Plugins

Task board plugin for the DSH web GUI: a sidebar entry plus a multi-column kanban view with real execution through DSH sessions, schedules, session rules and auto-cruise automation. Board truth lives on the host and syncs to every device over SSE (the bro

Render GeoJSON or vector data into an interactive GeoLibre map in a sidebar tab, and let agents operate the live map through tools: layers, styles, view, feature identification, GeoLibre processing algorithms, and the Whitebox toolbox (WASM in the browser).

Self-tending living memory in one local SQLite file — a nightly patrol dedupes, merges, decays and cross-links entries on its own, with seven-signal RRF hybrid recall (FTS5 + jieba Chinese-first tokenization, optional vector KNN, graph PPR), a typed knowledge graph, conflict detection instead of silent overwrites, and web telemetry panels.

DSH markdown preview: clicking a markdown document in the conversation opens a rendered preview panel docked to the right of the chat.

DSH GitHub connector: review PRs, triage issues, debug CI, prepare changes (18 tools, gh-first + REST fallback, approval-gated writes).

Task kanban where agents claim and hand off work through taskboard_* tools, which cannot move a task to done or canceled — acceptance stays with a human.

Adobe Lightroom Classic as native dsh tools through the lightroom-py MCP server: read the catalog, apply develop settings and presets, export JPEG/TIFF/PSD/DNG, and write ratings, labels, keywords and IPTC — 15 tools driving the Lightroom Classic installed on the local machine, no cloud round-trip; the Python package is on PyPI and the Lightroom plugin installs with one command.

Context trimmer: lists the current session's context entries with role, preview and ≈token estimate (cl100k), highlights over-threshold items, and removes selected entries exactly without LLM summarization.

Coding retrospect distilled memory for DSH: distills rejected solutions, pitfalls and constraints from each turn via a local LLM, tags them into MemOS (type:rejected_solution), and boosts weighted recall on coding tasks via agent/pre-step.

A lightweight plugin that adds model thinking token statistics to the bottom Dock.

Per-session question index for the DSH Web UI: a time-proportional dot rail on the right edge and an expandable chain panel showing every user question with its time, including branch/subagent sessions; clicking a node jumps to that message and highlights it.

right slider for deepseek-harness-plugin.

Visual channel configuration UI for DeepSeek Harness (feishu / imessage / telegram / ...)

Extensible AI-driven group-reaction narrative game framework for DeepSeek Harness: type one action and multiple NPCs each respond in their own chatroom message with avatar illustrations; worlds, locations, NPCs and feature extensions (e.g. a third-party drawing API for dynamic NPC expressions) are added and modified through the harness chat dialog without code.

Product Design workflow suite for DeepSeek Harness - a router plus nine pd-* skills carrying ideas from a minimum design brief through visual directions, evidence-grounded research and audits, URL cloning, frontend builds and a blocking design-QA gate.

Provisions the kimi-webbridge bridge daemon (auto-install with SHA-256 verification, auto-start) and registers a 25-action skill that drives the user's real browser through the local bridge.

Web search provider for the ctx.web seam that routes the DeepSeek web_search tool through a LiteLLM proxy using the OpenAI Responses API, reusing LITELLM_API_KEY.

Answers hard questions by staging a formal debate: two adversarial subagents argue opposite sides with research, then the main agent rules on the transcript through the debate_open, debate_round, and debate_verdict tools.

Connects the Qixin Insight MCP server over OAuth 2.1 with PKCE as a single plugin entry, mounting its tools as mcp__qixin_insight__* with automatic token refresh and revocation on disconnect.

Image generation workbench and agent tool for DSH: one tool (ark9_generate_image) paints text-to-image and image-to-image via any OpenAI-compatible API. Channels are entirely user-configured - no bundled endpoint, you bring your own baseURL, key and model name (manual input supported). Agent-initiated generations are approval-gated by default: requests queue in the floating panel and nothing bills until you approve; approval is non-blocking (the agent replies "awaiting your approval" immediately, and results, denials or timeouts are injected back so the agent reports them in the next turn). Floating glass workbench with five tabs (Generate / Approvals / Prompts / History / About), aspect-ratio grid with quality-budget + 16px-alignment sizing, transparent background, batch up to 10 images as aggregated sub-tasks, prompt library with custom JSON sources fetched through a host proxy, persistent generation logs with one-click retry, multi-channel aggregation with per-channel model fetching, bilingual UI (zh/en), stroke-SVG icon set, config import/export. Registers as a Better Sidebar tab when dsh-better-sidebar is installed; stacks above the dsh-cua FAB when both are present.

A-share market dashboard for DeepSeek Harness: realtime market indices, stock screener with 13 technical signals and multi-strategy intersection, 7×24 multi-source news aggregation, watchlist with group management, market sentiment thermometer (limit-up ladder, breadth), K-line charts with MA/EXPMA/BOLL overlays, and sector/limit-up/longhu rankings.

Cipher memory platform as a DSH bundle: four memory types (attention, experience, preference, cognitive) sedimented per turn by four memory agents, cross-session deterministic recall injected via systemPrompt.context, insight review kept out of user-facing output, per-session UNNI/LOOP modes with memory-driven auto-continuation, memory search/ingest tools, plus a settings page (SOUL editor) and an AgentPool panel.

Hindsight long-term memory for DeepSeek Harness: injects relevant memories before each turn and retains finished turns to a Hindsight bank.

Session handoff for DeepSeek Harness: the session menu creates a successor session that rebuilds the old session's memory, tasks and rules through an eight-section takeover packet, with light context via on-demand transcript readback.