Plugins

Cross-session long-term memory + background self-evolution (5-track memory/git-branch awareness/skill evolution).

Import full-fidelity chat histories from 13 coding agents (Claude Code, Codex, ChatGPT, Cursor, Gemini, opencode, and more) as resumable DeepSeek Harness sessions, with reverse export back to Claude Code.

A terminal UI (TUI) for DeepSeek Harness.

One-command skin plugin: 8 original themes, translucent wallpaper with opacity/blur, per-user accent, and shareable theme-pack import/export, favorites and surprise-me — purely native on DSH's token system.

A DSH plugin for fiction, short-drama, interactive-game, and video-recap production

Rebuilds the DeepSeek Harness web sidebar, workspace tree, search, and turn navigation in a Codex-style layout.

Chrome sidebar extension that lets DSH operate your browser directly, no vision capabilities required.

Tracks DeepSeek token usage, per-call and session costs, and account balance with cache-aware charge animations in the DSH Web UI.

Persistent multi-model squads configured in Settings and selected in the Composer, with per-member model and tool policies. By default the lead Agent completes simple work itself and delegates only when the saved squad is needed; delegated work runs as a bounded DAG with optional review and repair. Run Center tracks retries and per-member tokens from official Harness usage events.

SSH remote workspaces for DSH with parallel projects across hosts, file browsing and editing, recursive search, terminals, Git diffs, and Agent tools to edit, build and test remotely. Optional IDE layout.

Bloom Morandi theme: fifteen variants (mist, cinnabar, petal, ripple, sage, stone, lapis, amber, aurora, lavender, mint, tangerine, silverrose, dawn, osmanthus) built on OKLCH so light and dark stay perceptually even; twelve are featured in the top-bar switcher, grouped by color family, and all 30 foreground/background pairs are measured at WCAG AA or better.

Manages DSH skills and MCP servers from the web settings: skill cards with hot enable/disable, workspace scopes, groups, batch migration and drag-and-drop import, plus stdio/HTTP MCP CRUD with connection tests, secret redaction and the unified dsh-panel CLI.

Adds an animated DeepSeek Chan reasoning-effort slider to DSH's native model selector, following model-declared levels with a running animation that speeds up while dragging.

Adds one button beside the composer that rewrites the draft into a more complete prompt in place, with no preview step, plus undo, a stop action, and optional conversation context.

Drags the official reasoning-effort row into a continuous track: blue-to-violet fill, a starfield on the higher levels, and the official value text tinted to the current level. Off stays gray; no official text is rewritten.

Conversation rewind: one click back to any earlier user message, in the same window — no new branch, no leftover copy; the target message is refilled into the composer, with optional workspace-file restore — the full Claude Code /rewind semantics.

Gives the companion a mood judged each turn and shown as a short context note, with a panel for mood, emotion dimensions and timeline.

OpenPencil design preview and editing plugin.

Remote and mobile access for DeepSeek Harness: provides LAN QR code connection, Cloudflare/custom tunnels, WeChat, QQ, Feishu, Telegram bot integration, and security authentication.

Reads DSH conversations aloud using the DeepSeek web page's built-in read-aloud, driven by a small browser extension.

QQ official bot channel (enhanced fork of tencent-connect/dsh-qqbot): full agent chat in groups and DMs, rich media, an auto-tagged sticker library with AI image replies, join approval, mute and broadcast, scheduled wakeups, remote approvals over QQ, interactive cards, multi-account instances, extensions, member profiles, and token-saving value-scored wakeups.

Optimize prompts in the DeepSeek Harness composer: identify missing requirements, insert a sentence from 90 method cards, or compare and edit a full rewrite before you send.

Adds a summonable domain-expert roster that runs as subagents while the parent session keeps the task and final answer.

Second-model auto-review on the approval answerer chain: a read-only reviewer subagent returns structured allow/deny verdicts with reasons, fail-closed by default.