Plugins

Visualizes Finesse 3 KatScript in the conversation and adds a drag-and-drop optical bench designer that generates the Finesse model. It scans every user and assistant message for KatScript or a Finesse Python cell and renders them in the background with the first Python interpreter that can import finesse (Finesse 3, NumPy and Matplotlib required; interpreter overridable with FINESSE_VIZ_PYTHON), keeping the code and figures under ~/.dsh/finesse-vis.

Import your own picture as the DSH window background, with an adjustable scrim that keeps every panel and label readable.

Daily auto check-in for MiniMax Code, WPS Lingxi, Baidu DuMate, AStudio, Qoder, Trae, Doubao, Huawei CodeArts and Tencent WorkBuddy: reads each app's own local credentials so nothing has to be pasted, supports multiple accounts per service, and lets you add any other site yourself by importing a JSON definition the agent wrote for it. Streak tracking, per-service schedules, collapsible sidebar cards. The Doubao service can also read its login cookies from the local Chrome, Edge, Brave or Doubao app cookie store (Doubao hosts only), and a custom service sends requests to whatever http(s) URL its JSON names.

Export and import a DeepSeek Harness Desktop configuration, including installed plugins, plugin settings, MCP entries, and user skills. Credentials and API keys are not exported.

Skill manager with content-addressed version history: snapshots, per-file and line-level diff, rollback, zip export and import, and per-skill enable or disable.

Local Markdown notes panel: import any local folder, browse its Markdown tree in the sidebar, edit files with auto-save, and search across every imported folder. Shows read-only Git context for each file — status, diff against HEAD with per-line change bars, and line blame — and exposes six notes_* tools so the agent works on the same folders. Files stay where they are on disk; the plugin never commits, stages or checks out.

Mendeley-style paper library for DeepSeek Harness: import PDFs, read them in the panel with highlights, notes and questions, turn AI answers into note cards, compare 2–6 papers, build a typed relation graph (manual, AI-discovered, or citations parsed from PDF references), and keep everything as plain files in a folder any cloud drive can sync.

Connects Penpot to DSH across two independent channels with 9 tools: 5 MCP tools (execute_code, high_level_overview, api_info, export_shape, import_image), 2 browser-free REST tools (penpot_read and penpot_write to create files, pages and shapes or edit attributes without an open tab), plus penpot_status and penpot_control; supports official SaaS, local and self-hosted endpoints with auto-detection and config migration from DSH, Codex, Claude, Cursor, Gemini and .mcp.json, an isolated Chromium launcher, and a five-tab control panel.

Local-first AI literature desk for DSH: import and parse PDFs (MinerU APIs or on-device pdf.js), read original/bilingual text with in-margin annotations, ask grounded questions whose citations jump to the page, and build per-paper or library knowledge graphs; eight agent tools expose the same library.

Windows environment doctor: audits 30 developer tools, installs the missing ones, manages the user PATH, and exports or imports an environment share code so a team keeps identical setups.

Import, preview and export JSON accounts for dsh-codex-subscription with duplicate detection and explicit full-backup confirmation. Requires dsh-codex-subscription 3.2.6 or newer.

Three-tier memory (personal, project, session) built on the Hy-Memory engine, with relevant memories injected before each step. Ships seven memory tools (search, add, list, get, update, delete, forget), a settings panel with per-tier lists, editing, change history and duplicate cleanup, real token accounting per write, session summaries written by the engine at session end, and a user profile refreshed from recent memories. Memories can be exported to and imported from MemHub. Needs Python 3.11+ once to install the engine, or uv, which fetches 3.12 itself; uninstalling keeps the stored memories.

Imports chats captured from chat.deepseek.com by the repo's companion Edge extension (loaded unpacked in Edge) into DeepSeek Harness as new sessions; thinking is saved as a sidecar thinking.md, and trimmed, branched or very long chats also get the full transcript.md.

Adopts DSH sessions created outside the running window (IDE/ACP clients, other processes) into their matching Workspace, and imports local sessions from other agent harnesses (pi) as native, resumable DSH sessions with sidebar sync/import actions and idempotent re-import.

Imports DeepSeek usage exports (ZIP, CSV, JSON) locally and renders token and cost trends, per-model and per-API-key breakdowns, cache savings, input/output composition and usage spikes. The interface is Chinese only.

Records token usage per turn into two ledgers, imported history before installation and new events after, and shows exact per-bucket totals, per-model and per-session breakdowns, and day/week/month filters in a sidebar panel.

Personal reading log panel: track books as want to read, reading or finished with dates, page progress, ratings, tags, notes and excerpts; yearly reading stats; covers looked up from Apple Books, Google Books and Open Library; Goodreads and Douban CSV import and CSV export; and five agent tools: bookshelf_list, bookshelf_stats, bookshelf_add, bookshelf_update and bookshelf_add_excerpt.

An agent-writable spreadsheet editor inside DeepSeek Harness with formulas, formatting, CSV/Excel import, and export.

Import Claude Code, Codex, WorkBuddy, Cursor and Trae conversation history into DeepSeek Harness as resumable sessions, with readable titles and one workspace per source.

Web panel for the DSH AI history importer — a floating button and a three-column wizard to preview conversations, pick which ones to import, and file them into workspace folders.

Desktop notifications for DeepSeek Harness when a task finishes, with the final assistant reply as the notification body, plus optional approval and question alerts and synthesized or imported sounds. Derived from ltao0829/dsh-task-notify; install this fork or the upstream plugin, not both — they claim the same task-notify bundle row.

Career knowledge base vault with ten agent skills for setup, capture and import, audit, JD resumes, interview prep and review, plus Feishu interop.

Elysia's memory plugin for dsh. One shared, human-editable MEMORY.md across every session: two-disk mirror, history snapshots, cross-process write lock; entries tier between the main file and a searchable archive by hit frequency; retrieval is keyword co-occurrence plus BM25. Nine sections (persona, requirements, corrections, lessons, methods, requests, sessions, method library, ingested docs) plus a dedicated self-identity section for a character's own self-cognition, injected above the persona. Ships an opt-in memory pack (packs/elysia: 61,903-char identity + 2,482-char persona, distilled from 1,696 officially-confirmed voice lines and checked against a 112,175-line game-dialogue corpus) that is off by default, backs up before writing, only touches identity/persona, and can be uninstalled. Also a skills library and a sticker library (you import your own images; none are bundled) that sends a fitting sticker at the right moment. On by default: a text bubble with her avatar after each reply, which costs one extra small model request unless the agent already announced (voice.bubble: false turns it off). Opt-in voice playback needs a local GPT-SoVITS engine (about 27 GB, installed separately, NVIDIA GPU required; the plugin downloads about 200 MB of weights) and is Windows-only; the automatic second-drive mirror is Windows-only too (elsewhere set mirrorPath, otherwise there is no mirror).

One image behind the whole DSH shell. The image layer sits at z-index -1 and the shell's two --dsw-* tokens are repointed at translucent tints, so the picture shows through the frame, sidebar and composer. Ships a bundled default picture so it works with zero configuration, plus a floating panel with five sliders, presets, upload, and an SSRF-guarded URL import; changes persist to a local settings.json and the client self-heals when the SPA replaces its stylesheet.