Bundle
DeepSeek Harness (dsh) bundle that routes the harness through the OpenLLM gateway — an `openllm` provider on the in-box pi-ai adapter (via the local daemon gateway) plus the OpenLLM MCP server. Pure config; install OpenLLM first (see README).
Bundle
Multi-provider quota, balance and Token-cost dashboard for DeepSeek Harness Web, with a draggable widget, usage analytics, local pricing and route diagnostics.
Bundle
Attach local files to the conversation context: a composer chip adds files whose content is injected into the model context (agent/pre-step), with a removable ✕ chips strip above the input.
Bundle
DeepSeek Harness plugin: Claude, Codex, and Gemini via Antigravity OAuth through a local CLIProxyAPI instance
Bundle
Private plugin imports for DeepSeek Harness — import from private git repositories or local files (tarball upload / folder picker) from a first-class Settings entry. · DSH 私有插件:私有仓库 + 本地导入,设置内独立入口。
Bundle
Local-first, evidence-backed session retrospectives for DeepSeek Harness
Bundle
Trigger GitHub Actions workflow runs and local test pipelines, stream their logs back, and on failure hand the tail of the log to DeepSeek for a Markdown root-cause diagnosis.
Bundle
工具调用描述 / 模型思考 / 回复输出三个语言通道:跟随界面语言、强制指定或关闭,一条运行时指示实现,不改动预设与工具 schema。· Language control for tool-call descriptions, model thinking, and replies: follow the GUI language, force a fixed tag, or off — via one runtime-context directive, no preset or tool schema touched.
Bundle
DSH Desktop 桌面小组件:每日时间安排(周期重复 + 起止时间 + 进行中高亮 + 倒计时便签)、目标设置(进度百分比 + 自由流程图工作台)、日期规划(跨天任务月历 + 流程图截止日联动)三张可拖动、可缩放、自动记忆位置的毛玻璃悬浮卡片,带今日面板聚合视图。支持数据导出/导入、自动快照、可选自动备份文件与删除撤销。纯前端 vanilla DOM 实现,localStorage 持久化,零依赖。
Bundle
Adapt ERP: learn your ERP through the browser and build private local knowledge in DeepSeek Harness
Bundle
A dsh policy plugin that gates kubectl writes by kubeconfig context: hard-deny irreversible verbs outside local clusters, ask for the rest.
Bundle
Git-native, auditable long-term memory for AI agents
Bundle
DeepSeek Harness 本地模型插件:设置里独立的「本地模型」页,首条对话自动拉起 llama.cpp,空闲 5 分钟自动卸载释放资源。
Bundle
Find the doc your agent just wrote. Lists the DSH workspace's Markdown, images and video in the sidebar, ranked by relevance to the current conversation, with inline preview — and hands the same ranking to the agent as a tool, so it reads one doc instead of five. Zero model calls, zero network.
Bundle
DeepSeek Harness plugin: drive your local Adobe Photoshop from the agent — batch subject cutouts (Select Subject / Remove Background) to transparent PNGs, plus a raw ExtendScript escape hatch. · 让 AI 直接驱动本机 Photoshop 批量抠图。
Bundle
DeepSeek Harness host plugin: serves a configured workspace/media folder over the web server under /media, so any conversation can display local images by referencing http://<host>:<port>/media/<relative-path>.
Bundle
One-click DSH Web background switcher: gradient presets (aurora/sunset/emerald), local-image upload, Bing daily wallpaper (4K/UHD, region, daily auto-update), opacity/blur/fill controls, light streaks and particle effects.
Bundle
DeepSeek Harness 的独立创造模式工具集:把运行时检查与动态插件生命周期做成宿主层普通插件,绕开官方 @deepseek-ai/dsh-tool-cordis 的进程级注册表占位,使创造模式预设可以被复制
Bundle
Local OpenAI-compatible model-server discovery + tiered reasoning-metadata resolution for DeepSeek Harness (dsh).
Bundle
Living memory for DeepSeek Harness — self-tending knowledge base: nightly patrol, temporal decay, RRF hybrid recall, knowledge graph, telemetry. Built by 暖暖 (NuanNuan).
Bundle
Privacy-first browser-local Chinese UI and content translation for DeepSeek Harness Web
Bundle
Per-project runtime environments for DeepSeek Harness: auto-adopt or create a project-local Python venv (.venv_local/python) and wire in the toolchains/env vars for the runtimes each project uses.
Bundle
Model-facing analyze_image tool for the DeepSeek Harness: multi-modal image understanding via any OpenAI- or Anthropic-compatible vision API, with 8 analysis modes, local path / http(s) URL / data URL input, and a Web UI hint that guides image-incapable models to the reliable local-path route.
Bundle
Local-first vision for text-only DeepSeek Harness agents: route image understanding to a local OpenAI-compatible vision model, return structured JSON evidence (summary / OCR / layout / semantics / visual / uncertainty).