DeepSeek Harness (dsh) plugin: prompt your home servers into existence through home-hosted — Gitea, Jellyfin, anything — and manage the panel, the entries and boot autostart from dsh.

Self-contained DeepSeek Harness (DSH) plugin for Provider/Auth login, model switching, image fallback, token/cost analytics, and same-port Web restart. Useful? A star helps.

Unified Harness TUI (ACP client). Self-Improvement TUI plugin of DeepSeek Harness. Everything Here Is Also A Plugin.

Turn any idea, plan, or codebase into a beautiful interactive diagram. An agent skill for Claude Code, Codex, and more.

Give an AI a research direction: it runs literature synthesis, gap validation, hypothesis formation and experiment design itself. 267 markdown skills form a research graph: 51 operations built from 216 atomic steps, any order, explicit backtracking; the plan is approved before it runs and interrupted runs resume. npx install, no runtime, no API key

Official Huawei Cloud plugin for AI agents — skills, MCP tools, safety guardrails, and cloud sandbox to help AI agents build, deploy, and operate on Huawei Cloud securely.

Local-first AI math visualization desktop app: draw, analyze, and explain geometry with GeoGebra, Tauri, React, Bun, and native tool calling.

DeepSeek Harness (dsh) 从 0 到 1 深度手册：安装/插件开发/性能调优/实测案例/同模型多 Agent 实测对比（中文 + 英文 PDF）

An LLM-powered multi-agent framework for simulating interactive, evolving story worlds.

专利侵权分析系统 —— 输入专利公开号，产出竞品侵权分析报告；同时打包成 skill，可被任意 agent（dsh, codex, claudecode 等） 调用。

开放的侧边栏底座，支持三方拓展注册新侧边栏页面。内置文件渲染编辑/终端/侧边对话/Git/子代理页面 ｜ Open sidebar foundation, supports third-party extensions to register new sidebar pages. Built-in file rendering/editing, terminal, side chat, Git, and sub-agent pages.

[dsh]为纯文本模型设计更强大的视觉工具箱：一行安装使用、粘贴图片直接识别、多张图片问答、截图到前端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.

DeepSeek Harness Desktop App: a local AI desktop workspace for DSH Sessions, projects, files, web research, plugins, and Office artifacts.

Background automation runner for DSH: isolated agent runs, script/HTTP/SSH/Docker runtimes, cost guard, notifications, heartbeats.

In-GUI skill hub for DeepSeek Harness (dsh): browse the full local skill catalog from the official ctx.skills registry (every root + third-party providers), toggle skills on/off, inspect bodies, surface frontmatter diagnostics, and scaffold new skills — p

dsh-agent-team gives DeepSeek Harness agents that don't reset: durable Members with their own memory, notes, and skills across sessions, rollovers, and restarts. You set the direction; agents coordinate through Channels and Tasks.

Reasoning-effort editing for third-party models in DeepSeek Harness: per-model thinking levels with a knowledge base + protocol inference, edited inside the official Models page card.

Hash-anchored read/edit/undo_last_edit tools for DeepSeek Harness (dsh). Every line gets a unique 3-char hash (A-Za-z0-9) that stays stable across edits; stale or ambiguous anchors are rejected, never fuzzy-matched. Undo persists across restarts.

Newmark Core for DeepSeek Harness：MemoryLab、ComputerUse、Agent API、NewMate 陪伴内核与 heartBeat 重启投递，五个独立开关，共用 ~/.Newmark 用户库。

The AI analyst that shows its work. Runs Python and R on your own machine, and traces every chart back to the code behind it.

Evidence-backed UI delivery for coding agents working on existing Web products: declared criteria, criterion-bound artifacts, findings linked to declarations, and repair guidance. Evaluator review does not replace human semantic approval.

Evidence-first reading for AI agents — turn articles, books and PDFs into traceable claims, evidence, source locations and knowledge maps.

Agent OS: the agent gets smarter on its own. We just hold the line: Interview-gated, staged evaluation, budgeted evolution loop. MCP server, 14 runtimes: Claude Code, Codex CLI, Gemini CLI, OpenCode, Copilot, Kiro and more.

DSH Plugin Radar — open-source ecosystem radar for DeepSeek Harness plugins: continuous discovery (21k+ candidates), k8s runtime validation (13k+ tests), 15-min snapshots; the catalog is a generated artifact — 开源 DSH 插件生态雷达：持续发现 2.1 万+ 候选、k8s 运行级实测 1.3 万+、15 分钟快照；插件目录为自动生成的产物