MIT-licensed vision plugin for DeepSeek Harness, installed natively via `dsh plugin add` into Web or Headless Profiles — 10 vision tools plus playbooks and a built-in free Gemini 3.7 Flash service for image Q&A, OCR, and UI restoration.
DSH integration
Native runtime
Author-claimed
Safety audit
Unaudited
Last verified
2026-08-21
License
MIT
01What can it help you accomplish?
Complete high-value visual tasks in DeepSeek Harness: read long screenshots, rebuild a UI from a screenshot or sketch, restore graphics, or operate a GUI from screenshots
Markdown OCR output with chunks and audit info, rebuilt HTML/CSS pages, SVG / transparent-PNG graphics, and verified GUI states — produced by 10 composable tools guided by the bundled vision-skills playbooks
Developers running DeepSeek Harness who want text-only agents to do more than caption images — OCR, UI restoration, grounding and screenshot-driven GUI automation
Give a text-only DeepSeek Harness model a multimodal-style experience: paste an image and ask questions about it directly
Task-aware image answers with intent-focused evidence (e.g. where the error is, where the button is) instead of generic captions, with native thumbnails, session history and artifact previews kept intact
DeepSeek Harness Web users on text-only models who want to paste an image and ask directly, without changing models or copying paths
02How to install into DeepSeek Harness
Prerequisites
- A running DeepSeek Harness environment with a Web, Headless, or Desktop profile
- Python 3.11+ is preferred; when none is found the plugin downloads a hash-verified standalone Python (about 35 MB) automatically on first use
Installation steps
- 01
Run `dsh plugin --profile web add @anionex/dsh-vision-toolkit` to install into a Web Profile
$ dsh plugin --profile web add @anionex/dsh-vision-toolkit
- 02
Optionally install into a Headless Profile with `dsh plugin --profile headless add @anionex/dsh-vision-toolkit`
$ dsh plugin --profile headless add @anionex/dsh-vision-toolkit
- 03
For DSH Desktop, open DSH Terminal from the tray and run `dsh plugin --profile desktop add @anionex/dsh-vision-toolkit`, then restart DSH Desktop (the Desktop 2.0.1 built-in marketplace has known installation issues; the terminal command is the reliable path)
$ dsh plugin --profile desktop add @anionex/dsh-vision-toolkit
- 04
Restart the running Web Profile
Verify the integration
- Open Settings → Vision Toolkit; the free provider is already configured — run Test vision model to confirm it is reachable
03DSH integration and capability boundaries
Native DeepSeek Harness plugin installed with the dsh CLI into Web / Headless / Desktop Profiles, exposing 10 vision tools, a bundled vision-skills Skill, Settings panel, Credentials, Artifacts and Web UI presentation
10 composable vision tools
images (pasted, in the session workspace, or long screenshots) plus a task-focused question→image Q&A, pixel coordinates and boxed previews, PNG/JPEG crops, SVG traces, pixel-diff heatmaps with JSON, long-screenshot Markdown OCR, transparent PNGs, palettes, and HTML screenshots
vision_html_screenshot renders local pages via Chrome/Chromium/Edgetool outputs write result files (crops, SVGs, heatmaps, JSON) into the workspacevision-skills Skill playbooks
a visual task prompt, e.g. `(Use vision-skills) Rebuild this image into HTML.`→agent workflows for long-screenshot OCR, UI restoration from screenshots/designs, graphic/logo restoration, sketch-to-structured-code (Mermaid/Graphviz), and screenshot-driven GUI operation
Built-in free Gemini 3.7 Flash vision service
none (no API key required)→a working vision provider configured out of the box after installation
images are sent to the shared service endpoint https://vision.anionex.me/v1first start downloads a hash-verified standalone Python (~35 MB) from a domestic mirror (GitHub fallback) and installs locked runtime dependencies (Pillow, NumPy, vtracer) from a PyPI mirrorAutomatic image input routing in DSH Web
an image pasted into a DSH Web conversation→the text-only model transparently switches to its `(Vision Toolkit)` variant with a reusable workspace path and task-focused description; thumbnails, session history and artifact previews stay intact
04Who is it for? When not to use it?
Good for
- Developers running DeepSeek Harness who want text-only agents to do more than caption images — OCR, UI restoration, grounding and screenshot-driven GUI automation
- DeepSeek Harness Web users on text-only models who want to paste an image and ask directly, without changing models or copying paths
Not for
- The built-in free service is a shared endpoint with safeguards: 100 images per machine per day, up to 5 images per request, 4 MiB per image, 20,000,000 decoded pixels, and 4,096 output tokens; when capacity is reached it returns 429 with Retry-After. Higher volume requires bringing your own vision provider.
- First-time setup needs network and disk access to prepare the isolated Python runtime: it downloads a hash-verified standalone Python from a domestic mirror (falling back to the GitHub release) and installs locked dependencies (Pillow, NumPy, vtracer) from a Tencent Cloud PyPI mirror before falling back to the official PyPI index.
05Compatibility, maintenance and safety notes
- The built-in free service is a shared endpoint with safeguards: 100 images per machine per day, up to 5 images per request, 4 MiB per image, 20,000,000 decoded pixels, and 4,096 output tokens; when capacity is reached it returns 429 with Retry-After. Higher volume requires bringing your own vision provider.
- First-time setup needs network and disk access to prepare the isolated Python runtime: it downloads a hash-verified standalone Python from a domestic mirror (falling back to the GitHub release) and installs locked dependencies (Pillow, NumPy, vtracer) from a Tencent Cloud PyPI mirror before falling back to the official PyPI index.
- vision_html_screenshot requires Chrome, Chromium, or Edge — without one only HTML screenshot rendering is unavailable while the other tools still work; on DSH Desktop 2.0.1 the built-in marketplace has known installation issues, so installing via DSH Terminal is the reliable path.
MIT · actively maintained (latest release v0.1.36, 2026-08-20)
06Frequently asked questions
How do I install DSH Vision Toolkit into DeepSeek Harness?
Run `dsh plugin --profile web add @anionex/dsh-vision-toolkit` (or `--profile headless` / `--profile desktop`), then restart the profile. It is a native dsh plugin — not MCP — with tools exposed inside Profiles, sessions, Settings, Artifacts, and the Web UI.
Do I need an API key for vision?
No. A built-in free Gemini 3.7 Flash vision service is configured after installation with no API key required. For higher quotas or a private endpoint, change the provider in Settings → Vision Toolkit and store your API key as a DSH Credential.
What prerequisites does it need?
A running DeepSeek Harness profile. Python 3.11+ is preferred; otherwise the plugin automatically downloads a hash-verified standalone Python (about 35 MB) on first use. vision_html_screenshot additionally needs Chrome, Chromium, or Edge.
What are the free service limits?
The shared free endpoint allows 100 images per machine per day, up to 5 images per request, 4 MiB per image, and 20,000,000 decoded pixels. When capacity is reached it returns a 429 with Retry-After instead of failing silently.
Where do my images go?
With the default setup, images are sent to the shared free service at https://vision.anionex.me/v1. You can switch to your own OpenAI-compatible or Anthropic Messages endpoint in Settings, where the Credential secret is stored without being read back into the browser.
07Related DSH workflows
modlens
by liustack
Vision bridge for text-only models: paste an image, get structured JSON evidence (OCR, layout, semantics).
agent-vision-toolkit
by anionex
Vision toolkit and skills that give text-only LLMs eyes — multi-image understanding, image Q&A, OCR, frontend UI restoration and GUI automation, with optional agent integration.
dsh-vision-router
by ysr666
Eyes for text-only DeepSeek Harness agents: built-in free vision chain (no key) + pixel-level vision tools (Q&A, grounding, crop, pixel diff, colors, OCR, SVG trace, cutout, screenshots). One-command install, no Python, image turns work like ordinary tool-calling turns.
dsh-image-gen
by shanliuling
AI image studio for DeepSeek Harness — generate, edit & compare images in chat, with 500+ prompts, gallery, multi-model workflows and ComfyUI.
08Data and sources
A more powerful vision toolkit—give text-only models in DeepSeek Harness eyes: image Q&A, long-screenshot OCR, UI restor…
dsh plugin --profile web add @anionex/dsh-vision-toolkit
Native DSH integration: those capabilities live inside Profiles, sessions, Settings, Artifacts, and the Web UI, with a f…
This page is generated from the project’s public documentation, repository metadata and a structured parse of DSH Plugins; last verified on 2026-08-21. Found an error? Submit a correction.
Best DeepSeek Harness Plugins
Twelve plugins worth installing first — picked from the whole catalog, across every category.