xby-head-person-detection: Head and Person Detection
xby-head-person-detection is a DeepSeek Harness (DSH) plugin maintained by xby-skill for detecting heads or human bodies in images. It must be installed via the official command-line interface. Before use, users need to obtain and configure an API key from the xiaobenyang official website. The plugin provides four core features, including API key setup and three detection modes, supporting image URLs, Base64 encoding, or local file paths. It is released under the MIT license.
Read More@qizhen2021/dsh-plugin-vision: A Vision Analysis Tool for DeepSeek Harness
DeepSeek Harness (DSH) enables text-only models to gain visual processing capabilities through the plugin `@qizhen2021/dsh-plugin-vision`. The plugin registers a `see` tool that provides three analysis channels: offline OCR (supporting macOS language detection), ASCII layout maps, and semantic descriptions (based on the `mimo-v2.5` model). Installation requires modifying `package.json` via Profile Bundles and configuring parameters such as the key path and timeout in `cordis.patch.yml`. When invoking the `see` tool, parameters can be specified to select the processing channel, and a structured JSON report is returned. Note that OCR is limited to macOS, large images require preprocessing, and the plugin's first
Read MoreDeepSeek Harness Vision Plugin: dsh-vision
The DeepSeek Harness plugin `dsh-vision`, maintained by community developers, is designed to add visual analysis capabilities to DSH. By providing the `vision_analyze` tool, it supports integration with OpenAI-compatible vision models to describe and analyze images from local files or web URLs. Installation requires the `dsh plugin` command and configuration of an API key or local endpoint (such as Ollama). The tool primarily includes the `image` and `question` parameters, while supporting custom models and timeout settings. The plugin relies on external services, has a lightweight structure, and enables developers to integrate image understanding directly into DSH workflows.
Read Moredsh-luminance: A Relative Luminance Calculation Tool
`dsh-luminance` is a lightweight plugin for DeepSeek Harness (DSH) designed to calculate image relative luminance without network dependencies. Implemented in pure Node, it handles local visual analysis tasks without requiring additional network requests. Developers can install it with the specified command and invoke the relevant tools directly in a session. Because it runs with the current process permissions, reviewing the source code before installation is recommended to ensure compliance and security. It is especially suitable for developers in offline or restricted environments.
Read MoreDeepSeek Harness Visual Analysis Plugin
DeepSeek Harness (DSH) launches the `dsh-vision` plugin, embracing an "everything is a plugin" philosophy. By registering the `image_analyze` tool, it allows the main model to call a vision model (Google Gemini by default) for image analysis. The plugin supports PNG, JPEG, GIF, WebP, and other formats, along with multi-source inputs. Images are processed only in memory, with built-in automatic retry and security mechanisms. Users must install the plugin, configure an API key, and enable it in their profile. The agent can invoke the tool by passing an image path and a question, enabling use cases such as UI screenshot analysis and UI automation testing.
Read Moredsh-tool-visual-primitives: Supplement visual capabilities for DSH text-only models
# Introduction When building agents with DeepSeek Harness (DSH), you often encounter the same limitation: the text model at hand lacks native image input capabilities. If you paste screenshots or data charts into the conversation, the model cannot read them. Without plugins, you can only use a vision model upstream to read the images and manually paste the descriptions back into the conversation, breaking the chain in the middle. DSH's philosophy is "everything is a plugin," and such gaps are suitable for being filled by plugins. The dsh-tool-visual-primitives introduced below is exactly such a plugin: it hands images over to an external vision model for analysis, returns pure-text visual evidence with spatial localization information, and then passes it back to the original conversational model to continue reasoning. The enhanced model does not require native image input capabilities. # What is dsh-tool-visual-pr
Read Moredsh-vision-helper: Persistent Vision Plugin for DeepSeek Harness
dsh-vision-helper is a zero-dependency persistent vision plugin built for DSH, designed to integrate image analysis capabilities non-intrusively. It registers the `vision_analyze` tool, supports local path or data: URI inputs, and returns analysis text via a configured multimodal model. The plugin allows customization of provider, model, temperature, max output tokens, and image dimensions, with configurations taking effect immediately without requiring a restart and featuring a dedicated Web settings interface. Its core advantages include zero additional dependencies, global availability, persistent storage, and robust mechanisms such as automatic handling of invisible characters and deduplication. Installation supports npm, GitHub, or manual copying, and requires model routes or compatible endpoints to be pre-configured within llm-pi-ai. Users can configure it via the Web settings page or JS...
Read More