Plugins

Agent governance kingdom for DeepSeek Harness: territories, role bindings (bind/unbind/session with model/agent identity), and a plan→assign→execute→review task loop where Worker claims never auto-complete (Claim ≠ Fact), with a local GUI operations console.

DeepSeek Harness bundle registering one skill that turns long-form production (academic papers, industry analysis, business commentary) into a 9-role pipeline: T1 literature / T2 data / T3 case scouts running in parallel, T4 analyst, T5 writer, T6 critical companion, T7 auditor, T8 finalizer run by the coordinator, T9 peer reviewer — across 6 phases with triangular evidence verification, a 23-check M-gate, a G0-G14 audit including a Chinese AI-trace gate, peer-review scoring with journal matching, and 4 human checkpoints. Installs with `dsh plugin add lunheng-article-pipeline` (package.json#dsh.bundle.patch plus a lib/index.js entry that registers the skill); ships role cards for T1-T9, templates and 11 zero-dependency verification scripts, with five-language READMEs.

Anthropic Sans, Serif, and Mono fonts for the DSH Web UI, with Source Han fallback for CJK.

Adds an `auto` permission preset between workspace-write and danger-full-access: a classifier grants routine sandbox escalations once, while dangerous or uncertain requests still go to a human.

Gives text-only models vision: forwards user images to an OpenAI-compatible vision model and shows the descriptions in a Web UI right panel.

在 Web UI 中一键管理 DeepSeek Harness (DSH) 插件：查看、实时启停、安装/卸载、环境管理、插件市场。bundle 与非 bundle 插件全覆盖。

DSH Web UI 插件应用商店：目录浏览/搜索/一键安装/兼容徽章/已装列表。A plugin store for DSH Web UI — catalog browse, search, one-click install, compat badges, installed list.

DeepSeek brain + automatic image transcription: attach images in the GUI and each one is transcribed via the official deepseek-v4-flash-vision-exp by default (a pure-text V4-Pro brain can see images), with any OpenAI-compatible VLM or local Ollama as alternatives.

Claude-style skin with a warm-black canvas, clay accent, and serif UI that follows the native light and dark themes.

A visual workbench for reference-image generation, cropping and component-wise Tripo 3D modeling, with per-task paid-operation approval and local asset previews.

Pools every WorkBuddy account signed in on this machine into one auto-failing-over provider, serving OpenAI Chat, OpenAI Responses and Anthropic Messages from the same pool, with model aliases, usage statistics and scheduled credit automation.

Directed fuzzing driven by an LLM agent: from a target repository and a bug (CVE description, patch, crash trace, or file:line), it runs a PLAN, IMPLEMENT, EXECUTE, REFLECT loop in which the model writes Python input generators, until an input triggers the campaign's stderr-pattern oracle or the campaign stops.

LLVM static-analysis plugin that builds whole-program bitcode for C/C++ projects and runs kernel-analyzer (KAMain) reachability analysis on it, providing kanalyzer_* tools to the agent and a ctx.kanalyzer service to other plugins.

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.

DeepSeek Harness 默认 System Prompt 管理插件：在 Web GUI「设置」里浏览、检索并覆盖最终装配进每轮会话的系统提示词。

General-purpose LLVM static-analysis plugin for DeepSeek Harness: builds analysable bitcode and runs kernel-analyzer (KAMain) reachability analysis behind ctx.kanalyzer

Thinking-loop guard for dsh: observes the llm/stream waterfall and breaks a model that degrades into a loop. Detects two per-call shapes (reasoning-only calls, restated-material calls) and re-fires instead of latching; plus two mid-stream breakers that en

Local literature knowledge-base RAG: 10 tools (kb_ingest, kb_search, kb_rag, kb_zotero, kb_dedup, kb_clear, kb_fetch, kb_scope, kb_stats, kb_status), hybrid BM25+vector+reranker search, cited QA with clickable DOI links, all-local bge embeddings over a single-file SQLite index. Needs Python 3.9+ with pymupdf, faiss-cpu and sentence-transformers; the `npx dsh-kb-rag-install` installer sets those up and pre-downloads the model.

Draws every branch of a conversation as a clickable tree beside the chat, with favorites, custom icons and colors, branch merge and split, rewind-aware layout, and Claude Code branches that keep their memory.

Heartbeat loop for DeepSeek Harness: every 20 minutes (by default) the agent wakes on its own to keep a local profile of your interests and preferences, search the web for things you care about, and keep what it finds. When it has something worth sharing, it sends a short package of notes to the sessions you link it to. A set of rules in code - quiet hours, busy windows, a daily limit, a cooldown - decides whether it may speak at all, and the agent in that session decides whether to actually say anything. Windows only.

One settings panel managing MCP, skills, memory, subagents, prompts and sessions; customize scene combos to switch the whole environment; the Agent can also operate this plugin for you.

Provides a better model experience, including but not limited to: filling model parameters in multiple ways, improving model compatibility, remembering reasoning efforts, subagents following the parent's model and reasoning effort in real time, and AI self-adjusting reasoning effort.

Project file explorer in the details column (multi-select, drag-move, upload, download, rename, trash, system-open) with an in-session read-only preview tab for Markdown/HTML/JSON/CSV/notebook/PDF + code highlighting, a live model throughput badge, and a multiline GoalBar.