Plugins

Session-archive layer for DSH. It injects one per-workspace Markdown file into the system prompt on every turn, searches past session transcripts with AND keywords, an optional time window and a workspace filter, and recovers the images and documents those past sessions carried by returning their original local paths or copying them to a chosen directory. It also reports index health: version, entry count, cache usage, frequent sessions and sessions stored in an archive format it does not recognise. Keyword search only, no embedding service.

Puts a domain bar under the session header — a domain groups skills and tools and toggles as one block, so one click loads or unloads every member. Hovering a chip lists its members (skills, then tools) in a height-capped panel that scrolls. The right end of the bar is a compaction-threshold counter (− 5 +, 100k tokens per step) that rewrites the live compaction engine policies, so the compaction trigger line changes on the next turn without restarting dsh; a degraded fallback turns the number amber and is reported in the snapshot. Settings maintains domains and members with search, skill/tool tabs, all/selected/unselected filters and a copyable AI grouping prompt. Tool removal uses tools.restrict plus a guard; hiding a skill re-registers it with modelInvocable false, so it leaves the model catalog while /name still works. Sessions of another preset are left untouched.

Cites one specific message from another conversation: the @ menu inserts a chip, and at send time the quoted text is injected as untrusted background; a conversation_history tool also lets the model search and read other sessions of the same workspace. The @ menu searches the indexed sessions of every workspace (only the model tool is limited to the current one), and its HTTP routes (/dsh-message-cite/api/…) are guarded only by a marker header, not by a DSH access check.

Read-only session dashboard for DeepSeek Harness over the local ~/.dsh data: a sidebar overview of every session (tokens, estimated cost, turns, tool calls, model mix, daily activity, searchable and sortable session table) and an in-conversation Dashboard view that shows the current conversation turn by turn with per-turn tokens, cost, timing and tools. Zero dependencies, no network.

Connect a locally installed agy CLI to DeepSeek Harness 0.2.2-rc.1, with separate thinking levels, quota display, and Harness-owned tools. Community fork of dannndouglas/dsh-antigravity-acp, beta, verified on Windows x64 only. Needs the agy CLI signed in with your own Google account; installing makes new chats default to Agy models (messages go through agy to Google), switches web search to the agy provider and replaces the built-in compaction. Do not enable it alongside other forks that register the agy-local-acp provider.

Sidebar artifact shelf that collects the images, videos, files and links sessions deliver, deduplicated by SHA-256 content hash, with five filter tabs and counts, keyword search, video thumbnails, a lightbox, manual link saving, image paste, upload up to 25 MB, one-time backfill of past session logs, and a save_artifact tool the model can call. Copies each collected file into ~/.dsh/artifacts (up to 50 MB per file, 200 MB per video).

Codex-style compact sidebar for DSH: one top row holds the logo, an inline session search and the menu button; the plugin, market and automation entries fold into a popover where a + pins them back into the sidebar; pinned sessions get a collapsible section that survives collapsed projects. Client-side only, no dependencies.

DeepSeek Harness plugin: AI research toolkit — model release radar, model benchmark & community report, and AI news digest (4 tools + 3 skills).

Whole-disk file-name search for DSH with a self-built cross-platform index, agent tools and a Web panel; no Everything required. It indexes your home directory by default; the first content search also builds a local full-text index (SQLite in the platform cache directory) of text and source files there (by extension, up to 1 MB each, 200,000 files) and of your recent DSH session messages; locator_export writes a SQLite copy of the index to any absolute path it is given, replacing an existing file when overwrite is true. The engine is a prebuilt Go binary shipped for six platforms (source in engine/), and the plugin makes no network requests.

340-entry code-animation style library, 8 prompt templates and 5 renderable code templates in a sidebar panel, plus agent tools (awkit_search / awkit_get_style / awkit_render_template) so the model can pick a style and render a template during a turn; content ships inside the package, no extra download.

AI-assisted research workbench with editable step workflows, on-demand skill binding, a live execution graph and in-project document review (needs a local Python with python-docx, python-pptx, openpyxl and PyMuPDF), while keeping existing projects on their original configurations. Requires DSH 0.2.2 or later.

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.

DeepSeek web search with its own API key: a left-sidebar search page and a deepseek_search tool that every model in the profile can call, falling back to the DeepSeek key already configured for the model provider. It registers its own tool and routes instead of replacing the built-in web_search and web_fetch providers, so an existing search setup keeps working.

DeepSeek Search API and Exa queried in parallel and merged into one URL-de-duplicated, cross-source-first web_search result list for DSH. Needs a DeepSeek and/or Exa API key (either alone works); it takes over the default web_search provider, and each query goes to every service you have a key for.

Lightweight fork of DDDMUC/dsh-free-search: multi-engine web search and fetch with automatic fallback, failure cooldown and API key rotation; takes over DSH's default web_search/web_fetch providers. Cannot be installed alongside DDDMUC/dsh-free-search (same package name and bundle row).

Read-only QQ Mail over IMAP: list, search, and read messages; the settings page verifies the account before saving. Needs IMAP enabled on the mailbox and its 16-character authorization code (not the QQ password); the server is fixed to imap.qq.com.

Standing GitHub-first open-source check: a system-prompt section makes the agent extract 1-4 keywords on every new request and make one cached, rate-limit-aware github_search call, so the answer can list up to five reusable repositories with stars, language, license, last push and topics.

Read-only tools for mj7.cn: search standards, products and materials, plus HS-code lookup, Incoterms, trade documents and CNY rates across 6 tools. Network-only, no local writes.

Adds one agent tool (read-only on your transcripts) that searches Claude Code, Codex and DSH session transcripts and returns each match with its resume command. Needs ripgrep (rg) and zstd (zstdcat) on PATH and keeps a plain-text cache of DSH sessions under ~/.dsh/cache/history-search.

Five Brave Search tools — web/news/image/video results, token-budgeted page context, cited AI answers, local places, and autocomplete/spellcheck — plus a brave search provider for the built-in web_search tool. Needs a Brave Search API key (BRAVE_SEARCH_API_KEY; some endpoints need a higher plan). Based on Brave's official Search API skills; it uses the same plugin id as BuffMcBigHuge/dsh-brave-search, so install only one of the two.

A YAPI documentation panel for DeepSeek Harness with search, multi-tab, field tree, and copy features. Needs your own YAPI server and account.

Obsidian vault tools: 13 tools for listing, reading and searching notes, creating, appending and editing by line range, deleting to the vault's .trash folder, frontmatter CRUD, tag queries, image insertion, batch operations, and renaming notes while rewriting the wikilinks that point at them; writes are atomic and keep CRLF and BOM.

Local full-disk knowledge base: indexes documents from C:/ and E:/ into a SQLite FTS5 trigram index over filename, body, and path, with a searchable DSH sidebar panel, no-keyword browse, usefulness/topic tags, and a token-efficient kb agent tool. Windows only; building the index needs a system Python 3 with PyMuPDF and python-docx (plus python-pptx and openpyxl for PPTX/XLSX), and no prebuilt index ships with the plugin.

Sends deferred MCP tool definitions as an index of names, parameter signatures and one-line summaries grouped by server, with tool_details returning a full schema on request and call_tool running the real tool. Reading a schema or running a tool does not change the model-visible tool list, so the prompt cache is not invalidated.