MicroHEROX/dsh-koboldcpp-hands
MicroHEROX★ 0TypeScript最后同步: 2026-08-14
KoboldCpp for DeepSeek Harness - a tool plugin that lets the harness online model hand repetitive text and vision (OCR) labor to a local KoboldCpp (llama.cpp) server.
README 摘要
KoboldCpp for DeepSeek Harness dsh-koboldcpp-hands — give your DeepSeek Harness agent a pair of local hands. English · 中文 A third-party tool plugin for DeepSeek Harness that lets the online model (your main conversation model) hand repetitive, token-cheap labor to a local KoboldCpp (llama.cpp) server — plain text work and vision work (image analysis / OCR / comparison). The main model stays where your deployment puts it. When it decides a job is better done locally, it calls: - koboldcpp run — run one prompt on the local text model (batch rewrites, name translations, string munging, short summarization, extraction). - koboldcpp vision — send images to a local multimodal model (OCR, image analysis, multi-image comparison) with structured report templates. The plugin manages the local server lifecycle: it launches your KoboldCpp binary with your .kcpps launch config (which owns the GPU backend, model, mmproj , port), waits for the model to load, and stops the server on an idle timeout and/or harness exit. An externally started KoboldCpp is reused and never killed. What it does - Two model-facing tools registered on the harness tool registry ( ctx.tools ), following the official dsh-t…
在 GitHub 查看完整 README →分类
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)。
★ 1,123
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
★ 794
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.
★ 298