Give your text-only LLM eyes: zero-dependency MCP server that reads images via external OpenAI-compatible vision models with automatic provider fallback, plus a one-command patch for DSH image-attachment degradation.
Use your ChatGPT subscription in DeepSeek Harness to access Codex models and generate or edit images with gpt-image-2—no OpenAI Platform API key required.
DeepSeek Harness 第三方 API 与自定义模型设置插件：支持请求头、User-Agent、模型列表、图像输入和思考等级 | WebUI plugin for third-party APIs and custom models with request headers, image input, and reasoning levels
Eyes for text-only DeepSeek: view_image tool (local Ollama or any OpenAI-compatible VLM) + chat image-attachment bridge — paste/drop images in the chat and the model can see them.
Connect your sub2api gateway to DeepSeek Harness: OpenAI-compatible multi-provider routes (OpenAI / Claude / Grok / Gemini) behind one base URL, with per-key model discovery, usage lookup, and a settings page.
dsh plugin: model catalog auto-discovery - fetch model listings, pricing and capabilities from OpenAI-compatible API hosts, normalized into ready-to-use config
Unified static-image generation router for DeepSeek Harness: one image_generate tool with standard parameters, config-driven engine routing (OpenAI Images, Zhipu CogView, and any compatible endpoint) with health-aware fallback, durable workspace attachments, per-session quota accounting, and a Plugins settings panel
Make your AI agent a math tutor. Structured extraction of vectors, matrices & geometry from math figures, with dimension-consistency + geometric self-check. Vision plugins for DeepSeek Harness, opencode (MCP) & CLI. Verify, don't believe.
