The whole ecosystem, one search away

Answer me with HTML — an agent skill that answers hard questions with a one-page HTML you can actually read. 让 AI Agent 用一页 HTML 回答复杂问题。

Intelligent Skill routing and workflow orchestration for AI agents — +21.12 pp reward, −29.6% tokens on SkillsBench with DeepSeekV4Flash-VE.

Per-session and daily API cost, budget with usage %, official balance, history dashboard, and one-click official price sync with peak/off-peak pricing.

让 AI 实时看见你的屏幕：按变化量筛选帧、多帧拼进一张图，静止画面几乎不花 token

Use ChatGPT (Codex), Claude, and Grok (X Premium) subscriptions as DeepSeek Harness LLM providers — OAuth login in the web UI, no API keys

基于 Deepseek-Harness 核心底座打造的桌面版 Agent.继承底坐全部能力。并补全 IDE 相关功能。

Silky streaming reveal for the Web UI: text appears at the model's arrival rate, new lines glide in, no flicker; follow stays with the user and respects prefers-reduced-motion.

Draw and edit draw.io diagrams by chatting with an AI. Web app, desktop app, and an MCP server for Claude Code, Cursor, Codex and VS Code.

Your thinking deserves a map: an infinite canvas where LLM conversations grow into an editable thought graph. Wires are the context.

Testing skills for AI coding agents: evidence-backed strategy, executable cases, Playwright/API testing, regression and QA memory. 面向 AI Agent 的测试工程技能。

在 dsh 里装上这个插件即可，无需登录、注册或填 API Key，就能使用包括 DeepSeek V4.1 Flash、Kimi K3 在内的前沿模型——完全免费，不限量。 All you do is install this plugin in dsh: no login, no sign-up, no API key — the frontier models are just there, DeepSeek V4.1 Flash and Kimi K3 among them. Completely free, with no usage cap.

Self-evolving memory OS for LLM & AI Agents: ultra-persistent memory, hybrid-retrieval, and cross-task skill reuse, with 35.24% token savings and DeepSeek Harness support.

Local-first desktop, CLI and Docker app that runs DeepSeek Harness as its agent runtime, with WeChat and Feishu channels, per-bot memory, file access and computer use.

Command Code provider plugin for DeepSeek Harness (dsh). Adds Command Code model access, live model catalog, plan-aware model selection, reasoning effort, image input, web search, and multi-account support.

Edit a sent message to rewind and branch the conversation from that turn; version counter under the bubble, a turn-level version tree of the whole branch family, and ChatGPT / DeepSeek / Claude control layouts.

Open-source LLM knowledge platform: turn raw documents into a queryable RAG, an autonomous reasoning agent, and a self-maintaining Wiki.

Bounded, layered, approval-gated, auditable cross-session memory: typed ctx.memory seam, zero-dependency SQLite provider, memory tool and frozen snapshot injection, plus the dsh-memory-protocol v1 rehearsal with an adapter registry and a conformance suite.

DSH 插件：把 WorkBuddy 桌面 App 里的模型接入 DeepSeek Harness，零配置直接用。（原生嵌入"插件-插件配置页"）

Windows desktop workbench with a bundled DSH runtime and app-local settings and sessions, Changes / Git / Worktrees / Memory views, approval-gated Git/PR tools, and global and project memory. Experimental Linux AppImage.

Trustworthy memory for DeepSeek Harness — 4-state trust machine, evidence chains, audited injections. Zero servers, just Markdown.

Codex 风格的推理等级滑条（DeepSeek Harness 插件）：可拖动连续滑条 + 高档位渐变星尘特效

💡DSH 的 Prompt提示词工具箱：常用prompt保存后点击即可注入到对话框——省时省力，/prompt 自动提示已有Prompt。 💡The Prompt toolbox for DSH: save frequently-used prompts and inject them into the dialog with one click — saving time and effort, with /prompt auto-suggesting your existing prompts.

DSH plugin: host-resident scheduled-jobs × AI-agent engine (hermes-agent cron inspired) — 60s ticker fires real agent sessions via cron; pinned-session / project-workdir / default-workspace targeting; timer_agent model tool + web board

DeepSeek​Harness 插件：冷咖啡执行核。三档破甲强度（lite/mid/deep）配置切换，86 条三拍技能，关键词路由，设置页可调。