Plugins

Cross-agent, local-first persistent memory plugin for DeepSeek Harness (DSH), powered by Mnemon. It shares long-term memory across Mnemon-enabled agents and adds runtime memory, searchable project documents, semantic recall, knowledge graph, and a Sidebar UI.

Read-only Molio knowledge base tools: list vaults, browse the file tree, full-text search and read documents, served over the local Molio daemon HTTP API, which must be running. Published on npm as dsh-plugin-molio.

Three-tier memory control plane for DeepSeek Harness: persistent runtime context, searchable project documents, pluggable long-term memory, smart routing, supervised agent workflows, WebUI, and headless tools.

Paper reading workbench: library + PDF reader + tutor-style companion. Answers cite clickable page numbers that jump back and flash the exact passage; select-to-ask without leaving the paper; bundled strict-tutor preset (reading plan, section coaching, graded quizzes tracked across sessions). With MinerU configured (self-hosted, no signup / mineru.net cloud token): scanned PDFs become readable, formulas become click-citable (one click sends the LaTeX source into the chat) and searchable (QK^T hits directly), plus a per-page formula panel; optional embeddings endpoint adds semantic recall for plain-language questions. Rename/delete topics and papers — deletes go to a recoverable .trash with a batch-clear flow for non-empty topics; reader with scroll/single-page modes, rightbar-fullscreen safe, one-click path copy and translated-PDF export; in-place original ↔ Chinese toggle (babeldoc, zero preinstall). Transcription and search run locally by default — documents never leave your machine; only when cloud MinerU, an embeddings endpoint, or a translation endpoint is enabled does the corresponding text go to the service you configure.

Puts the Markdown documents, source files, images and video that already exist anywhere in the session workspace into the DSH sidebar, ranked by relevance to the current conversation. The default lexical mode matches your recent messages against title, summary and body locally with IDF weighting (BM25) — no model calls, no network, nothing leaves the machine. The list comes from scanning the workspace rather than from a recent-files list, so restarting DSH or opening a new session does not empty it. Results are organised into a three-tier reading order (primary / supporting / related) with a verifiable reason on every row — which field matched, which document cites this one — and one click opens an in-place preview: Markdown as rendered text, relative-path images actually drawn, source code with the host's own syntax highlighting, video streamed over HTTP Range. The same Context Pack is exposed to the agent as a knit_docs tool. Later versions added read evidence and lifecycle tracking (attribution is frozen at the moment of reading), pin / exclude (exclusion applies before retrieval, and is undoable), relation evidence (references / imports / tests, with line numbers) and an incremental index reused across restarts. Since v0.23 there is also an optional hybrid mode: it is off by default and only runs once you configure an Ollama or OpenAI-compatible embedding provider yourself. When it runs, what leaves the machine is your query text plus each candidate file's title and summary — a Markdown summary is an excerpt of the body's first paragraph (at most 60 characters), a code file's summary is its workspace-relative directory, and an image or video contributes its file name; full bodies and absolute paths are not sent, and a loopback provider keeps everything on this machine. Since v0.24 it also associates uncommitted changes: a read-only git status (fixed argv, no shell, whitelisted child-process environment) combined with the same reference / import / test / mention evidence shows which files a change is likely to drag along, and it is off by default. The benefit of semantic retrieval still awaits a real-provider run, so no recall improvement is claimed.

File upload with color-coded attachment cards (session-isolated storage, sha256 dedup, TTL sweep) plus a content-sniffing read_document tool for PDF/DOCX/XLSX/TXT.

One-click optimization of a raw instruction into a professional prompt: three output styles, situation-aware role/task/goal profiling, multi-sample selection scored by a model judge, self-iterating learning (session memory + smart defaults + user overrides), /template for 22 sub-scenes with zero model calls, input-box ✨ one-click optimize/undo, prompt_optimize tool, auto-optimize hook, a runtime status page, a settings panel (dsh 0.2.0) and auto-detected zh/en documents.

Turns local markdown and text documents into a queryable knowledge base with hybrid semantic and keyword search, citation verification, and source injection.

Creates, reads, and edits DOCX, PDF, PPTX, and XLSX through `/documents`, `/pdf`, `/presentations`, and `/spreadsheets`; renders pages to check layout, and turns selections in the sidebar preview into edit requests for the session. Python 3.10-3.13 required.

Windows only: the agent edits documents inside the Word, Excel and PowerPoint (Microsoft Office or WPS Office) windows you have open, through the applications' automation interface, so changes appear live and you can edit alongside; it reads structure, applies batches of edits, renders pages to images to check layout, and saves or exports PDF.

Import SillyTavern/TavernAI character cards and world books, save them as local Markdown lore documents, and generate novel prose from your prompts with the world settings as reference.

Knowledge base as a canvas in the right sidebar: notes are nodes, and nine tools let the model read, write, link and remove them. A node can carry pictures and documents, and reading one returns their text — Office files extracted in place — while pictures can be handed over as images.

Project documents and long-term memory as plain Markdown in a dedicated Obsidian vault: six mem_* tools (search, read, write, log, brief, admin), one budgeted recall injection at the first step of a session, and automatic distillation of completed turns. Obsidian does not need to be running, and the vault stays readable with the plugin uninstalled.

Global cross-session todo list in the sidebar that the person and the agent both write to: ten global_todo_* tools add, batch-capture, update, attach documents and links to, append progress notes to and complete items from any session, and each item can be handed to an agent session in one of four modes with the outcome recorded on the item. The list is a single JSON file.

Parse PDFs and documents into structured Markdown with MinerU. Uploads files to the MinerU cloud; no offline mode.

Drive WordCraft from the agent: create documents, insert and style text, build tables and headers, track changes and comments, then save as DOCX or convert to PDF, ODT, RTF, Markdown and more. Exposes WordCraft's command ids and its MCP server. Requires the matching ArtCraft app CLI installed locally; it is not bundled.

Drive PhotoCraft from the agent: open and create documents, work with layers and selections, apply adjustments and filters, run batch actions, then save or export PSD, PNG, JPG, TIFF or WebP. Exposes PhotoCraft's command ids and its MCP server. Requires the matching ArtCraft app CLI installed locally; it is not bundled.

Offline civil-service exam study panel integrating 16 upstream open-source question banks with SRS wrong-book, mock exams, essay grading, an interactive knowledge graph and whitebox observability, plus a HuaSheng-13 methodology view (25 documents) with BM25 search. The npm package ships no question-bank or corpus data: after install, the question-bank manager clones the required set (about 360 MB, needs git) from the upstream repos (all 16 are about 2.2 GB).

Claim-verification skill that checks design documents and plans against codebase facts, escalating behavioral claims to executable logic-primitive verification for state machines and data models, with before/after regression, domain constraints, and concurrency risk mining.

Session handoff & context management: structured handoff documents (export/resume/status) so a fresh session can continue seamlessly, plus active context pruning (acp_* tools via the official compaction API with model-authored summaries).

A lightweight, general-purpose attachment Dock for DSH: paste, drop, or choose images, PDFs, documents, archives, code, and other files, review and manage them before sending, then pass them to the Agent as local paths. It gives non-image files a consistent attachment entry point.

File-drag fork: drop documents as removable chips above the composer, send without typing.

Artifacts-like documents in the sidebar: the agent writes a self-contained HTML document, you comment on any part, send the comments back for the next version, or edit text and formatting yourself. Every change is a new version; local only. A local-only fork of tdoc (https://github.com/tornado-doc/tdoc), rewritten as a DSH plugin.

Keeps project decisions in plain markdown instead of chat history: one main document plus per-module documents, every entry carrying a file:line citation. The agent interviews you to turn open questions into settled decisions, and a five-dimension score (task complexity, extensibility, maintainability, code quality, reusability) is derived from the documents and shown on a button beside the model picker. A session can bind several projects; projects are sized small/medium/large, which widens the entry limits, and a reusable-pipeline section in the main document is injected when its trigger words appear.