Plugins

3D Gaussian Splatting / NeRF / computer-graphics research skills — 18 AI skills (paper reader, method compare, experiment planner, code reviewer, training debugger, visualizer, MCP renderer…) over a curated 1011-method catalog, plus a stdio MCP server for agent-driven 3DGS rendering.

Let Claude Code or Codex do the thinking: understand the request, write a clear prompt for DeepSeek Harness to do the work, and review the result. dsh-baton runs your tests itself, lists what changed, and has a sub-agent check every requirement, so your main model only reads the result and decides. Codex waits in one call of up to 59 minutes, with no hook to trust and nothing to poll; you can change the request while it runs, and name the Harness model for a task. On big jobs it saves most of your plan's quota.

OpenPencil design preview and editing plugin.

Browser agent.

Bridges a DSH session and QQ over NapCat HTTP, forwarding agent replies to QQ and feeding messages you send in QQ back into the session.

Local Git-backed long-term memory for DeepSeek Harness with hybrid CJK/English retrieval, cited context, transactional sync, previews, and rollback.

Model-driven context compression (Active Context Pruning) for DeepSeek Harness: the model decides when and what to compress.

Shared real browser for DSH: a native Electron window the human can watch and take over, driven by the agent over CDP with 20 browser_* tools (open/snapshot/execute/fill/screenshot/download/auth), per-task session isolation, cookie persistence, CAPTCHA detection; self-hosts on plain dsh web without a desktop shell.

Study workspace for DeepSeek Harness: imports your own PDF, DOCX, PPTX and Markdown materials plus lecture recordings, turns them into source-cited flashcards, quizzes and open questions, and schedules spaced review with FSRS-6 in a built-in web panel. Imported recordings are transcribed with your own SiliconFlow, Groq or Gemini key; live classes can instead use an on-device SenseVoice engine that needs no key (about 239 MB on first install); requires DSH 0.2.0-rc.2 or later but below 0.3.

Moves an existing DSH session to another agent preset through a previewable five-section handoff, preserving the source session and either pausing the target for confirmation or continuing immediately.

Let DeepSeek Harness see and operate any program on Windows. The model looks at the real screen and drives the mouse, keyboard and windows itself. It is fast: several steps run in a single round trip, and a window can be focused before input lands, so the click hits the right one. It can do anything you would do on a desktop, including but not limited to CAD drawing, circuit simulation, and sending messages.

Three-tier memory control plane for DeepSeek Harness: persistent runtime context, searchable project documents, pluggable long-term memory, smart routing, supervised agent workflows, WebUI, and headless tools.

Drive a local or remote ComfyUI server from DeepSeek Harness: comfyui_run / comfyui_object_info / comfyui_workflow tools generate and edit images and videos, with a workflow library (graph extraction: per component / main flow / all), a load area with resolution auto-match, a live queue, SDXL and Wan 2.1 templates, a companion skill, and a same-origin media proxy.

The DeepSeek Harness plugin shop: browse, install, enable, and update dsh plugins from a git-auditable catalog.

Arknights: Endfield industrial-editorial theme for the DSH Web UI: cream paper, ink text, zero border radius, two switchable accent palettes (signal yellow / teal-cyan), plus optional marching-squares contour background, ENDFIELD watermark and boot progress plate.

Curated file-based long-term memory for DeepSeek Harness — human-readable markdown notes, one plain-file store shared across hosts (git-ignored when it lives inside a project repo), and a deterministic index cap enforced by ctx.tools.guard()

Diagnoses and repairs DeepSeek Harness on native Windows around the official persistent PowerShell and Workspace Write stack, creates the desktop shortcut, and keeps earlier Git Bash and BusyBox presets behind an explicit legacy setup. No WSL.

UltraCode-style multi-agent orchestration: a generatable, savable, governable, observable, resumable workflow layer.

Bridges a DSH session and QQ over NapCat HTTP, forwarding agent replies to QQ and feeding messages you send in QQ back into the session.

Desktop feature aggregate that installs the DSH Web UI collection, dshmarket, Codex Connect, and reasoning-effort controls at pinned versions.

Red-team engagement mode: send one target organization name; a planner session runs five execution roles (recon, asset triage, vulnerability discovery, exploitation, internal pivot) with configurable concurrency; preflight checks skills/resources; scoring uses four stages (recon, internet, boundary, internal) with server-side caps and privilege-wins dedup; findings stay in a local SQLite fact base. The persistent right-side console has nine pages and includes asset mapping, agents, sessions/tunnels, findings, score targets, reports, POC knowledge base and skill library. v0.15.2 adds automatic HTTP evidence/action records, batch ingest, scope check, tunnel pivot probe, data proof, cleanup ledger and T0-T3 asset admission to prevent scope drift. 59 redteam_* tools; 38 bundled skills.

Authenticated mobile gateway for DeepSeek Harness: connects the companion native iOS client over WebSocket for sessions, live events, tasks, goals, approvals, commands, and file transfers, with QR pairing and device revocation.

Lets the AI insert streaming-generated UI into the conversation or a side panel, written in TSX — already one of the model's native languages, so there is no JSON schema to teach it. Rendered without flicker, state kept across frames with no hard remount, and a click in the card driving the next chat turn. Inline is where streaming matters most; the side Canvas is the more agentic shape. Cards get agentic capabilities of their own — run bash, curl, call the model, read and write files.