Reviewed DeepSeek Harness extensions — filter by category, search by capability, and jump straight to each plugin's public source.
Vision bridge for text-only DeepSeek: send images (alone or mixed with text) and a fast tiny vision model describes them behind the scenes — the chat keeps the picture, DeepSeek sees only text. Pure plugin: uninstall restores everything.
dsh plugin add balue8246-maker/dseyesopen
Let your AI agent see and operate a real Android phone: phone_look (vision + UI-tree fusion), tap/swipe/type, screenshot — over adb, for any MCP client.
dsh plugin add boheastill/phone-eye
Give DSH text-only models vision: an image/OCR/document recognition skill (race pool → custom channels → local) plus an idempotent host patch so image messages reach the model.
dsh plugin add br1nosense/dsh-vision-solution
Configurable image recognition for text-only DSH models: image messages are first transcribed by any OpenAI-compatible vision model (Base URL, model ID and key configured in a Settings section), then passed to the main model as text; image-input support is advertised while enabled.
dsh plugin add bug-huntter/dsh-vision-plugin
Reuses DeepSeek web's built-in vision mode for text-only models: the deepseek_vision tool drives the local deepseek-vision-cli browser automation (manual login helper, deep-think enabled, auto-closes browser) and returns image descriptions as text.
dsh plugin add Cheng-cheng9669/dsh-deepseek-vision
Free vision OCR with adaptive tile recognition for long documents and Markdown/Word/PNG/Excel export.
dsh plugin add Ck-epsilon/aura-vision
MCP bridge to gemini.google.com: vision analysis of images and videos, Imagen image and Veo video generation, and conversation management using the logged-in browser session with no API key.
dsh plugin add ConsoleSun/Gemini-Eyes
Automatically generates and displays images in the DSH chat via API channels or local CLIs (mmx / codex / agy), and can also recognize images using the corresponding CLI.
dsh plugin add corrinehu/dsh-chat-imagine
Lets text-only models handle pasted chat images, with a native vision experience, batch image viewing, and a built-in OpenAI-compatible analyze_image tool; vision-capable models are unaffected.
dsh plugin add dami9527/dsh-image-pathify
Gives a text-only model image understanding via a vision-language model, exposed as a `describe_image` tool.
dsh plugin add DamonKoy/dsh-web-ui#dsh-tool-describe-image
AI image generation for the DSH Web GUI: text-to-image and image-to-image through a configurable OpenAI-compatible endpoint (gpt-image-2 / gpt-image-1 / dall-e-3), with an api_url/api_key settings card and a sidebar split-pane generation studio.
dsh plugin add dickpy/dsh-imagegen
Native LLM-provider vision bridge: images pasted in the chat are described by a vision model (Qwen3-VL via pi-ai/llama.cpp) and the text description is fed to text-only DeepSeek for the reply — image admission, routing and compaction all run through harness-native mechanisms, with an LRU description cache and 503 retry.
dsh plugin add Einskyle/dsh-llm-vision-bridge
Image-to-text input for the Web UI: paste or drag an image and it is transcribed into structured text and sent, giving text-only LLMs image-input takeover (OpenAI-compatible vision API).
dsh plugin add Elohia/dsh-plugin-image-input
Synesthesia Encoder for DSH: a vision model translates images into compact structured spatial text (canvas/elements/percentage coordinates), giving text-only LLMs pixel-level image understanding via the `mm_vision` tool.
dsh plugin add Elohia/dsh-plugin-mm-vision
Labnana image generation for DeepSeek Harness: text-to-image / image-to-image / precise editing with credits estimation, subscription balance and web settings UI.
dsh plugin add exoticknight/dsh-labnana
Drive a local or remote ComfyUI server from DeepSeek Harness: comfyui_run / comfyui_object_info / comfyui_workflow tools generate and edit images and videos, with a workflow library (graph extraction: per component / main flow / all), a load area with resolution auto-match, a live queue, SDXL and Wan 2.1 templates, a companion skill, and a same-origin media proxy.
dsh plugin add fandc520/dsh-comfyui
DeepSeek brain + automatic image transcription: attach images in the GUI and each one is transcribed via the official deepseek-v4-flash-vision-exp by default (a pure-text V4-Pro brain can see images), with any OpenAI-compatible VLM or local Ollama as alternatives.
dsh plugin add Flyvhidbwo/dsh-vision-proxy
Free vision bridge for text-only models: image understanding, OCR, UI and debug analysis via free-tier providers (Qwen3-VL-Flash, Doubao, DeepSeek-OCR) with a settings GUI.
dsh plugin add FuzzySoul/dsh-free-vision
Local-first structured vision for text-only agents: images go to a local OpenAI-compatible VLM and come back as JSON evidence (summary, verbatim OCR, layout regions, entities/relations, colors, explicit uncertainty), with anti-hallucination fallback and an optional paste/upload bridge; zero cloud cost, images never leave the machine.
dsh plugin add gloryxpnv/dsh-tool-vision
Transparent image guard for text-only routes: paste images without the 400 session deadlock, plus a vision_analyze tool for OCR/PDF/docx/pptx/video.
dsh plugin add good-boy4069/dsh-vision-guard
Routes images to a vision model of your choice - auto-rewrite, explicit tools, or hybrid - so a text-only chat model does not fail a turn that contains a picture.
dsh plugin add GooDAnDReaDY/dsh-vision-bridge
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.
dsh plugin add GOU-GEE/deepseek-vision#plugins/dsh-plugin-deepseek-vision
Bridges session images to configurable vision providers and returns text-only analysis to eligible DeepSeek Harness model routes.
dsh plugin add GXX182/dsh-vision-bridge
Combine text, vision, and image-generation APIs into one Mix model with automatic routing: text-only requests go to the chat model, user images and agent screenshots go to the vision model, follow-ups keep using the same session image, and agents can generate or edit images with session-scoped call history.
dsh plugin add haiziyao/dsh-vision-mix
Page 81 of 138
Filter by category or keyword — every listing is a public GitHub project.
Commands follow the upstream list; check each repo's README for exact package names.
Plugins run third-party code with your permissions — read the source first.
This directory is a snapshot of the community-maintained awesome-dsh-plugin list (updated 2026-09-07). Listings link to the authors' repositories; inclusion is not an endorsement or a security review. Missing a plugin? Contribute to the upstream list.