Plugins

DocChain knowledge base, document conversion and knowledge-graph toolkit — filename, content and metadata search, locate-by-doc_id/name with content reading, topic listing, bulk document upload, document-to-Markdown conversion, image-similarity search, per-document image descriptions saved to a sidecar markdown (flowcharts and architecture diagrams are turned into PlantUML sketches, other images into text descriptions; the original image is replaced by a clickable link), a deep-research workflow, and a knowledge-graph layer (ontology inspection, read-only Cypher, ontology/entity/relation writes). Every script-backed capability also ships as a native DSH tool executed in-process: doc search, content search, filename search, topic info, metadata search, upload, image search, image describe, doc2markdown, plus kg schema / kg cypher / kg upsert node / kg upsert relation / kg delete node / kg delete relation. All graph operations go through the DocChain API, so no Neo4j password is needed. The configuration page keeps several docchain environments (each with its own address and credential), switches between them in one click, and pre-selects topics per environment. Needs a docchain service URL and API key (except doc2markdown); image descriptions additionally need an OpenAI-compatible multimodal endpoint (defaults to an internal gateway model, configurable).

Meeting notes for dsh: one meeting per conversation, transcribed and speaker-separated on the machine itself, with points, assignments, handwritten notes, reviews and monthly scores in the same panel. Exports SRT/Markdown/Word and packs a meeting into a portable zip another dsh can import; confirmed assignments go to DingTalk/WeCom in one click, following your robot settings. Recognition models are swappable (a stronger local model can be imported from a file), and cloud recognition is off by default with no request made before consent. Word export needs Python and python-docx; the first run downloads a recognition model (28 or 77 MB).

Reads a local video or page link with ffmpeg and Paraformer ASR, returning a timestamped transcript plus key-frame images the agent can open; finds candidate videos by keyword and installs its own runtime dependencies on first use. Requires Python 3.8+ on PATH; video_discover also needs a one-time douyin/xiaohongshu login.

Cross-session artifact center: agent tools that register deliverable files (PDF, Excel, PPT, code, JSON) into one shared directory, plus a sidebar panel that filters them by category, extension or keyword.

Local memory for DeepSeek Harness: what you write is filed under a topic and linked to related entries, recall ranks results by embedding similarity (word matching when no model is installed), and the data stays in a local SQLite database.

Archives the QQ Zone posts you published yourself into a local library, auto-sorted into three columns — thoughts, dreams and reviews (book/film recommendations) — all three of which can be corrected by hand, one column at a time, and undoing a correction never disturbs the other two. Ships a private web viewer that can be locked with a password, repairs long posts that the upstream API truncates to its first ~500 characters, counts words by year and month, and backs up attached images for offline reading. The cookie is stored on the local machine only.

Local-first knowledge base for DeepSeek Harness: imports Word/PPT/Excel/PDF (text or scanned), EPUB and MOBI/AZW3, builds Markdown parts with page anchors, OCR quality/confidence and column-aware PDF reading order; adds an LLM-maintained wiki layer (schema.md rules, auto index.md, append-only log.md, typed notes with sources and backlinks), adds source-trust labels (high/medium/low) with trust-aware ranking and low-trust warnings, and supports ranked search, cross-KB query, precise reading/editing, and md/jsonl/zip export. MOBI/AZW3 need Calibre; legacy .doc/.ppt need Word/PowerPoint (Windows) or LibreOffice (Linux); scanned-PDF OCR downloads models on first use.

In-conversation keyword search for the current session: pages the history back to its first window before matching, then highlights every hit and scrolls to the one you pick.

Gives the model a private glossary: reads 「滚木」 as "none" and 「棍母」 as "doesn't exist", and decides on its own whether to phrase a sentence with those words when expressing that meaning. Registers one system-prompt section and rewrites nothing; word lists ship as per-category YAML (moba/fps/comments/ai/dev/private) with a settings page to toggle files, change reminder strength and open the glossary folder.

Describe the persona you want and the agent writes it: nickname, bio, taglines and links come from the host model, the avatar comes from your local asset library (or a path you give), then it fills your profile page and hands the picture to the site's own uploader. Dry-run by default - it only touches profile fields, never passwords or security settings.

Predicts your next message after each completed turn and shows it as ghost text in the composer: press → to accept, or keep typing and finish it word by word with Ctrl+→, Esc to dismiss. The prediction model follows the session by default or can be picked in the settings card, which also has an on/off switch and a speed test.

AList v3 file management: browse, search, upload (streamed and multipart), offline downloads, archive listing, task polling and control, plus admin tools for storages, users, roles, meta rules, settings, search index, shares and labels - 75 tools in total; every write goes through the approval flow and passwords are never read back.

A delivery receipt panel for a project hand-off. One trigger collects the branch and commit, the test and build results, screenshot dimensions with sha256, and the secret-scan verdict, then assigns every line to one of three zones by evidence alone — verified, local-only, or unverified. A claim in the unverified zone keeps its label and prints an explicitly empty slot instead of the claim itself, because a confidently worded sentence with nothing behind it is the exact thing the receipt exists to catch. Test failures and secret-scan hits are still evidence, so they land in the verified zone with a red tone rather than being quietly dropped.

Banter lexicon plugin: collects the words and angry quips the user said into banter ammo with add, list and random-pick tools, and injects the current ammo list into the prompt every turn.

ChatGPT-like conversation layout for the DeepSeek Harness Web client: a 768px centered column, right-aligned neutral bubbles for user turns, full-width assistant text at 16/28, and rounded code blocks with their own copy banner. Adds semantic inline markup (`==confirmed==`, `!!risk!!`, `++key word++`, with bare 4xx/5xx codes highlighted automatically) and line-start check/warn/tip callouts; a fast/thinking chip in the composer that switches the model reasoning effort through ctx.modelDirectories; and sidebar contrast, where the selected session gets a tinted row with an accent bar and workspace folder icons are colored.

Adds a four-pointed-star button left of the composer's model selector that rewrites the unsent draft in place — grammar, wording, punctuation and execution order — preserving code, commands, paths, identifiers, numbers and URLs byte-for-byte, answering nothing and never overwriting text typed while it runs. A pencil under every user message reopens that message for editing without touching the draft; because the Harness session log is append-only, an edit forks the conversation before that message rather than rewriting it. A circular restart icon under every reply asks that one question again in a fresh conversation that carries none of the earlier turns. Both are refused while a turn is still answering, and disabled when the reply used a tool that can leave a trace or when the files the message named have since changed. A right-sidebar memory tree draws the conversation as turns, showing what was actually asked and answered, every answer to one question on its own line labelled original, edited or memory-free, newest first, with arrows that re-read an answer in place; right-clicking jumps to a branch or removes it from the plugin's own history.

Reskins the DSH conversation hero — brand mark and workspace picker — with a Wordless-style landing view. The native composer stays untouched, and the picker still adds new workspaces (the entry declares its own directory-flow child hole, exactly like the shipped picker).

Per-turn development progress memory: completed turns are classified into date-indexed Markdown files under doc/progress/ with a maintained INDEX.md, system-level bugs are kept in a cross-project SYSTEM_MEMORY.md and re-injected on error keywords, and a progress_read tool loads full documents on demand.

Bounded self-managed long-term memory (Hermes-style MEMORY.md / USER.md with hard character limits and a safety scan), a review that runs after every turn and writes plain-language notes or refines an existing skill instead of adding a near-duplicate, a curator that finds and surgically repairs skills the loader would silently discard, cross-session search over past messages, and a learning card above the composer that appears only when there is news and asks before it deletes or rewords a memory.

Replaces personal data in conversation messages with placeholders before they reach the model (Chinese names found by context, mainland-China mobile and ID numbers, emails, bank card numbers, and terms from a user word list), shows the originals only in the local UI, and creates redacted copies of CSV/XLSX files.

DeepSeek Harness bridge to a relay-hub station: TOIP dynamic-password onboarding, LAN discovery, and per-plugin log accounting

SillyTavern-style prompt rules for DSH: layered system-prompt anchors, constant/keyword entries, reproducible probability gates and regex rewriting.

Local English-Chinese dictionary plugin for DeepSeek Harness (DSH).

Counts keywords inside thinking rows and highlights them once a row is expanded, with a count chip per keyword on the title line that doubles as an on/off switch for that word, per-keyword tint, text colour and text size (10-22px, the same range the host body-text setting uses), typeface, bold / italic / underline and whole-word matching, plus a dedicated settings section.