, be mindful of the Python version requirements and screenshot parameter settings to help agents process complex visual information more effectively.
Read MoreAura Vision: A Free Vision Recognition Plugin for DeepSeek Harness
`aura-vision` is a free visual recognition plugin specifically designed for the `web` profile of DeepSeek Harness, addressing the issues of long-document recognition being truncated due to token limits and the lack of unified management tools. It supports multi-channel visual recognition through APIs such as Zhipu GLM-4V-Flash, and features adaptive grid segmentation for long documents, multi-format export to Markdown, Word, Excel, and PNG, as well as history management. Built with the Aura UI design, it requires a restart after installation to take effect, stores data locally, and emphasizes privacy and security.
Read MoreDeepSeek Harness Plugin: dsh-siliconflow-vision (Visual Recognition via SiliconFlow)
The DeepSeek Harness plugin `dsh-siliconflow-vision` is designed to add visual analysis capabilities to the DSH system. By calling SiliconFlow’s vision large models (using Qwen3-VL by default), the plugin supports recognizing local files, URLs, and Base64 images, and allows custom identification instructions. Users need to configure an API Key, after which image content can be analyzed directly in conversations once the plugin is installed.
Read Moredsh-vision: A Plugin for Providing Vision Capabilities to DeepSeek Harness
dsh-vision is a vision plugin for DeepSeek Harness, designed to address the limitations of text-based models in image processing. By taking over the input stream, it supports image recognition and generation, with a multi-engine failover mechanism. Users can install it via the command line and use engines such as Codex and Gemini to read local images or generate images, with an interface that supports preview and download. The plugin follows strict temporary storage principles and offers flexible configuration options to manage credentials, engine parameters, and file retention policies, empowering agents with robust visual interaction capabilities.
Read Moredsh-vision: Adding Visual Recognition Capabilities to the DeepSeek Harness Text Model
`sjakdhasdh/dsh-vision` is an open-source plugin that adds visual recognition capabilities to DeepSeek Harness (DSH). It calls vision large models via an OpenAI-compatible format, defaults to Alibaba Cloud Bailian’s `qwen3.7-flash`, and supports image input from local paths and remote URLs. The plugin has zero dependencies and can be installed via a command or configured through environment variables/a profile. When using it, provide an image path and a recognition prompt. The project is open-sourced under the MIT License and aims to address the issue that DSH’s default model does not support images.
Read Moredsh-eyes: Attaching external "eyes" to DeepSeek Harness pure text chat
# Preface The philosophy behind DeepSeek Harness (hereinafter referred to as DSH) is "everything is a plugin," but its web chat interface is text-based: pasting a screenshot of an error or dragging in a design draft means the model cannot see them; you can only describe them in text or use other tools to perform OCR before copying the results back into the conversation. For agent developers, such operations are frequent and interrupt the workflow each time. qing9835's open-source plugin, dsh-eyes, addresses this problem: images pasted, dragged in, or imported are intercepted by the plugin, passed to OpenAI-compatible vision models for recognition as text, and automatically sent into the conversation. # What is dsh-eyes (package name dsh-vision-bridge) is a DSH web...
Read Moredsh-vision: Enabling text models to process image requests in DSH
dsh-vision is a DSH plugin designed to address the issue where text-based models like DeepSeek V4 Flash/Pro cannot process images directly. When a request contains an image and the target model does not support visual input, the plugin automatically invokes a vision model or system OCR to describe the image, then replaces the image block within the provider call with a text description to ensure the model can continue processing the context. Original images are retained in session logs and the UI interface. The plugin offers two modes: Auto and Specified Model. In Auto mode, it attempts declared vision-capable models sequentially; if that fails, it falls back to system OCR (Vision on macOS, Media.Ocr on Windows, and Tesseract on other platforms). In Specified mode, it uses only the configured model and does not retry on failure.
Read Moredsh-image-reader: Image reading tool providing read_image for DeepSeek Harness Agents
`dsh-image-reader` is an MIT-licensed DeepSeek Harness plugin designed to provide image reading capabilities to text-only agents. By exposing the `read_image` tool, this plugin enables agents to utilize arbitrary OpenAI-compatible vision endpoints to parse screenshots, charts, or photos within the workspace and answer questions based on the image content. Key features include: support for inputting image paths and optional query questions; flexible configuration covering `baseUrl`, `model`, timeout settings, and allowed directories; and robust security mechanisms, such as dynamically reading API keys from environment variables, resolving paths via `realpath` to prevent symlink bypasses, and performing size and extension checks prior to upload. Usage.
Read Moredsh-xiapan-media: Adding Vision, Image Generation, and Video Generation to DeepSeek Harness
`dsh-xiapan-media` is a client plugin for DeepSeek Harness (DSH), designed to integrate visual understanding, image generation, and video generation capabilities into existing text conversations by connecting to the Xiapan cloud service. Maintained by `dongsheng123132` under the MIT license, the plugin requires Node.js >=22.19.0. Its core features include: leveraging the `xiapan-vision` route for image understanding and OCR, supporting direct image paste with backend translation into text; performing image generation and modification via the `gpt-image-2` model; and calling the Seedance service to generate 5-15 second videos. The plugin supports standalone installation via `cordis.patch.yml` or
Read More