Gives text-only coding agents the ability to see: image question answering, OCR on long screenshots, restoring frontend UI from images, and GUI automation. It ships as local vision CLIs plus a skill, with optional integration for several coding agents.
Claude Code
$ npx -y skills add Anionex/agent-vision-toolkit --agent claude-code
Codex
$ npx skills add Anionex/agent-vision-toolkit -a codex
Cursor
$ npx skills add Anionex/agent-vision-toolkit -a cursor
Gemini CLI
$ npx skills add Anionex/agent-vision-toolkit -a gemini-cli
GitHub Copilot
$ npx skills add Anionex/agent-vision-toolkit -a github-copilot
OpenCode
$ npx skills add Anionex/agent-vision-toolkit -a opencode
Windsurf
$ npx skills add Anionex/agent-vision-toolkit -a windsurf
What it thinks is what it sees β give any text-only coding agent eyes: image Q&A, long-screenshot OCR, frontend UI restoration, and GUI automation, as a vision toolkit plus a skill, with optional drop-in integration for Codex, Claude Code, Pi, Oh My Pi, and OpenCode.
π― An agent's vision capability doesn't have to live in the model β it can live in the harness.
π δΈζ ο½ English
If your agent already runs on a text-only model such as DeepSeek but is held back by the lack of multimodality β unable to see images, with every attempt to use an image tool blocked by the system β this repository provides tools, skills, and proxy integrations that let text-only models handle visual tasks on equal or even better footing. The goal is to make the experience of using a text-model agent as seamless as using a multimodal one, and ultimately let a tool-equipped text-model agent outperform a native multimodal agent that does not use this toolkit and its methods.
This repository provides two kinds of components:
All code has been verified in real Codex + DeepSeek sessions, and the same pipeline has been live-verified end-to-end in Claude Code, Pi, Oh My Pi, and OpenCode.
If this project helps you or gives you some inspiration, feel free to starπ & fork.
Want to sponsor this project? See FUNDING.md or email davidyang042@gmail.com.
Click to collapse
2026-08-18 β Skill renamed: the included agent skill is now vision-skills (formerly vision-tools), so the name describes the capability rather than the underlying tools.
2026-08-13 β Native DeepSeek Harness support is now available. The new dsh-vision-toolkit linked package brings this toolkit into DSH Web and Headless profiles as a native Profile Bundle. It provides 10 structured visual tools for intent-aware image Q&A, grounding, detection, tracing, cropping, pixel diff, long-screenshot OCR, foreground extraction, dominant-color analysis, and HTML screenshots, while adding DSH Credentials, a managed isolated runtime, previewable Artifacts, Web Settings, and Agent-scoped progressive tool exposure.
The package is tracked here as a Git submodule and maintained independently at Anionex/dsh-vision-toolkit. Clone this repository with --recurse-submodules, or run git submodule update --init --recursive in an existing checkout.
Contents
The included vision-skills skill contains complete examples that an agent can follow directly.
When to use them, the order in which to call tools, and how to verify the result are all documented in the corresponding skill guides:
| Use case | What the agent learns to do |
|---|---|
| Extract long screenshots, chat histories, and scrolling pages | Find low-content cut bands, OCR each chunk in order, preserve chat speakers/timestamps/quotes, merge only duplicated overlap, and surface risky boundaries for verification. See the Telegram reference run β |
| Rebuild a UI from a screenshot or design | Reuse project components and assets first, then combine code-native UI, extracted visuals, rendered screenshots, and visual comparison to align a page or component. |
| Restore an icon, logo, illustration, or other graphic | Extract a transparent PNG from the source image, or rebuild an editable/scalable SVG when needed, then verify shape, color, and alpha edges. |
| Turn a sketch, diagram, or whiteboard into structured code | Recover nodes, labels, connections, and directions as editable Mermaid, Graphviz, or another structured representation. |
| Operate a GUI from screenshots | Locate a control, perform one action, capture the screen again, and verify the resulting state before continuing. |
| More use cases | Other step-by-step visual-agent playbooks are being added gradually. |
Left: the original infographic screenshot. Right: an editable reconstruction built with HTML/CSS. View the HTML source β
Left: the hand-drawn reference. Right: the restored JupyterLab workspace made from it. See the UI restoration playbook for the workflow. Executed in Codex with deepseek-v4-flash.
Left: the original page. Right: a fast reconstruction that preserves the main layout, content, and visual hierarchy while allowing approximate colors and library icons. Fast mode targets a first screenshot in about three minutes.
Left: multi-round image Q&A with glance. Right: with ground, DeepSeek V4 locates screen elements to play chess autonomously.
Left: DeepSeek V4 answers a UI style question with similar-style comparisons. Right: DeepSeek V4 debugs a field-name mismatch from a screenshot.
The easiest way to install it is to send this to your agent:
Follow the instructions in https://github.com/Anionex/agent-vision-toolkit to install the vision toolkit and skill locally. If the vision API is not configured, locate the configuration file for the current operating system and guide me through setting
VISION_API_KEY,VISION_BASE_URL, andVISION_MODEL.
If you also want the optional seamless integration layer, send this:
Stars on GitHub
See 12 agent-vision-toolkit alternatives
A development methodology for coding agents that makes the agent brainstorm before building, follow plans, run parallel work and finish branches in a disciplined way. You get fewer skipped steps and more consistent results from your coding assistant.
@obraHelps you take a change from a rough idea or bug report through to a tested, reviewed result, with each step handled by a focused skill. Its skills cover pinning down domain terms, designing module interfaces, diagnosing hard bugs, and reviewing changes against your repo's coding standards.
@mattpocockGives your coding agent a planning, testing and review routine to follow on every task. It plans before building, checks changes with tests, has a fresh reviewer look for regressions, and saves repeated wins as reusable skills.
@affaan-mDeveloper tools for working on the React codebase itself. Provides skills for extracting error messages, managing and debugging feature flags across release channels, running Flow type checks, and fixing lint and formatting issues before committing.
@facebookInstall it with the command on its page. It includes vision-skills. Its skills do not fire on their own yet. Free and open source.
Is this plugin yours?
Claim it with GitHubSubmit a pluginPromote it
