플러그인

Qwen mode for DSH: manages local GenieX and Alibaba Cloud QwenCloud providers, normalizes thinking and sampling, detects model capabilities, and shows per-turn latency and decode speed. Its bundle patch replaces the permission plugin's preset table with reply-only, read-only, workspace-write and danger-full-access (the last two as in stock), so any custom presets are overridden.

Rewrites a draft prompt against the current project: a composer button, slash command and agent tool ground the rewrite in the workspace stack, structure and conventions.

Turn the seam between the sidebar panel list and the workspace list into a divider you can drag, snapping one row at a time, with the panel list scrolling when squeezed.

Sorchron Study Board, a study workspace plugin with pomodoro timer, task management and activity heatmap for DSH harness. Records stay in the browser's localStorage (JSON export for backup) and the plugin makes no network requests.

Draws an icon in front of every session row in the DSH sidebar, decided from the session itself: keyword rules on the title first, then the session content (title, first user message and tool names), then an optional one-shot model verdict, then a workspace fallback. 445 Ant Design outlined icons are inlined for offline use, and the rules, colours, keywords and row indent are editable in a settings page.

Reads EPUB, TXT, Markdown and HTML from the workspaces registered in dsh in a right-sidebar tab, restores the last reading position, and collapses the whole sidebar with Esc to return to the conversation. No runtime dependencies and no build step.

Creates DSH workspaces under a configurable base directory, links several external folders into one workspace, and relocates a workspace without losing its conversations. Its managed_workspace tool lets the agent create, adopt, link, move and unregister workspaces (moving relocates the whole folder and leaves a link at the old path when it has conversations), and its HTTP routes (/dsh-managed-workspaces/api/...) have no DSH access check beyond a marker header.

Sidebar workspace tree: create nested sub-workspaces at any level, start a session on any level, and pin a session to the top of its nearest folder.

Native Google Antigravity agents loader and subagent orchestration engine with model selection and Web UI settings integration. Loads agent definitions from ~/.agents/agents and the workspace's .agents/agents; the selected main agent's instructions go into the system prompt, and a matching agent's instructions are prepended to DSH's own subagent and spawn_teammate calls. Settings are written to .agents/agents/settings.json in the workspace.

Composer for the DeepSeek Harness Web GUI: bracket and quote pairing, wrap-on-selection, closer skipping, empty-pair backspace, and a completion popup over draft words, language tables, workspace files and model ids. Full-width brackets typed through a Ch

Delete sessions into a recoverable trash, clean up sessions orphaned by deleted workspaces, and group workspaces into categories.

A New Session switch that puts the conversation into a throwaway Git worktree under the project's worktree pool (`<project>/.dsh/worktrees` by default), plus a panel to inspect and discard the copies.

DeepSeek Harness (DSH) Web session organizer: group sessions by custom tags, archive/restore in one click, browse archived sessions. 会话整理插件：标签分类、归档/恢复、已归档浏览。

Context-budgeted local memory for DeepSeek Harness: fixed ~600-token cache-friendly injection (session/daily snapshots), three-stage sleep consolidation, spaced repetition, temporal validity, subagent-driven L0 mental-model rewrite, typed memories (fact/s

A session-aware code pane for the DeepSeek Harness right sidebar: browse, edit and run workspace files, see what the Agent changed, and step through every recorded edit. 代码面板 for DeepSeek Harness。

Back up and restore dsh-mnemon memory and skill components (memory spaces, project documents, runtime memory, skill files, skill data) to S3-compatible storage or WebDAV.

A desktop pet for DeepSeek Harness: an always-on-top character and a roster panel that show what the watched conversations are doing, with seven animations, Workspace grouping, subagents drawn under their parent, and one click to open a session. Ships Windows, macOS (Intel and Apple silicon) and Linux window binaries in the package, so installing runs no install scripts and needs no build step.

Read Xiaohongshu recommendations, browse Baidu Tieba threads and nested replies, and quote posts when replying on NGA from DSH workspaces.

Live view of the agent machine's desktop in the DSH Web UI, with sound, relayed through DSH's own login. Take control for a CAPTCHA or QR login, with clipboard and file transfer, also from a phone. Needs cua-spacesd from a Cua desktop image on the same machine.

Open the full DeepSeek Harness running on your computer from a phone browser, with QR pairing over LAN HTTPS and shared sessions and workspace; cross-network access needs your own HTTPS entry or a self-hosted relay (no public relay is provided). Connection and auth code is adapted in part from saya-ch/dsh-mobile.

Keep SSH, WSL and Docker projects in the native DSH sidebar. Group directories by environment while choosing full remote DSH or lightweight local Agent mode per project. Manage shared full-backend connections together, keep lightweight connections independent, and selectively sync local Skills with difference previews. Aimed at the Windows desktop client with Linux, WSL or Linux-container remotes that have Python 3 and Bash (macOS and Linux hosts untested); lightweight SSH needs an existing SSHFS mount, and Docker has not yet been run against a live daemon.

Cold-start boot animation for DeepSeek Harness, with an unlock gate in front of the workspace: PIN, Windows Hello or an authenticator code, all local.

Scans a workspace for plaintext API keys, flags files inside git repositories, and reports findings masked so no full secret is ever printed.

Saves per-workspace dev commands behind a header button, starts and stops them as process trees, and exposes four tools so the agent can list, start and stop those saved commands and read their logs (it cannot add or change commands).