Plugins

Infinite-canvas e-commerce visual workspace for product photography, virtual try-on, background edits, and video, synced live with the Harness conversation.

Loja de plugins independente e comunitária para o DeepSeek Harness: descubra, instale e envie plugins, ferramentas e extensões verificados. | Diretório de plugins independente e comunitário.

Auto-evolução contínua: estado do harness versionado, auditável e seguro para rollback (prompts, memória, skills, especificações de subagentes), refinado a partir das trajetórias das sessões, com portões de revisão e skills recarregadas a quente.

Connects DeepSeek Harness to OOMOL-managed apps and services, with progressive Connector Action discovery and execution plus an in-app panel for managing Provider connections.

Deixe qualquer projeto pronto para agentes de IA com um único comando. Detecção adaptativa de stack tecnológica (7 linguagens × 14 frameworks × 61 componentes), geração automática de AGENTS.md, esqueleto de documentação, CI/CD e infraestrutura de testes. Em uma frase: dê a qualquer projeto capacidade de desenvolvimento com IA.

Edit the global ~/.dsh/AGENTS.md rules from the web settings panel, live on save.

Read any page as clean main content: charset auto-detect (GBK/GB2312/UTF-8/Big5), noise stripping, compact text/Markdown, offset continuation, optional SPA rendering, batch reads and site crawling.

Quantitative R&D toolkit for DeepSeek Harness — 46 tools across six domains covering market data, indicators, factor evaluation, walk-forward ML validation, risk, options, bonds and fund simulation, with an end-to-end research pipeline.

Claude-style drag-and-drop/paperclip file upload with content sniffing, document-to-Markdown via Microsoft MarkItDown (built-in JS fallback), text inlining, and a read_document tool for agents.

Estratégias de retentativa e fallback de LLM baseadas em papel (role).

Local-first persistent memory infrastructure for DeepSeek Harness: bounded hot-memory bootstrap, explainable cold recall (exact + Chinese BM25), lease-lock transactional writes, read-only governance, and trajectory review. Pure Python + Markdown, zero ext

Arrastar e soltar no estilo Codex: arraste qualquer arquivo para a GUI web do DSH, ele é salvo em ~/.dsh-dropbox, e o caminho é inserido no compositor como um chip azul completo

Um segundo cérebro para o seu agente DeepSeek Harness — revisão por um modelo forte antes de chamadas de ferramentas arriscadas, além de 67 modelos a partir de uma única carteira. Sem contas, sem chaves de API.

Edit the host-wide global instructions (~/.dsh/AGENTS.md) from a dedicated Customize page in Settings - every session on this machine applies them.

Semantic retrieval, resource management, auto-recall (user + agent dual spaces) and session memory for DeepSeek Harness: memsearch/memfind/memread/membrowse/memgrep/memglob over viking:// URIs, memadd/memremove resource management, memqueue observer status, memcommit session capture, and memlearn skill playbook minting.

Transforme qualquer ideia sua em conteúdo promocional nativo para cada plataforma

Plugin de navegador real para o DSH: por meio do Kimi WebBridge, permite que o Agent opere o navegador já autenticado do usuário, fornecendo 13 ferramentas webbridge_*. / Deixe os Agents do DSH usarem seu navegador já conectado através de treze ferramentas Kimi WebBridge.

Execution-discipline suite for DSH with identical-retry interception, forced reflection, todo enforcement, memory deduplication, and experience-to-skill promotion (11 plugins + 6 skills).

Agent Client Protocol (ACP) server plugin for the DeepSeek Harness (dsh) — drive dsh agents from Zed and any ACP client

Migrate and import a whole Claude Code or Codex setup into DSH. Skills, slash commands, MCP servers, hooks, subagents and permission rules, with a dry-run moving estimate, a migration diff report and a post-move doctor; installs as a plugin exposing a movein_from_claude_code tool so the agent can do the move for you.

Installs a multi-agent novel-writing preset for DeepSeek Harness: one conductor agent dispatches five specialized subagents — world-building, plotting, character management, prose writing, and QA review.

Barrage-meme skill distilled from 22,771 real messages in the 6657 live room: wanjiqi-style banter, CS and DOTA cross-memes, player roasting and casting commentary.

Let agents search, read, and cite your local Zotero library: find papers, view notes and annotations, pull evidence by question, open the source document, and generate citations.

Technical-preview local graph memory for DSH and Codex: recalls owner-global and current-project evidence before each turn, writes USER and ASSISTANT records separately, and preserves project, session, actor, and source provenance for a visual atlas and cited knowledge pages.