Plugins

A permanent DSH plugin that bundles a developer workbench, an in-session conversation tree, and a plugin manager: build and run an LVAL project, browse its code, and keep per-program version snapshots with rollback; edit, retry, or branch any message in place, with message micro-versions; a feature manager plus a global-plugin library whose entries each carry an enable tier; cross-dialogue memory, one-shot temporary chats, and model collaboration; five network-permission tiers, mixed-model routing, a security audit, and browser control through a companion extension.

Adds quick installation and switching for workbench templates in DSH Desktop.

Enterprise workbench for DSH: manage AI employees, knowledge bases, skills, MCP servers and DSH plugins from a running session.

Codex-style Git workbench: workspace-scoped changes, diff, stage, commit, guarded branch operations, graph history, fetch, fast-forward pull, and upstream push through official plugin APIs.

A workbench-quality docking system for DeepSeek Harness Web plugins

A desktop-style project and AI workbench for DeepSeek Harness

Trusted office suite for government/enterprise work by Beijing Caizhi Technology (深知可信智能): three skills — trusted consulting (policy/regulation Q&A with citation markers + provenance HTML), trusted search (authoritative policy/standard retrieval with traceable HTML + clean Markdown), and official-document writing (draft/rewrite/Word/red-head delivery); all interfaces go through the dknowc trusted workbench MCP (Bearer auth), products land in the session workspace, one-time key setup persists for later sessions; ships on npm as dknowc-dsh.

Ecommerce operator workbench: CSV batch preview with marketplace column adapters, reproducible profit/six-dimension scoring, public product-page snapshots, Chinese skills, and a replaceable store-policy KB.

Self-editing desktop workbench for DeepSeek Harness: a full dsh web replica with an edit mode in which the agent modifies the workbench (patch layers, plugins, UI) with hot reload.

装在DeepSeek Harness里的网络运维工作台，集成多种工具用来管理网络设备、定位问题等。A network operations workbench built into DeepSeek Harness, integrating multiple tools for managing network devices, troubleshooting problems, and more.

Agent-native static security review workbench with scan artifacts, finding triage, and SARIF/JSON exports.

Chinese display layer for DSH skills: the / menu groups skills under Chinese categories with Chinese names and summaries, while the invocation token stays the English /name and no SKILL.md is edited. Also fills missing summaries from install sources and moves uninstalled personal skills to a recycle bin.

Turns a video, article, PDF, or text into a narrated video, with an in-app workbench for settings and project history, per-scene images, TTS, metadata, and ordered API fallback.

Single-cell RNA-seq workbench usable from the Harness UI or from agent tools: imports h5ad, 10x, loom, Seurat RDS and archive files, runs QC, filtering, normalisation, highly variable genes, PCA, neighbour graph, clustering, UMAP/t-SNE, marker genes and cell-type annotation, offers resolution scans and saved marker panels, and exports h5ad, result tables and reports.

GEO and bulk transcriptomics workbench backed by a local Python and R engine: search and download GEO series, import your own counts or TPM matrix, then run QC, filtering, normalisation, batch correction, PCA, differential expression, GO/KEGG/GSEA enrichment, immune infiltration, survival and prognosis, signature mapping onto single-cell data, and circRNA, miRNA, lncRNA, fusion and alternative-splicing modules.

A batch workbench and six-step wizard for the PDL engine: group raw well files by well, merge them into delivery tables, and export GeoEast-ready load packages, with run records and reference libraries.

DSH 插件开发测试工作台：写插件时装上就能用。生成脚手架、七层检查、沙箱四阶段测试。装不上的原因（inject 写错、output schema 不合法）会直接告诉你在哪一层。

ZenTao workbench for DSH: load a ZenTao browse-page URL into a panel, multi-select bugs, tasks and stories, and hand them to the current or a new session with description, recent comments, screenshots as real image attachments and other files saved locally; when the agent is done it writes comments and status transitions (resolve, close, activate, start, finish and so on) back into ZenTao, one item or a batch, from the panel or through five registered agent tools (bug write-back verified end to end, task and story forms share the same code path).

Automatically discovers the local Magpie gateway to sync chat models, enables Codex and Gemini image generation, and configures image sources for eligible workbenches.

Disk, CPU/memory/GPU, listening-port and token-usage cards with a full-page zoom; runs as a workbench module or standalone. The port card works on Windows only and the GPU card needs nvidia-smi.

Paper libraries and literature management tools with nested collections, PDF imports, local metadata, reading, translation queues and optional ink annotations. An extension of GGboya/dsh-paper-reader 1.6.1 that reuses its default data directory (~/.dsh-paper-reader/data), so back up the library before migrating and enable only one of the two in a profile, because tool names and routes clash. Needs Harness 0.2.2-rc.1 and Node 24.9 or later; the ink annotations use tldraw, which needs a tldraw license key that you obtain and enter yourself.

Project workbench for DSH: groups sessions by project (workspace) in a panel with project cards and session lists, applies a project's default preset, model and reasoning effort to new sessions, scopes memory per project on request, previews AGENTS.md/CLAUDE.md read-only, and groups the sidebar by project at startup.

Runs a complete HR workbench inside DSH — a 3D office, recruiting pipeline (resume, interview, written test, score), employee roster, files, attendance, performance, training and analytics — with the site’s AI assistant answering through the model DSH already runs.

SSH workbench for launching remote agent CLIs with durable sessions, terminal, file editing, Git worktrees and local port forwarding. It drives the local OpenSSH client (macOS/Linux; remote Linux with GNU coreutils, tmux optional) to run commands, edit files and forward ports on any host from ~/.ssh/config, with host-key checking defaulting to accept-new; the last 512K characters of each terminal's output are saved under ~/.dsh/remote-agent/terminals. It uses the same package name and mount id as zbzbhs/dsh-remote-agent, so the two collide if installed together.