Bundle
Conversation tick rail and thinking-process fold for the DeepSeek Harness web GUI. Codex-style left rail by default; optional DeepSeek right rail in Settings. Click-to-scroll, eager history load, collapsed Think/tool rows.
Bundle
DSH extension suite: runtime injector, task-aware reasoning-mode routing preset, cross-session mailbox, agent teams, model delegation, skill manager, and plugin-manager UI.
Bundle
DeepSeek Harness 会话左侧虚线时间轴:横短横线波浪、当前消息定位(scroll-spy)、点击跳转、圆角预览 tooltip、可收起/展开。
Bundle
Enhanced model picker for the dsh web GUI: provider-tabbed left column with model list on the right, both independently scrollable, plus cross-provider search
Bundle
Guide Dog for DSH, powered by MiniMax — multimodal plugin: image/video/music/speech generation, vision inspection tools, voice mode, microphone voice input and real-time voice call mode.
Bundle
ADHD behavioral coaching skill for DeepSeek Harness. Guides readers through task execution - breaks tasks into micro-steps, manages overwhelm, provides launch rituals, calibrates time estimates, and recovers from self-blame.
Bundle
Graceful restart + client auto-reconnect + cross-restart goal continuation for DeepSeek Harness (dsh). After a plugin update dsh-phoenix restarts dsh at a safe idle boundary, keeps the browser page connected, and resumes a running goal so a task can keep evolving across restarts.
Bundle
对话滚动时间线(Scroll Timeline)导航条——user 消息快速跳转(自渲染 DOM,官方 client 通道)
Bundle
Renders images, video, audio, PDF and Office documents inline in the dsh web UI through a display_file tool, streaming bytes over a signed HTTP route with range support.
Bundle
Animated blue whale-maid and anime skins for the DSH Web GUI Deep diving status row, with eight continuously rotating actions and cross-version settings support.
Bundle
Aggregate and natively control DeepSeek Harness sessions across multiple remote dsh web servers from one pane: server registry, merged session list, history, prompt, cancel, rename, fork, model selection and approval/question answering.
Bundle
Minecraft Launcher built on DeepSeek Harness: full-screen launcher UI (root slot) with Microsoft device-code login, version download/install, and game launch from the DSH host process.
Bundle
A DeepSeek Harness (dsh) bundle: when `dsh web` is ready, print the full GUI URL and open it in your default browser. Cross-platform, dependency-free, fail-safe.
Bundle
dsh-crosstalk — cross-session messaging for DSH: any session on the machine can list and message any other, Claude Code-style
Bundle
Cross-session plaintext memory plugin for the DeepSeek Harness — deterministic BM25 recall, human-owned, no embeddings
Bundle
TaskSwarm (蜂群) — multi-agent task orchestration for DeepSeek Harness. Native port of TaskPlane (github.com/HenryLach/taskplane, MIT): waves/lanes parallel execution, git worktree isolation, PROMPT.md/STATUS.md task packets, file mailbox, cross-model review.
Bundle
Better DSH: archived-session management, task-stop desktop notifications, an update checker, model routing (keyword rules + allowlist-gated model_route), multi-task scheduled triggers (interval heartbeats & fixed-time tasks), and a DeepSeek-style message scroll nav for the dsh web GUI
Bundle
Cross-session usage & cost observatory for dsh — daily token charts, cache hit ring, 90d/1y heatmaps, model and project breakdowns, adaptive color themes and CSV export in the web UI
Bundle
DSH 定时任务与状态监控插件:cron 自动触发 Agent 执行任务、任务管理命令与设置页、系统与 harness 状态仪表盘
Bundle
Turn navigation rail for dsh web following the official TurnNavigator design · 轮次导航轨道(大纲/刻度/毛玻璃预览)
Bundle
Conversation indicator for the DeepSeek Harness web GUI: clickable markers along the transcript scrollbar that jump to the corresponding message or turn.
Bundle
A portable coding lifecycle for AI agents with deterministic routing across 25 skills, durable state, mutation-aware verification, specialized skill packs, lifecycle hooks, DeepSeek Harness plugin & consumed web UI, and an optional local request proxy.
Bundle
A DeepSeek Harness (dsh) plugin: orchestrates complex tasks across multiple models — a 'main brain' decomposes the task and dispatches subtasks to GLM / Kimi / Qwen etc. sub-agents by each model's strengths, with per-model token usage.
Bundle
Cross-session notebooks with model tools, typed Remote API, and a Web workspace