Plugins

A dsh status plugin with host-plane and browser halves: harness runtime health (process, listener, API-key presence, memory, uptime, plugin inventory) as JSON plus server-pushed SSE alerts, surfaced as a header badge with an expanded panel in the Web UI

DeepSeek Harness plugin: Nocturne Memory client — automated long-term memory (boot/read/search/create/update) backed by your own Nocturne MCP server.

Read-only Windows device information tools: one agent tool per Win32 device category (time, system, cpu, memory, disk, gpu, network, battery, processes, usb, audio, printers) via WMI/CIM and Node os collectors.

Cross-session memory for the model: full-text search all past sessions (SQLite FTS5 via ctx.sessionQuery) and bring the strongest matching excerpts back into the current context.

Cited memory over DSH's lossless session log: distilled facts carry `(sessionId, eventRange)` citations that expand back to the exact original log excerpt.

Blocks risky tool-call shapes before execution: inline multi-line Python, forwarded content without a source, missing source labels, and memory writes past the character cap. It also asks for confirmation before shell commands, and one rule is specific to the author's WeChat sending workflow.

A multi-project todo board inside DSH: capture notes in a global capsule overlay, group them into projects and mind maps, and export a todo into the composer as a task for the agent. Notes and todos are read and written on the author's hosted service (todo.memorymap.cn) after you sign in; set config.apiBase to point it at your own backend. Its HTTP routes have no DSH access check.

End-of-turn voice summary: the model calls voice_say once before finishing a reply so the conclusion is spoken through Breeze TTS, with Chinese bracket audio tags (laughter, sighs, pauses) and optional performance instructions. Audio is synthesized host-side and played from browser memory without ever touching disk; the character limit is a writing target for the model, not a cut-off, so long lines still play in full. The API key stays in the credential store, and an optional daily Breeze check-in is included. Needs a Breeze API key and sends the spoken text to the Breeze service; its HTTP routes (including the settings route that stores the key) have no DSH access check.

A fastfetch-style system and DSH panel: one slash command (/fastfetch or /ff) and one simple agent tool render OS, kernel, host, CPU, GPU, memory, every disk and local IP address, plus DSH version, model, session mode, plugin and skill counts into a colored terminal card, with a settings page that edits every field.

Manage memory files written by DSH memory plugins inside Settings (view/edit/delete), and sync them to one cloud drive with conflict-safe three-way sync; other drives take upload-only backups.

Cross-session memory and compaction archives for dsh, plus a persona kernel. After each substantive turn a background model call extracts facts, preferences, open tasks and commitments; entries carry ids, fade when they stop being mentioned, are capped per kind and can be corrected. When the host compacts a conversation the compressed span is written to the note vault as an archive card whose catalog is injected into the session, so details can be read back by id. Ships an append-only ledger, a settings page, a /whale command group and nine tools.

Long-term memory ported from the OpenAI Codex memory pipeline: sessions idle for 6 hours are extracted in the background by a chosen model, then merged by a hidden agent into a Markdown memory folder at most every 6 hours; new agents get the memory summary in the system prompt plus four tools to list, read and search memory and save corrections. Models are chosen on a settings page or with /memories; an optional filter keeps a notes folder out of memory.

Shares one set of Markdown memory files between DSH and WorkBuddy: project memory, user memory and the user profile are injected into the session context, while daily notes stay out of the prompt and are read, appended and archived through the tools. Six tools (status, read, search, append, edit, prune) write back through a cross-process lock, revision check, backup and atomic write, and a panel in the left rail and the right sidebar edits entries, sections and whole files.

Every few turns asks the model whether anything is worth keeping, then sorts the answer into memory, skill or hook.

Turn completed DSH conversations into a local, versioned memory wiki with a sidebar manager, memory map and run logs.

Bridges a memory-nebula store into DSH: a panel inside the Harness UI to search, edit, pin and forget memories, plus three agent tools to check, search and revise them.

Whale-chan: an in-page companion for DeepSeek Harness that also lives on Telegram. One character, one agent session, one memory: chat in the browser or from your phone, with real tools.

Douyin for DSH: bounded autonomous watching with storyboard frames and danmaku sampling, persona and interest memory, a daily watch report, plus direct-message auto-reply and one daily greeting for a whitelisted set of friends. This is a maintained fork of dafeiyu1314520/dsh-douyin-agent 1.4.7 that fixes follow-list read timeouts, unclickable conversations, missed replies, and greetings that stopped scheduling after a single send. Windows only (a dedicated Edge window, Node.js 22.13+). Replies and greetings are sent as ordinary messages with no “automated reply” label, and once you have enabled them they restart by themselves each time DSH launches until you stop them by hand. It registers the same bundle id as dafeiyu1314520/dsh-douyin-agent and LockyBee/dsh-douyin-agent, so it replaces them rather than running next to them.

macOS only. Shows a live badge in DSH and an optional SwiftBar menu-bar item reporting what the Yunshu (Eagleyun SASE) endpoint agent is doing on this Mac right now — TCC permission requests, its own agent logs (screen capture, clipboard, browser URL reads, browser window counts), DLP scan paths and the process table. Read-only: it never blocks, disables or modifies the agent, keeps the last 60 events in memory only, writes three state files locally and makes no network calls. Requires the Yunshu agent to be installed; SwiftBar is optional.

Disk, CPU/memory/GPU, listening-port and token-usage cards with a full-page zoom; runs as a workbench module or standalone. The port card works on Windows only and the GPU card needs nvidia-smi.

Workspace long-term memory for DSH: records rationale, lessons and constraints that files never capture, then injects them into later sessions automatically.

Port of MiMo Code's infinite-context memory: as the window fills it asks the model in the background (the current provider route unless writerProvider/writerModel is set) to write a structured checkpoint and a project MEMORY.md, then, ahead of DSH's native compaction, replaces the visible window with a rebuilt dump of tasks, checkpoint, recent user messages, memory and notes, falling back to a MiMo-style compaction. Memory files live under $DSH_HOME/mimo-context (per session, per project, plus a read-only global one); it adds mimo_* memory, history, checkpoint and rebuild tools and /mimo-* commands, with dream/distill off by default. Needs DSH 0.2.2-rc.1 or a later 0.2.x.

Project workbench for DSH: groups sessions by project (workspace) in a panel with project cards and session lists, applies a project's default preset, model and reasoning effort to new sessions, scopes memory per project on request, previews AGENTS.md/CLAUDE.md read-only, and groups the sidebar by project at startup.

Seal proven command chains into reusable executable tool scripts for DSH agents. DSH 代码脚本固存，留住模型成功自实现的工作流。