Plugins

Shares one set of Markdown memory files between DSH and WorkBuddy: project memory, user memory and the user profile are injected into the session context, while daily notes stay out of the prompt and are read, appended and archived through the tools. Six tools (status, read, search, append, edit, prune) write back through a cross-process lock, revision check, backup and atomic write, and a panel in the left rail and the right sidebar edits entries, sections and whole files.

Bridges a memory-nebula store into DSH: a panel inside the Harness UI to search, edit, pin and forget memories, plus three agent tools to check, search and revise them.

Browse, filter, search by ID, delete, restore, export, and import every local session. Its HTTP routes have no DSH access check, and they can delete and restore local sessions.

Nested session folders for the DSH sidebar: create folders per workspace, nest them and drag to reorder, move sessions by drag or context menu, click a folder activity count to open the matching sessions, and tag sessions with a header tag filter. Undo, rename, archive, search and keyboard navigation work on the tree.

Native DeepSeek Harness surfaces for markets and finance: a full page with 11 live quotes (SSE, SZSE, ChiNext, Hang Seng, Nasdaq, S&P 500, Dow, COMEX gold, dollar index, BTC, ETH) and sparklines, a market-cap heatmap of up to 96 A-share industry boards with a constituent drawer, movers, an eastmoney news feed, 25 plain-language articles and a 293-term glossary; the complete OpenFinLens terminal (MIT, vendored, served by the Host) embedded as the default tab; and a floating quote card with a searchable instrument picker and a boss key that also hides the optional always-on-top desktop window. The Host fetches upstream server-side with a 30 s snapshot cache, per-part timeouts and stale fallback: no API key, no browser CORS workaround.

Pick the text, code, and terminal font stacks from the fonts installed on this system, replacing the shipped plain-text font fields with searchable, ordered stacks.

Research-style problem solving in four gated stages: record sources by retrieval tier with local before web, turn each shortfall of existing tools into a gap that needs evidence, score candidates against weighted metrics with a deterministic engine, fuse or improve the weak ones, then iterate on measured deltas. Also organizes a directory into human-facing and machine-facing trees.

Writes engineering decisions down the way DSH documents its own — every non-trivial change leaves a Markdown note under .agents/notes/<lifecycle>/<class>/ holding the problem, the decision, the rejected alternatives and the consequences, committed to git and reviewable like code. It supplies the workflow for that: five tools (note_search, note_read, note_write, note_verify, note_skip), an end-of-turn hook that asks a code-changing turn to either write a note or record an explicit skip, the tree/format/archived checks, and the write-notes-like-deepseek skill bundled in the package and mounted by the plugin. A sidebar board that renders the notes into four views (architecture baseline, timeline, rejected proposals, decision list) comes with it; the notes themselves stay plain Markdown.

Agent browser for DeepSeek Harness built on playwright-core with two visibility modes, where hidden sessions for private research close themselves after 45 seconds of idling and visible sessions open in a real Edge or Chrome window on request, exposing eight browser_* tools (search, open, read, click, type, screenshot, close, status) and a left-sidebar panel with engine state, live sessions and an activity feed.

Cross-domain search and A-share data for DSH: arXiv, Crossref, GitHub, Hacker News, Hugging Face, Product Hunt, plus stock quotes, klines and announcements.

Adds four tools that query a local SAG Wiki index through the installed SAG CLI: semantic search, exact or regex match, and index status or update. Needs the SAG CLI on PATH, and semantic search also needs a JEV model configured in SAG; the model chooses which directory to index or drop (default: the session working directory).

Local-first knowledge base for DeepSeek Harness: workspace Markdown notes with provenance, review status, BM25 search, and four km_* tools.

Adds a Markdown outline and full-reply search to conversations, with section references, reversible turn hiding, and new sessions from selected turns.

Zero-credential Outlook automation for DSH Harness on Windows: the AI agent drives your LOCAL desktop Outlook client via COM: search/read mail, drafts, reply/forward, calendar, address book, rooms, free/busy. No Graph API app registration, no SMTP passwor

Run Google Antigravity CLI (agy) as DeepSeek Harness subagents, with Gemini web Deep Research and parallel/team modes.

Deep research for DeepSeek Harness: multi-query search, source fetching, evidence extraction and a cited evidence report, through the host ctx.web service. · DSH 深度研究插件：多查询检索、正文取证、交叉印证，产出可引用的证据报告。

Evidence-based research workspaces with archived sources, knowledge graphs, exact citations and exportable reports. Experimental alpha. Needs Node 24.9 or later, uv and Python 3.13, plus a one-time setup step (setup-engine.mjs) that copies the engine and runs a locked uv sync; pnpm must also be allowed to run the build scripts of onnxruntime-node and protobufjs.

Sidebar skill hub: browse and search DSH skills, import from a folder or GitHub, and read full SKILL.md bodies rendered as Markdown. Imports are copied into ~/.dsh/skills (existing names are overwritten only on opt-in), skills there can be moved to a .trash folder from the detail view, and GitHub imports download the repository archive from codeload.github.com. It uses the same package name (dsh-skill-hub) and mount id (skill-hub) as cheshireez/dsh-skill-hub and hoshino114/dsh-skill-hub, so only one of the three can be installed.

Local-first RSS/Atom reader with full-text search, bulk read marking, on-demand AI summaries and native reading companion. Uses the native better-sqlite3 module, so approve its native build when the installer asks.

Lets the agent read the app, title, URL and text of the window in front through the macOS Accessibility API, with opt-in on-device screen memory it can search.

Zhihu inside DeepSeek Harness: hot, recommendation and follow lanes plus in-site search, formatted question and column bodies, a per-item discussion that runs as a real Session, and one-key export to Obsidian through its REST API. Reads with your own signed-in cookie, kept in the credentials service.

Zotero bridge: search, read, add, update and trash items in a local Zotero library, read PDF annotations and notes, pull indexed full text, and find related papers by DOI. Needs Zotero 7 or later with its local API enabled; the first write triggers a Zotero authorization prompt (the key is stored in plugin-data/dsh-zotero/auth.json) and permanent deletion asks for confirmation. Finding and adding items query OpenAlex, Crossref, arXiv, PubMed and Open Library. Uses the same package name (dsh-zotero) as Vncntvx/dsh-zotero, so only one of the two can be installed per profile.

Local jot-down notes for DSH: one Markdown file per note, stored under ~/dsh随手笔记 by default (portable home path, no drive-letter assumption). Redesigned card UI, trash bin (deletions restorable for 30 days), custom tag management with stable per-tag colors (create tags ahead of use, delete one everywhere), compact/comfortable density, adjustable font size and line width, flat quick-scan list, full-text search, Markdown preview, autosave, batch deletion, zero-dependency Office text extraction, and AI write-back from conversations. Heavily reworked from dsh-knowledge-lite; pick the old library via the in-app root picker to migrate.

Session trash for DeepSeek Harness: move cold sessions out of the sidebar into a recoverable trash, restore them within the retention window (30 days by default), or delete their logs permanently. A trashed subagent tree moves and restores as a whole, a shared DSH toast offers undo, and the settings page supports search, sorting, multi-select batch restore and emptying the whole trash.