Plugins

Region & sticker image skin for the DSH (DeepSeek Harness) web UI - paint the window, center, sidebar, welcome, right panel and composer with your own images, GIFs or videos, add two draggable stickers, and let the interface take its colour from your wall

Claude Code Desktop 风格的 DeepSeek Harness 桌面版界面插件

Make Enter approve a pending DSH approval without clicking — DeepSeek Harness client plugin (审批卡自动聚焦，Enter 批准 / Esc 拒绝)

蓝湖（Lanhu）设计稿读取插件 —— 把设计稿的精确色值/字号/字重/圆角/坐标/文本喂给 agent，替代靠截图估算

Side-by-side model comparison for the DeepSeek Harness Web UI: send one prompt to 2–4 models in sibling sessions forked from the current one, watch the answers stream in columns (tabs on phones) with latency, time to first token, tokens, and cost, then co

One private Feishu group per DSH workspace with real-time two-way message synchronization.

Cloudflare Zero Trust access for DeepSeek Harness (DSH). Access 认证、Tunnel 与 DNS 配置，无需公网 IP。

Keeps a project's documentation in step with its decisions on DeepSeek Harness: the same append-only decision log and derived design snapshot, kept fresh in-process instead of by a hook process.

OpenCode gateway provider for DeepSeek Harness: the Zen pay-as-you-go plan and the Go subscription, with their settings UI

Graph runtime capabilities for the DeepSeek Harness: register LangGraph compiled graphs as DSH tools, plus a graph-driven routing agent.

Lets the model trigger compaction itself at a safe point via a compact_now tool (works mid-turn), plus a context_status tool reporting real token usage against the session's actual context window.

Guards session logs from malformed model tool calls (empty id/name, non-string arguments) so a bad call can never make a session unloadable.

2D engineering prints (PDF/PNG/JPG) of plate parts to noBS CAD scripts and STEP files: modelling skill, CAD tools over the noBS CAD MCP engine, packed native print probe, and a 2D → 3D panel in the Web UI.

DeepSeek Harness plugin for Agent-Playbook: multi-agent claims, isolated git worktrees, and enforced acceptance checks. "Done" is an exit code, not a claim.

独立本地记忆插件：JSONL 记忆条目、每轮 runtime-context 注入、local_memory_search/local_memory_remember 工具、设置面板管理页。不依赖 Mnemon。

Readable transcript export for DeepSeek Harness: turn any Session into a Markdown / HTML / ZIP transcript with reasoning blocks, tool calls and results, images and usage — from the Session header or the /export-md command.

Turns course, lecture, tutorial, meeting, and talk videos into structured study notes: it extracts the audio track with ffmpeg, transcribes it with Whisper, then writes notes with a chapter outline, emphasis markers, and a quick-reference card.

Adds a diagram button under every finished reply in the DSH Web UI: the configured model writes a single-file HTML page with inline SVG and the right sidebar renders it in a sandboxed iframe, with diagram, source and original-text views, a per-session replay history that is served from a disk cache instead of calling the model again, redraw, and save to a .html file.

Personal dsh preferences: a tunable companion to the official compaction engine (threshold, retention, summarization model/reasoning, turn-end compaction), llama.cpp model import for the Models page, and tab/notification helpers (status-light favicon, bro

Turn a dsh session into a shareable, redacted idea and deliver it to DeepHub friends. Built on DeepSeek Harness.

UI-level access gate + process-wide agent tool brake for DeepSeek Harness: shared session, strict 60-minute idle lock, native settings module. NOT server-side authentication.

Cut LLM costs: a Jev (System One) classifier vets each turn against a declarative policy and recommends the subagent model route, so routine work runs at flash rates while the main model keeps the hard parts; explicit /route trigger, runtime delegation-capability gate, credential redaction, and offline policy replay over the verdict log.

Cross-session long-term memory: captures durable facts from each turn, auto-associates them by shared entity and tag, and recalls with BM25 plus spreading activation over the link graph.

Uses a configurable system-prompt section to request a chosen reasoning language (Simplified Chinese by default), and expands thinking rows by default while preserving rows the user manually collapses.