Plugins

Plugin PWA para DSH — adiciona suporte offline, cache de service worker e capacidade de instalar como app.

PWA móvel completa para o DSH, construída sobre o dsh-mobile-gate: gateway de acesso remoto seguro e instalação na tela inicial (manifest e service worker), capacidade offline, gestos de toque (puxar para atualizar, deslizar da borda para voltar, pinçar para o tamanho da fonte), notificações push de conclusão do agente e layout touch-first — o desktop não é afetado.

O GPT planeja DAGs de dependência, os workers DeepSeek executam tarefas com paralelismo adaptativo e um revisor GPT opcional audita diffs incrementais de Git e conduz rodadas de reparo.

Recall de histórico de conversas para DSH: recuperação em três camadas (literal/difusa/semântica) sobre o texto original de cada sessão passada, totalmente local e offline — a IA nunca esquece o que você disse a ela. Instalação em um comando via `dsh.bundle.patch`, a camada semântica roda em uma thread de worker.

Notifies you about 11 configurable DSH agent events (task completion, questions, denied approvals, background subagents/goals/jobs, team tasks, context compaction, triggered schedules, plugin startup and permission changes) as browser Web Notifications through a bundled service worker, falling back to Windows toast or Linux D-Bus, with three silence levels and click-to-open.

Envie um projeto para a Cloudflare e publique seu plugin no npm — a primeira implantação não precisa de conta na nuvem e as credenciais nunca chegam ao modelo.

Um plugin de meta-agente nativo do modelo para o DeepSeek Harness: o modelo sintetiza workflows específicos da tarefa em tempo de execução a partir de cinco padrões de workflow agêntico (encadeamento de prompts, workers paralelos, roteador, supervisor, ciclo de avaliação) e coordena ferramentas e subagent

Safe detached DSH restart: /restart and /dsh-restart slash commands with native candidate styling plus a dsh_restart agent tool; a detached worker restarts DSH after 3 seconds without freezing the session, and Windows/macOS use a native Node helper built on the official appExit service.

DSH 会话管理插件：删除（回收站恢复/彻底清除/一键清空）、强制删除异常会话、恢复归档会话、统计、继续/暂停、打开日志目录、未读标记、工作区分组与排序、上下文压缩阈值。DSH session manager: recoverable trash, empty trash, force delete, stats, continue/pause, log folder, workspace grouping, compaction threshold.

Processes as little workers: how many, the busiest, the family tree and badges.

Generate images from chat by calling a fleet of local or LAN ComfyUI workers, with workflow templates, worker health checks and queue control.

Multi-channel notification plugin for DeepSeek Harness: dispatches in-page toasts in the foreground and PWA system notifications (Service Worker) or browser notifications in the background, with per-event toggles for task complete, approval request, question, plan review and errors, persistent notifications, and Web Audio synthesized alert sounds without audio files.

Knowledge base with a corrective acquisition loop for DeepSeek Harness: when the agent keeps hitting the same failure, a background worker fetches the web under a rate limit, distills the result into a staging area, and only a two-stage commit makes it recallable — pages without sources are refused.

Settings section that reports token usage: totals for input, output, cache read, cache write, reasoning and call count, with breakdowns by model, day, month and project plus a per-day trend chart for the last 30 days; history is rebuilt once on a worker thread and then kept current from live session events.

Adiciona um olho flutuante senciente ao DeepSeek Harness — injeta um kernel de domesticação que faz a IA verdadeiramente te compreender, com 11 skins dinâmicas de olho, modo fantasma e custo zero de tokens quando o modo IA está desativado.

Transforma uma necessidade declarada em escolha de plugin: uma skill de agente que consulta um catálogo de todo o tópico `dsh-plugin` (mais de 2600 repos, recrawled a cada 6 horas, descrições em chinês via Workers AI) por uma API de busca ranqueada e devolve o comando `dsh plugin add` correspondente.

Um plugin do DeepSeek Harness que transforma a sincronização git do anywhere-claude-mem em um peer do DSH: puxa memória entre máquinas no início da sessão e envia novos prompts/observações assim que chegam ao worker do claude-mem

Um plugin do DeepSeek Harness que integra o claude-mem: consulta, injeção de contexto, salvamento manual e ciclo de vida de sessão via a API HTTP de um worker local do claude-mem

Delegate DSH tasks to a paired LAN worker and drive it like a subagent (ACP over WebSocket).

Saves architecture and validated plans, runs native AgentTeams workers with approval, parallel coding and independent review, and summarizes progress and verification results.

Cloudflare Workers AI media tools for dsh - text-to-image, text-to-speech and speech-to-text. Per-model price badges, a native settings card, reuse of an existing Cloudflare account, and output files named after the model that made them.

Requires Claude Code installed and signed in on this machine. Delegates a self-contained coding task to the local Claude Code agent through the Claude Agent SDK, prepends the current DSH conversation history, and keeps the worker's intermediate tool calls out of the main context.

Fork of fourzkw/dsh-drawai that keeps the editable .drawio canvas and its two agent tools, and adds a second vectorization engine beside the original tracer: hierarchical color clustering with Bezier spline fitting and per-channel color precision, selectable per drawing task in three fidelity levels (measured about 18, 38 and 46 dB PSNR on the same 1920x1080 frame (the upstream engine scores about 26 dB on that frame)), with worker parallelism raised to half the logical cores instead of a cap of four. The original tracer stays the default and remains the right choice for whole videos, where the new engine produces files hundreds of times larger.

A DSH conversation workspace: turn actions, provenance quotes, local notes and summaries, in-conversation find, focus lock, and per-workspace command buttons.