orrinzeng/chat-deepseek-vision
orrinzeng★ 1JavaScript最后同步: 2026-08-18
A native DeepSeek Harness (DSH) Cordis plugin that analyzes images through the reverse-engineered chat.deepseek.com vision mode (model_type=vision) — free, no third-party vision API key required. DeepSeek Harness(DSH)原生 Cordis 插件:通过逆向 chat.deepseek.com 识图模式(model_type=vision)分析图片,免费、无需第三方视觉 API key。
README 摘要
English 中文 chat-deepseek-vision A native DeepSeek Harness (DSH) Cordis plugin that analyzes images through the reverse-engineered chat.deepseek.com vision mode ( model type=vision ) — free, no third-party vision API key required. - No stdio/MCP bridge (replaces the old @deepseek-ai/dsh-mcp-client + node dist/index.js setup) - Tools are registered directly into the current agent's tool registry, isomorphic with the official @deepseek-ai/dsh-tool- plugins - Pure ESM JavaScript with zero runtime assets (the official PoW wasm is embedded as base64), no build step Tools Tool Description analyze image Analyze an existing image (local path / http(s) URL / data URI) via chat.deepseek.com vision mode, returning a text description analyze attachment Analyze an image attached in the send box / session (by attachment id , with a custom prompt for deep-dive analysis) describe screen Capture the screen and analyze it (full / primary / specific window; captured in the background without switching windows) take screenshot Capture the screen and save it only (no analysis) list windows List the titles of all visible windows dsv status Plugin self-check (masked token, endpoint, timeout, screenshot di…
在 GitHub 查看完整 README →分类
:rocket: The Ultimate Image Uploader for Efficient Creators. Supports Obsidian, Typora, VS Code etc. and 60+ image hosting services (S3, GitHub, Cloudflare R2, Imgur, Aliyun OSS...). Paste, upload, done.
★ 27,002
liustack/modlensThe first vision plugin for DeepSeek Harness, and the vision bridge for every text-only coding agent. Paste an image, get structured JSON evidence (OCR, layout, semantics). | 全网最强 DeepSeek Harness 外挂视觉插件,为 DeepSeek、GLM 等纯文本模型外挂视觉能力,粘贴图片即得结构化 JSON 证据(OCR、版面、语义)。
★ 3,503
Tiger3807861189/J-Space-Cognition-Suite-V3.6J-Space Cognition Suite V3.6 - AI cognitive-enhancement Skills based on Anthropic's J-space global workspace research. | 哔哩哔哩:Tiger380 (UID 3494375382321675) — https://space.bilibili.com/3494375382321675
★ 3,013