npm62Moderatehealth index
TypeScript★ 182↓ 3,969/moSep 18, 2026
crates.io62Moderatehealth index
Rust★ 53↓ 2,598/moSep 17, 2026
crates.io62Moderatehealth index
Rust★ 14↓ 1,918/moSep 17, 2026
npm57Moderatehealth index

FuzzySoul/dsh-free-vision为DSH(DeepSeek Harness)量身打造的视觉插件,现已支持agent调用图片显示/Vision plugin for DSH(DeepSeek Harness),support Proactive Image Display.
JavaScript★ 7↓ 4,909/moSep 18, 2026
npm57Moderatehealth index
TypeScript · JavaScript★ 1↓ 4,069/moSep 16, 2026
crates.io56Moderatehealth index

strawlab/dltDLT (direct linear transform) algorithm for camera calibration
Rust★ 5↓ 1,514/moSep 17, 2026
PyPI54Moderatehealth index

SIMON-WORLD/codex-deepseek-visionCodex vision bridge for DeepSeek V4 Flash: give text-only DeepSeek image capability in Codex. Local proxy turns pasted images and view_image into text via free GLM-4V-Flash or any OpenAI-compatible vision API. No GPU, no Ollama.
Python★ 7Aug 24, 2026
npm54Moderatehealth index

getpipher/visionCapability-aware vision + paste extension for the pi coding agent. Delegates image analysis only when the active model is text-only; passes through natively for multimodal models (zero delegation).
TypeScript★ 13↓ 1,588/moSep 16, 2026
PyPI53Moderatehealth index
Python★ 1↓ 1,013/moOct 20, 2026
npm51Moderatehealth index

Flyvhidbwo/dsh-vision-proxyDeepSeek Harness 插件:DeepSeek Pro 大脑 + 自动识图。GUI 附加图片默认经官方 deepseek-v4-flash-vision-exp 原生识图,转译成文字后交给 DeepSeek 作答(纯文本的 V4-Pro 也能看图);支持百炼/智谱/OpenRouter 等任意 OpenAI 兼容 VLM,无 key 自动探测本地 Ollama;安装时有一问式确认
JavaScript★ 14↓ 2,602/moSep 22, 2026
Python★ 0↓ 9,002/moJul 19, 2026
Mixed★ 9↓ 11K/moSep 14, 2026

jing-hy/picturereaderDSH plugin: pixel-to-text image reading for text-only models. image_scan/image_ocr/image_sample tools + image-reading skill (34-image trained methodology). Pure local, optional PaddleOCR.
JavaScript★ 36↓ 2,442/moOct 21, 2026
TypeScript★ 0↓ 2,213/moSep 18, 2026
TypeScript · JavaScript★ 14↓ 616/moSep 12, 2026
C#★ 25Oct 7, 2026
TypeScript★ 0↓ 4,573/moSep 15, 2026

hekmon/subtitles-ai-ocrRead PGS (Bluray) and VobSub (DVD) image subtitles and extract their text using external Vision Language Models.
Go★ 12Oct 20, 2026
JavaScript★ 0↓ 5,312/moSep 15, 2026

kalyanjanumpally/sap-joule-ai-pluginReference implementation: SAP Joule procurement copilot backed by a CAP AI service and an LLM-agnostic plugin (Anthropic / Ollama / SAP Generative AI Hub).
JavaScript★ 2↓ 4,372/moSep 18, 2026

wuzenghai616-lang/goldbeanx402 Micropaid MCP Server — 51 Baidu AI tools for global developers. Pay-per-call with USDC, PayPal, or Alipay. No Chinese phone number needed.
JavaScript · HTML★ 1↓ 373/moSep 13, 2026

cleverIdeaz/phewsh-cliThe phewsh CLI — a local-first continuity layer that keeps your intent aligned across every AI tool. Source-public (MIT) for inspection; the npm package 'phewsh' is built from here.
JavaScript★ 1↓ 600/moSep 13, 2026

staticdeng/image-vision-mcpMulti-Model Visual Understanding MCP Server, GLM-4.6V, kimi-k2.7, Qwen3-VL-Flash and gpt-4o. Provide visual processing capabilities for AI coding models that do not support image understanding
TypeScript★ 13↓ 2,062/moSep 18, 2026
npm · Maven · RubyGems27At Riskhealth index
Objective-C++ · Kotlin · TypeScript★ 12↓ 5,554/moOct 19, 2026