PineKings/deepseek-harness-desktop
PineKings★ 0TypeScriptLast synced: 2026-08-15
在官方的基础上增加了视觉能力的可选项补充deepseek模型的视觉能力,增加了本地一键安装的桌面支持
README excerpt
DeepSeek Harness DeepSeek Harness ( dsh ) is a plugin-based agent harness where everything is a plugin — models, tools, skills, sessions, storage, the agent loop, and even the UI are all replaceable Cordis plugins, freely recomposed per profile. It ships both as a CLI/Web harness and as a native desktop app ( deepseek-harness-desktop ). Community fork : this repository is a community derivative of deepseek-ai/deepseek-harness, maintained by PineSound, adding a desktop app, plugin marketplace, image recognition, and a release channel on top of the unchanged core harness . This is not the official DeepSeek repository. Full list of changes: MODIFICATIONS.md · MODIFICATIONS.zh.md. Proof What it is An agent harness assembled from plugins. Instead of a monolithic binary, every capability lives behind a documented seam — Service Definition / Provider / Consumer — so you swap tools, skills, storage, terminal, web, or sandbox without touching the loop. Runs are traceable : everything a model sees is reconstructable from the session log. Why it is different - Everything is a plugin — models, tools, skills, sessions, storage, loop, and UI are replaceable, recomposable units. - Traceable by de…
View full README on GitHub →Category
The 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). | 全网第一个 DeepSeek Harness 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)。
★ 1,700
Anionex/agent-vision-toolkit为纯文本模型"看图“设计更好的视觉工具箱和技能,支持多图理解,图片问答,前端UI还原、GUI 自动化等,并可选无缝接入多个主流agent,直接识别粘贴图片| A vision toolkit and skill designed for text-only llms — image Q&A, long-screenshot OCR, frontend UI restoration, and GUI automation, with optional seamless integration for Codex, Claude Code, Pi, Oh My Pi, and OpenCode
★ 884
Anionex/dsh-vision-toolkit让纯文本模型更好地做视觉任务的DeepSeek Harness插件:带意图的图片问答、长截图 OCR、UI 还原等|DeepSeek Harness-native integration for agent-vision-toolkit: image Q&A, long-screenshot OCR, UI restoration, grounding, pixel diff, Artifacts, and Web UI.
★ 405