DeepSeek Harness Plugins · Model Inference
Plugins that extend DeepSeek Harness (DSH) with vision, workflows, memory, web tools and more.
This plugin provides character profiling, appearance weight statistics, and behavior deviation detection for long-form novel writing to ensure character consistency.
A DeepSeek Harness plugin for delegating subagent work to a configured model route, with support for model selection, waiting for completion, and UI integration.
A plugin for DeepSeek Harness that enables editing reasoning effort and input modality for third-party models, simplifying configuration through auto-adaptation and page injection.
A high-resolution vision enhancement plugin for DeepSeek Harness, designed for the deepseek-v4-flash-vision-exp model, which improves recognition of large images through automatic tiling.
Adds multimodal eyes and hands to DeepSeek Harness, supporting image transcription and generation with user-configurable vision endpoints for flexible and secure interaction.
A VLM analyzer plugin for DeepSeek Harness featuring an analyze_image tool with automatic failover between primary/backup vision APIs and an auto-saving settings page.
dsh-plugin-deepeye is a native Cordis plugin that adds vision capabilities to DeepSeek Harness, enabling image description, OCR, visual Q&A, UI layout analysis, and automatic translation of pasted images.
A model switch for DSH that points to any OpenAI-compatible endpoint with curated presets and automatic fallback on rate limits.
DSH Effort Tweak adds a settings page for adjusting the reasoning effort levels of models in custom providers for DeepSeek Harness.
dsh-vision-tools enables DeepSeek text models to understand images via vision APIs, supporting paste, drag-and-drop, and file selection.
A minimalist WeChat plugin that supports QR code login and file sending/receiving.
A multi-panel live subagent viewer for DeepSeek Harness with a subagent_with_model tool for per-call model/provider override.