Plugins

Human-readable Markdown memory for DeepSeek Harness: user-level (~/.deepseek-harness/MEMORY.md) + workspace-level memory injected every turn, auto daily-log writing with distillation, bridges existing WorkBuddy/CodeBuddy memory dirs, memory_note / memory_note_user / memory_read tools with built-in dedup, and a bilingual settings page. Plain-text storage, no database.

A long-term memory plugin for DeepSeek Harness. Every turn is judged and stored into a local SQLite (utterance / event / version / stage / decision), with a browsable panel.

Git-style dot timeline on the right edge of the DSH web UI: one dot per user message, hover for content and metadata (time, turn, duration, TTFT, tokens), click to jump. Also adds a full-session message list, in-session and cross-session search, bookmarks with #msg= deep links, and keyboard navigation.

A study tab with course-map, tutor and blackboard columns that turns markdown files, local folders or GitHub repos into guided courses, with lesson unlocking, mastery tracking, spaced repetition and a tutor-designed course import.

Visual branch brainstorming that creates an isolated Session for each direction, automates parent, sibling, checkpoint, and return Handoffs, and provides a full tree tab with an optional Better Sidebar view.

Folds degenerate reasoning loops out of the model-visible history so they are not replayed upstream on the next turn. Detects two shapes — one sentence hammered repeatedly, and short-sentence rotation — and replaces the matched span in place; a companion escape valve aborts a turn that will not stop on its own.

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.

Second model passively reviews each turn and injects notes.

Conversation navigator panel: turn-folded outline of the current session with per-step kind badges (assistant, tool, command, compaction, error), a hover bubble showing the full user question, a minimal mode that hides turn numbers for an all-badge view, keyword filter over user questions and assistant replies, click-to-jump with reading-position tracking, and load-earlier/load-all history paging. Host >= 0.1.2-rc.1; legacy hosts install @legacy/0.2.5.

DSH plugin for Blind Whale Farmer, a SMAPI mod in the same repo that turns Stardew Valley into a text game state so an AI can play it through MCP tools: farming, fishing, mining, gifts, festivals and marriage, plus LAN co-op on the same PC where you chat with her in Chinese (F6). A config card on the plugin page sets play limits (days and minutes), time freeze while thinking, the co-op mode, extra instructions and the guide, and pushes them to the running game; an optional session preset or a single stardew gateway tool (both off by default); and an automatic "keep playing" when a session stops on a tool call that came back as plain text. Needs the mod installed in the game.

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.

Turn a one-line requirement into verified delivery. TeamFlow runs a multi-stage pipeline — triage, PRD, design, technical plan, parallel development, QA with defect rework, acceptance — and gives the model 12 `teamflow_*` tools plus a workbench with a live pipeline graph and a backlog kanban. Each requirement gets its own folder holding the PRD, design, technical plan, QA report and acceptance record.

Adds an Execution graph conversation-view tab that renders each turn's prompts, replies, and tool calls/results as a foldable timeline with a detail panel and PNG export.

Turns an article in the DSH conversation into an Excalidraw canvas in a session tab: the Agent drafts the structure with diagram_create, you edit labels, nodes and layout with autosave, export PNG, SVG or .excalidraw, and the Agent reads your edited canvas back with diagram_read. 0.6 adds an editable classification overview plus a complete detail index for large three-level trees.

Two-suit VTuber theme for Joi: Flowers and Library are separate token systems for light and dark, with a standing portrait and a whale girl napping on the headline of the new-session page, two chibi companions above the composer that follow the turn state, a duo sidebar mark, and a context meter shaped as a ripening mandarin; a third card returns the stock DeepSeek look with the plugin still installed.

Pair a second model that passively reviews each turn and injects notes.

Smart Charts skill: turns CSV/TSV/TXT/XLSX/XLS/JSON data files into standalone interactive ECharts HTML - 32 chart types including offline maps, 3 themes, no CDN. A --profile data profile (per-column dtype, cardinality, missingness, samples, statistics, entity grain, insight signals) lets the agent read the data and pick the chart itself; each chart embeds a fact sheet (plot_stats + data_preview) whose numbers are the only quotable values. LLM transform code runs in a restricted sandbox (blacklist + AST whitelist + safe builtins); --doctor self-checks the Python environment. Fully offline, ECharts bundled.

Zero-dependency, event-driven voice announcement plugin: no extra model, no token cost. Speaks with the system's built-in natural voice, supporting both Windows and macOS; final-reply announcements, approval & question alerts, optional event announcements (turn end, command done, goal change, tool errors, todo updates), replayable final replies, and a bilingual visual settings page.

Turns "open with the default application" file requests inside the conversation into the built-in right-Sidebar preview: the browser intercepts `POST /api/present.open` and calls `ctx.sidebarRight.openResource` with the official resource address grammar, so nothing is sent over the network and no renderer ships with the plugin; "show in file manager" is deliberately left untouched.

Context lens: visualizes token usage of every request (context composition, KV cache hit rate) and enforces per-turn / per-session budgets with warning and blocking (npm: `dsh-my-context`).

Cross-session persona and diary for DeepSeek Harness: each turn can leave a first-person diary entry with a short retrieval index, and the next conversation injects the persona, a hand-note file you write yourself, and a dated batch of past entries retrieved by searching the diary text itself; anything older is found through feiyu_recall using that index.

Zero-residence context engine: large tool payloads are evicted out of the live context into a queryable store and only deterministic pointers are left behind, so per-turn prompt tokens stop growing with the transcript. Any masked content is reconstructed verbatim from the session log on demand, by tool-call id or session seq.

The organ kernel of Agent-Body: plugins organized as one body. Each command is turned into a nerve impulse that deterministically innervates the organ which should handle it and names the capability to use; a heartbeat with a variable interval (faster on alerts, slower when idle) pumps operator directives, proprioception and homeostasis warnings system-wide; reflex arcs fire with zero model calls; failures go through deterministic attribution (missing tool / arguments / permission / timeout / network), a prescription, and a re-check loop, with argument errors never auto-retried. A missing organ is compensated by the one with the highest capability overlap, and tool schemas are gated by the current intent (84.7% measured reduction, reproducible in-repo). This entry is the kernel plugin package inside the agent-body repository.

Browser notifications and a beep when a session turn ends, the agent asks a question or approval is pending; clicking the notification jumps to the session; remote trigger endpoint and SSE channel (npm: `dsh-my-notify`).