MIT-licensed vision toolkit that gives text-only agents eyes; connects to DeepSeek Harness natively via the dsh-vision-toolkit Profile Bundle, and works in any shell-capable agent via CLIs + skill.
DSH integration
Native runtime
Author-claimed
Safety audit
Unaudited
Last verified
2026-08-21
License
MIT
01What can it help you accomplish?
Give a text-only coding agent (e.g. DeepSeek) working vision: image Q&A, OCR of long screenshots and chat histories
Task-aware image answers, transcribed text, and merged OCR of scrolling pages with speaker/timestamp preservation
Developers running text-only models such as DeepSeek who need image understanding without switching to a multimodal model
Rebuild UI pages, infographics, icons and diagrams from screenshots or sketches into editable code
HTML/CSS reconstructions, transparent PNG extractions, editable SVG, and structured Mermaid/Graphviz representations
Frontend developers and designers who want agent-driven screenshot-to-code / sketch-to-interface restoration
Operate a GUI from screenshots: locate controls, act, and verify the resulting state
Pixel-coordinate grounding of controls and a verify-after-each-action automation loop
Automation engineers who need screen-element grounding (e.g. `ground`/`detect`) for GUI control with a text-only agent
02How to install into DeepSeek Harness
Prerequisites
- A coding agent already working with a model, including a text-only model such as DeepSeek V4
- A multimodal vision API supporting OpenAI Chat Completions, OpenAI Responses, or Anthropic Messages, plus its base URL, API key, and model name
- Python 3.11+ for `glance`; optional `pillow` for `ground`/`detect`/`crop` and the long-screenshot OCR playbook, `pillow` + `numpy` for `trace`
Installation steps
- 01
Point it at a vision API — write three env vars (`VISION_API_KEY`, `VISION_BASE_URL`, `VISION_MODEL`) to `~/.config/agent-vision-toolkit/env` (`chmod 600`)
- 02
Put the CLIs on your PATH: `git clone https://github.com/Anionex/agent-vision-toolkit.git` then `export PATH="$PWD/agent-vision-toolkit/bin:$PATH"` (add to your shell profile to persist)
$ git clone https://github.com/Anionex/agent-vision-toolkit.git
- 03
Install the skill so your agent knows the tools exist: `npx skills add Anionex/agent-vision-toolkit --skill vision-skills -a codex -g --copy -y`, or copy `skills/vision-skills/` into your agent's skills directory (e.g. `~/.codex/skills/`) and restart the agent
$ npx skills add Anionex/agent-vision-toolkit --skill vision-skills -a codex -g --copy -y
- 04
Optional seamless integration: follow AGENT_INSTALL.md to install the transparent local proxy (Codex / Claude Code) or single-file native extension/plugin (Pi, Oh My Pi, OpenCode); for native DSH support use the linked `dsh-vision-toolkit` package (clone with `--recurse-submodules` or run `git submodule update --init --recursive`)
$ git submodule update --init --recursive
Verify the integration
- After installing the optional integration and restarting the agent, paste an image directly or let the model call its built-in image tool
03DSH integration and capability boundaries
Native DSH Profile Bundle via the linked `dsh-vision-toolkit` package (tracked as a Git submodule); the standalone CLIs and `vision-skills` skill also run in any shell-capable agent
glance — intent-aware image Q&A and OCR
an image file plus a question (or `--ocr`)→task-aware answers or transcribed text, focused on the current step's intent instead of a generic description
sends the image and focus hint to the configured external multimodal vision APIground / detect — pixel-coordinate localization
an image plus a target description (optionally `--region`)→bounding boxes in original pixel coordinates; numbered element inventories with exact visible text
sends the image to the configured external multimodal vision APItrace / crop — deterministic SVG fitting and region cropping
a flat, high-contrast graphic (or a pixel box for `crop`)→editable SVG primitives (`<circle>`, `<line>`, `<polyline>`, `<polygon>`) fitted locally; cropped region files for reuse
writes output files (SVG / cropped images) to diskSeamless integration — transparent local proxy / native extensions
agent requests containing pasted images or built-in image tool calls→images replaced with task-aware text descriptions before reaching the text-only upstream, with no extra prompting
runs a local proxy at 127.0.0.1:19100 and forwards requests (including the original Authorization header) to your existing upstream
04Who is it for? When not to use it?
Good for
- Developers running text-only models such as DeepSeek who need image understanding without switching to a multimodal model
- Frontend developers and designers who want agent-driven screenshot-to-code / sketch-to-interface restoration
- Automation engineers who need screen-element grounding (e.g. `ground`/`detect`) for GUI control with a text-only agent
Not for
- This is an image-to-text layer — it doesn't hand vision tokens directly to the text model, and overall visual-task quality is determined jointly by the primary LLM and the multimodal LLM.
05Compatibility, maintenance and safety notes
- This is an image-to-text layer — it doesn't hand vision tokens directly to the text model, and overall visual-task quality is determined jointly by the primary LLM and the multimodal LLM.
- Requires an external multimodal API (OpenAI Chat Completions / Responses / Anthropic Messages) with its own base URL, API key, and model name; images leave your machine to that endpoint.
- The proxy's cache lives only inside its process and is cleared on restart.
MIT · actively maintained (latest release v0.2.0, 2026-08-14)
06Frequently asked questions
How do I connect agent-vision-toolkit to DeepSeek Harness?
Through the linked `dsh-vision-toolkit` package — a native Profile Bundle for DSH Web and Headless profiles with 10 structured visual tools, DSH Credentials, a managed isolated runtime, and Agent-scoped progressive tool exposure. It is tracked as a Git submodule: clone with `--recurse-submodules`, or run `git submodule update --init --recursive` in an existing checkout.
Is the DSH integration native or MCP?
Native — `dsh-vision-toolkit` runs as a native Profile Bundle inside DSH, not through MCP. Separately, the base toolkit's CLIs can be used by any agent that can invoke a shell, with no integration needed.
What prerequisites do I need?
A coding agent already working with a model (text-only models like DeepSeek V4 are fine), plus a multimodal vision API supporting OpenAI Chat Completions / Responses / Anthropic Messages with its base URL, API key, and model name. `glance` needs Python 3.11+; `ground`/`detect`/`crop` need `pillow`; `trace` needs `pillow` + `numpy`.
Where do my images and data go?
Image content and a task focus hint are sent to the multimodal vision API you configure via `VISION_BASE_URL`. The optional local proxy at 127.0.0.1:19100 forwards your existing upstream Authorization header unchanged — it does not store your upstream API key.
What limits should I know about?
It is an image-to-text layer — no vision tokens reach the text model; visual-task quality depends jointly on the primary and multimodal LLMs; and the proxy cache lives only in its process and clears on restart.
07Related DSH workflows
modlens
by liustack
Vision bridge for text-only models: paste an image, get structured JSON evidence (OCR, layout, semantics).
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-vision-toolkit
by anionex
为纯文本 DSH Agent 提供 10 个结构化视觉工具：意图感知图片问答、长截图 OCR、原始像素 grounding、UI 还原、像素 diff 等
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
The new [`dsh-vision-toolkit`](https://github.com/Anionex/dsh-vision-toolkit) linked package brings this toolkit into DS…
It provides 10 structured visual tools for intent-aware image Q&A, grounding, detection, tracing, cropping, pixel diff,…
The package is tracked here as a Git submodule and maintained independently at [`Anionex/dsh-vision-toolkit`](https://gi…
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.