Plugins

Right-edge user-message navigator with an adaptive block layout that fits the available height, plus hover previews, keyboard controls, and click-to-jump navigation.

Personal memory sidebar and agent tools for Mory, with search, editing and optional GitHub/Gitee synchronization. Requires a Mory service installed and running on the DSH host.

A personal home page for DSH that gathers feature entry points and readings into a card wall: one-click DSH core updates, security review of a plugin before install, local Skill management, session status and more. The page is customizable, and any other plugin can add its own cards through the interface.

Design-review gate for DeepSeek Harness, a DSH port of Google's Elephant-Goldfish Model: a context-rich Elephant session drafts the design, then fresh, zero-context, read-only Goldfish reviewers stress-test it before implementation. Registers the `egm` plugin id; install one EGM bundle per profile.

High-performance fork of SAOS-3624/dsh-video-storyboard — install this or the upstream plugin, not both. Turns a video into addressable storyboard grids (numbered cells, a timestamp and transcript line per cell, audio envelope); needs Node 20+, ffmpeg/ffprobe on PATH, and a configured ASR endpoint when the file has no subtitle track.

Antu diagrams inside DeepSeek Harness: Host tools (antu_validate / antu_layout / antu_render) and an interactive chat card.

Codex-style dark interface for DSH on Windows, with navigation, project and conversation sidebars, and model and reasoning controls.

Browse Tencent ima knowledge bases in a DSH sidebar panel, preview PDF, Office, note and media files inline, and let the agent search and read them through five tools.

Switchable backends behind the native web_search and web_fetch, chosen per session from a composer menu or /setup-search and /setup-fetch: DeepSeek, Exa, Firecrawl, Tavily, Tinyfish, OpenAlex, Semantic Scholar and server-side model search for search; local HTTP with a private-network allowlist, the DeepSeek Fetch API, Exa, Firecrawl, Tavily and Tinyfish for fetch.

AI short-drama workspace for DeepSeek Harness, with a dedicated drama agent preset, 35 agent tools and 10 bundled skills covering outline, characters, script, storyboard and export.

Brings the WorkBuddy, Trae and Qoder desktop logins on this machine into DeepSeek Harness as OpenAI-compatible local endpoints, with an account pool, automatic account switching when WorkBuddy is rate limited, and a settings panel.

Old conversation is folded into short summaries by a side model before the window fills (on-disk ledger survives restarts and re-anchors after host compaction), so long sessions stop getting more expensive every turn — one real full-day session: 6 folds replaced 209 old messages and the live context stayed in the tens of thousands of tokens. The session model picks the model per subtask across six pools (economy/mechanical/main/hard/vision/review); or pick Auto and a small intent classifier routes each message itself, switching only past a confidence threshold to keep prompt caches warm. A three-line watermark ends in an automatic four-step handover (fork backup, handover doc, compact, wake) without losing in-flight subagents; /ctx-pause, /ctx-resume and /ctx-handover keep it manual when wanted. Optional Agent Teams mode adds teammates and a shared task board; /vision gives text-only models eyes via the vision pool; tiered verification sends bigger diffs to a tester plus an independent reviewer. Settings UI, READMEs and language preferences cover the same 11 languages. Bundles three skills: read-only MySQL/Redis verification, commit-message generation, and a requirements/design document convention.

Companion for DSH Notch that synchronizes session navigation and read state with DSH Desktop and Web.

Relays the ZCode CLI (the client-bundled coding agent) into DeepSeek Harness as a model provider: a resident app-server session injects the Start Plan account and signs each request with the OAuth plan token, so model requests burn ZCode Start Plan / Coding Plan quota directly — real streaming, image input, per-session resume, no API key.

Network proxy settings page for DeepSeek Harness: set a global HTTP(S) proxy with bypass hosts, or give each LLM provider its own proxy or a direct connection; changes apply on save without a restart.

AX-first macOS computer use for DeepSeek Harness: accessibility snapshots with stable refs, background input, Unicode typing, menus and apps, set-of-mark screenshots, on-device OCR and verified actions — 11 tools bridged to the macos-cu CLI.

Per-message delete for DSH: remove a user message, one reply step, or a whole assistant reply from the derived model context through the official surface-replace contract, and hide it from the visible transcript without rewriting the append-only log.

Serves the live opencode Go model catalog from the harness's built-in opencode-go provider route.

Evidence-first conclusion gate that cross-checks first-hand claims against a durable per-session tool-activity index, blocks unverified guesses and tracks blocked-versus-converted metrics.

Hot-switches in-process DSH fetch traffic among direct, manual HTTP(S)/SOCKS5 proxy, and ambient system-proxy modes, with no-proxy rules and optional proxy-environment export for newly spawned child processes.

ClineBot and ClinePass integration for DeepSeek Harness: dedicated settings page, live quota dashboard, in-UI key saving, curated and custom model selection, and a /cline command.

DSH plugin bundling the kimi-ppt skill: create, edit and export presentations as a locally generated .pptx with Pillow-rendered previews. Derived from the MIT open-kimi-ppt-skill.

During Beijing working-day peak hours (default 09:00-12:00 and 14:00-18:00) it blocks official DeepSeek requests or reroutes them to a configured target provider; off-peak traffic flows to official as usual.

Terminal coding agent for DeepSeek Harness with a full-screen alternate-screen UI, turn-aware session navigation, and a gated /ship workflow that takes one-line requirements through specification, TDD, and rerun acceptance checks.