Plugins

Batch recursive extraction: magic-byte format detection (disguised extensions), nested archive auto-unroll, multi-password pool with per-layer dynamic discovery, SFX/split-volume pairing.

What's up - a zero-maintenance status board for your sessions. Scans every conversation on the host, extracts a goal + one-line status per session (multi-provider LLM, fingerprint-cached), surfaces half-done, unanswered and recent work in a sidebar panel, and jumps you back into any session with one click.

Read-only CAD tools that inspect, extract and export DWG/DXF drawings, including SVG and PNG previews and DXF conversion.

Skill de busca do Cânone Taoísta (DaoZang): pesquisa por palavra-chave ou semântica em 285,117 blocos e extrai o texto original exato com números de linha e marcadores de ocorrência. Configura o espaço de trabalho em um comando a partir do conjunto de dados Godners/DaoZang.

Automação de navegador genérica com seis ferramentas (browser_open, browser_click, browser_type, browser_extract, browser_screenshot, browser_eval), referências @e a elementos, e backends duplos Playwright-headless / CDP (conecte ao seu próprio Chrome).

Webhook de encaminhamento de SMS para o DeepSeek Harness. Apps de telefone (SMS Forwarder, Tasker, ou qualquer HTTP POST) enviam mensagens para um endpoint HTTP local; o plugin as armazena como JSONL e expõe ferramentas sms_recent / sms_search para que o agente possa ler códigos de verificação SMS durante tarefas. Extrai automaticamente o primeiro OTP de 4–8 dígitos de cada mensagem, suporta filtragem por palavra-chave e funciona via LAN ou Tailscale.

Kit de ferramentas de áudio/vídeo local no navegador para o DSH — extraia quadros, capture miniaturas, comprima imagens e converta clipes em GIF com FFmpeg.wasm.

Memória pessoal local e auditável para DeepSeek Harness: preferências, convenções de projeto, fluxos de trabalho e lições de erro persistidas como um arquivo JSON com changelog no workspace, com onboarding, extração automática de convenções de projeto e lições respaldadas por evidências.

pi-web-access para o DeepSeek Harness: busca na web multiprovedor com fallback automático (SearXNG → Tavily → Brave → DuckDuckGo sem chave) mais extração de conteúdo de URL, integrado à costura web para que a ferramenta web_search integrada seja alimentada pelo piwa. Search engin

Ponte na nuvem do Browser Use para dsh: execute tarefas reais da web — abrir páginas, clicar, digitar, preencher formulários e extrair dados — pela API do Browser Use.

Kit de tradução para agentes DSH: segmentação de frases, extração de termos e glossários, QA origem-destino (números, unidades, colchetes), guias de tom e uma memória de tradução durável por workspace.

Memória de pistas de eventos entre sessões para o DeepSeek Harness: extrai automaticamente pistas de tarefa/conversa e hábitos de linguagem do usuário de cada turno para um banco global persistente de pistas, e depois reinjeta o contexto lembrado ao detectar troca de assunto (correspondência por palavra-chave ou vetor).

Plugin de migração de sessões entre ferramentas para o DeepSeek Harness (dsh): importação de alta fidelidade, continuação, extração de conhecimento, exportação bidirecional e redação de privacidade

Servidor de ferramentas hospedado via MCP: extração de faturas e extratos bancários com verificações aritméticas no código, conciliação de livro-razão em centavos inteiros, conversão de PDF e tabelas, transpilação de dialetos SQL e sondas de alcance da China continental a partir do ponto de vista da rede da China Mobile.

Extract text from an image or PDF, reading a born-digital text layer directly and falling through to a configured OCR engine for scans.

Pull invoice number, date, parties, tax IDs and the amount/tax/total triplet out of text, then verify that amount plus tax really equals the total and flag documents that do not reconcile.

Open a page, wait for it the way it actually needs, extract the readable article, and take a screenshot. Playwright is optional: when it is absent the tools fall back to a static fetch and say so in the result, because a page whose JavaScript never ran means something different from one that rendered. Content is chosen by scoring candidate subtrees on prose density rather than on tag names, so a container loses to the article inside it instead of winning by containing more of the document.

Pack a directory into a deterministic tar, read an archive's contents without extracting it, unpack while refusing every member that could reach outside the destination, and verify what came out against what went in by SHA-256. No external dependency — the tar format is written and read in this plugin. Extraction is deliberately more permissive on reading than on writing, because a reader's job is to report what an archive says, while a writer must never emit what it cannot read back. A tar has no central index, so the walk tracks whether it reached the end-of-archive marker: without that, a half-file checksums fine and reads as complete.

Thesis and empirical-analysis workbench that drives IBM SPSS from the conversation: spss_check (environment self-check), spss_variables (list .sav variables with labels, types, measurement levels, case counts), spss_data (sample case rows to inspect missing and outlying values), spss_run / spss_run_file (execute SPSS syntax or an .sps file, relative CD and GET FILE paths auto-rebased), and spss_analyze (one-shot frequencies, descriptives, crosstabs with chi-square, t-tests, one-way ANOVA, correlation, linear regression). Results come back as structured tables extracted through OMS. SPSS 25-31 is auto-detected; the bundled MCP server is zero-dependency stdio.

DSH 插件：会话菜单多一行「继承」。把跑久了的会话机械提取成一份交接单（任务、最近的指令、改过的文件、失败、命令、待办），在干净的新会话里接着干——不调模型、不带旧历史，预设默认一并继承。 | DSH plugin: an "Inherit" row in the session menu. Extracts concrete anchors (task, instructions, files edited, failures, commands, todos) from a long session into a handoff, then continues in a clean one - no LLM call, no old history, preset inherited.

DeepSeek Harness document-routing tools: sniff a file's real format and a PDF's page layout, then extract with the right pipeline — layout-aware Markdown for multi-column papers, MarkItDown for everything else, images for scans.

Composer attach button for DSH Web: multi-file picks become inline draft capsules, files are stored under the workspace uploads root with an auto-extracted UTF-8 .txt sidecar (txt/docx/xlsx/pptx/zip/odt, zero dependencies), and sent messages carry only the file name — never a raw path.

Paper library and reading workbench: arXiv search, a local plain-file library (metadata / PDF / extracted full text), and three-level reading notes (overview / understanding / critique) kept as markdown beside the PDFs; seven model tools plus a web panel.

Native headless and visible Chromium browser automation agent for DeepSeek Harness with DOM tree extraction, screenshot capture, and built-in SSRF protection.