Well-documented, actively maintained plugin that gives text-only models vision via configurable OpenAI-compatible APIs.
Code quality8
README documents a clear dual-implementation structure (Python script and zero-dependency ESM JS port) with explicit sync-maintenance notes, though no tests or CI are mentioned.
Security7
Install instructions include curl-pipe-to-bash one-liners and plaintext API keys in env files, but the README warns to chmod 600 and never commit secrets, and the plugin itself uses only Node built-ins.
Utility9
Solves a real and common pain point by letting text-only models like DeepSeek perform image description, Q&A, and OCR through many OpenAI-compatible providers.
Maintenance8
Last updated 2026-08-14, not archived, and the README includes explicit maintenance notes about keeping the Python and JS implementations in sync.
Docs9
README provides per-host install tables, three installation methods each, full configuration variables, provider references, and usage examples for Codex, Claude Code, and DSH.
Generated by AI after reading the project README, as a decision aid; neutral scores are given when information is thin. Not an official endorsement.
This command passed the install-plan safety check and can be executed by a DSH host; verification status is not equivalent to a security audit or official背书。
This repository does not provide a project description yet.
How popular is image-vision?
image-vision has 8 stars and 0 forks on GitHub, last updated 2026-08-14.
What license does image-vision use?
image-vision is distributed under the MIT license.
Is image-vision compatible with DeepSeek Harness?
image-vision is listed in the DSH Universe directory as a tool for DeepSeek Harness. This plugin is listed in the DSH Universe directory and covered by its validation pipeline.
CLASSIFICATION EVIDENCE
/10类依据
项目类型技能
功能/10类开发工具
规则置信度High
System reads GitHub Topics first, then compares against the in-site category dictionary and word-root rules. Current match:claude-code-skill、codex-skill。
Agent skill for beautiful, verifiable architecture, workflow, sequence, data-flow, and lifecycle diagrams—self-contained HTML with motion and crisp export.
✨ All your agents and workspaces in one place, on every device you own. Track tasks on a board, accessible from desktop, mobile, browser, or API. Self-hosted.
Enterprise-grade, local-first Agent Workbench for people and agent teams. A unified multi-engine workspace for Codex Harness, DeepSeek Harness, and OpenCode, with unified plugins and Skills, multi-agent projects and tasks, and editable code, documents, presentations, design, and video.