Find the right DSH plugin
for your next workflow

Audit each finished assistant turn with an independent reviewer model and steer the agent to fix failed output, with at most 2 review rounds per turn.

White-box AGI architecture exploration: metacognition (self-cognition loop), continual learning (knowledge flywheel), world model (condition space, spatiotemporal memory graph), self-improvement (bootstrap discipline), zero-LLM white-box pipeline, and auditable trust guardrails.

Evidence-driven goal verification plugin for DeepSeek Harness. Locks goals via /ultragoal and verifies completion against command exit codes and generated artifacts, preventing the model from falsely reporting task completion.

Replaces the "Deep diving..." turn-status label with rotating meme-worthy phrases, with typewriter and gradient effects.

Workspace/chat context menu for the DSH home page: pin, rename, open in file explorer, archive, fork, copy, and open in a new window.

Keyboard-first command palette for the DSH Web UI.

Adds an "About" settings page to the DeepSeek Harness web interface, showing the running DSH version and recent release notes.

Session-based task board in the sidebar: drag sessions into todo/doing/review/done columns, create sessions with model and reasoning-effort selection, trash with restore, notes, export/import.

Composer expand/collapse toggle for the Web UI: a ⬆/⬇ button in the composer tool row grows the input to a tall 70vh writing view for long drafts.

Input-bar prompt optimizer: rewrites drafts with 6 strategies × 3 languages plus custom instructions, optional goal/todo/compaction-summary/tool-result and chat context, a confirm dialog, last-5 history and three-tier settings persistence.

A Claude Code-style reasoning-effort slider for the DSH Web UI: stepless drag, snap-on-release, a WebGL fire trail, and real, working thinking-effort control for any custom third-party model or provider.

Runs open-mcp-apps inside DSH: every MCP app gets its own sidebar container with a separate workspace, session, and App mode, an agent status strip under the app, and inline app rendering in ordinary chats.

Edge breathing border showing DeepSeek peak/valley hours, with flowing light and scheduled push reminders.

Vault button beside the DSH composer: save keys, servers, phone numbers, addresses and URLs, auto-collected from conversations, password-protected with WebDAV backup; click to insert, Ctrl+click to send.

Drag-to-resize the chat content width in the DeepSeek Harness web UI: a handle on the column right edge overrides the built-in 748px width (default 1040px, 520-2400 range, persisted per browser, double-click resets).

Adds searchable filtering to the model selector by provider, model name, and model ID; spaces act as wildcards.

Codex-style workflow auto-collapse: finished turns fold into a single "processed in Xs" row leaving only the final answer; tool calls and think blocks collapse into live-summary chips that follow streaming; expand level by level, fully reversible on uninstall.

WorkBuddy-style skill picker: a button beside the composer opens a searchable list of installed skills; picking one inserts the official /skill-name gesture, so the skill loads with your message.

Clickable file paths in DSH replies: Codex-style inline open, reveal in file manager, and a mentioned-files chip list at the turn tail.

One upload button plus drag-and-drop files into the conversation as local paths: save to the project's uploads/, path text into the input box, works with any vision tool.

HUD status panel: Git status, MCP servers, skills, model and token usage in a floating side panel.

One-click enter/exit Plan mode for the DSH web input bar, a quick-click shortcut for /plan.

Add independent opacity controls for the sidebar, message panels and composer in dsh web.

In-session question navigator for the DSH Web UI: a dot minimap on the conversation edge (left or right, configurable in settings), one dot per user question — hover shows the full question text, click jumps to it.