Plugins

Delegate from DeepSeek Harness Web to existing Codex CLI, Codex Desktop and Claude Code sessions with progress and completion callbacks.

Native SSH remote development for DSH: remote workspaces, mirrored sessions, terminal and file access, approvals, and a DSH UI. Requires DSH Desktop 0.2.1-rc.2 and a remote host running Linux or macOS.

Auto-classify DeepSeek Harness sessions via Jev decision models or Agent tools, displayed as title emoji prefixes (wip 🚧, blocked ⏸️, review 👀, done ✅, plan 💡, bug 🐛). Features seamless lifecycle recovery, optional Jev inference (needs a Jev API key), model tool maintenance, and a visual settings panel.

Composer and sidebar helpers in one plugin, each switchable in Settings: a git Changes panel (uncommitted / unstaged / staged / branch diffs), Turn rollback, Project memory (notes per project that later chats read, off by default), a Task board (kanban board of chats by their live state), Assistant (one lasting chat that sets reminders with dsh scheduled tasks and reads your other chats; it changes a chat only after your approval) with Assistant apart from chats, Assistant always free (long steps go to background subagents) and Assistant news from chats (off by default), Remote computers (another Mac's dsh over Tailscale, off by default), 11 extra UI languages and Automatic updates.

Drive your local DSH from WeChat: a self-hosted iLink bridge over a persistent ACP session (context lives in DSH and is resumable), phone conversations grouped into the desktop workspace, with image recognition, file messages (Excel/Word/PDF, parsed by the agent itself) and voice transcripts. Tool approvals are answered inside WeChat itself (numbered card; ask/allow/reject policy; 120s timeout means reject), and any process can push a message to your phone through the outbox helper. Access defaults to strict (only registered devices are served); the phone channel's permission preset is configurable - see the README security section before sharing the bot.

Remote development launcher for DeepSeek Harness: provisions dsh on a remote host via SSH (or a local WSL distro) and connects from the local client, with LLM credentials proxied through a reverse tunnel so they never leave the local machine. Ships as both a standalone CLI and a dsh plugin with a session panel, /remote-explorer slash command and remote_* agent tools.

Laya typed decisions (`noul` yes/no, `choice`, `score`) as a first-class Cordis service (`ctx.laya`) plus the model-visible `laya_ask` and `laya_plan` tools. The plugin itself installs and downloads nothing: it is a client of a `laya-mcp serve` sidecar you start yourself, and it reports that the sidecar is not running instead of failing obscurely at the first tool call.

Unofficial DeepSeek Harness integration for Unreal Engine 5.8 Unreal MCP

Remote development over SSH: pick a directory on a registered machine as the session workspace and the file, shell, bash, and search tools run on the remote host — the agent works there with the same local tools, and no extra model-facing tools are added.

Models+ settings page for the DSH web UI: per-model reasoning-effort tables, input modalities and compat flags saved through the official settings pipeline, with models.dev metadata prefill and API key management.

Slides out a Monaco editor plus a lazy-loaded file-tree panel in the DSH Web conversation, so you can edit the local workspace inline without switching to an external editor.

Phone access to DSH over a self-hosted relay (WSS via your own TLS-terminating proxy): bundle plugin with bridge supervisor and QR login, a native Android app, and server-side device revocation.

Identity-gated Tailscale access to the Web GUI with dsh still bound to loopback: a 127.0.0.1 proxy published by `tailscale serve` admits a request only when the Tailscale login it stamps is allowed, with an optional per-device allowlist, so the privileged /api methods behind the loopback check — Settings, Models, Plugins — answer without dsh being told to trust a remote host.

A governed swarm of six specialist DSH agents — orchestrator, planner, knowledge-base bridge, developer and two reviewers — turns a requirement into a strict phase pipeline where every delivery must prove itself with structured evidence before the next phase may start; reviewers are read-only, code merges only after a review pass, and an append-only event log gives full replay and audit on a live kanban board. Its design draws inspiration from the Hermes Agent kanban.

Inline +N −M badges on edit/write tool rows and a collapsible per-turn file-change summary card with aligned diffs, review and undo — covers native edit/write, str_replace_editor and Code Dispatch sub-calls, no git required.

Decentralized multi-device fleet: mDNS LAN discovery, key pairing, and SSH direct execution across networks.

Gated multi-agent pipeline for OpenSpec changes — six opx_* tools drive the phase state machine, two agent presets (developer and reviewer) carry implementation and review, and 23 bundled skills define the quality standards they are checked against; full mode runs analyze, implement, then tool, task and dimension-based quality review, while simple mode runs implement and one merged quality review.

GPT Image 2 `image_gen` with Codex subscription OAuth by default or explicit API-key mode: developing card, up to three live API partials, durable attachment replay/lightbox/download, text-only model output, and bounded credential-safe requests.

Visual GitHub login without a terminal: in-window device flow, token synced into the gh CLI, and host status/launch endpoints.

Eleven game-development agent presets cut by workflow stage — concept, design, build, art and audio, QA, release, narrative, level, engine — plus one orchestrator that delegates across them, carrying 37 bundled skills. Regroups the 48 agent prompts of Claude Code Game Studios (MIT) by stage so each preset loads only the skills its stage needs. Installs with dsh plugin add; run node install.mjs once afterwards to deploy the skills the presets reference.

Connects the free ZCode plan to the model picker: a multi-account pool with rotation, per-account rate-limit and quota display, and bigmodel/zai device login.

Drive LightCraft from the agent: import photos, apply develop settings, and export JPEG or other formats from a photo library. Exposes LightCraft's command ids and its MCP server. Requires the matching ArtCraft app CLI installed locally; it is not bundled.

Side-panel Chrome and Firefox extension that lets DSH drive the tab you are on: pages reach the model as structured text with a numbered element list, and clicks, typing and navigation wait for your approval. Beyond upstream it adds viewport screenshots, opening a URL in a new window, scrolling inside nested scroll containers (chat transcripts, side panes, modal bodies), permission-mode, model and slash-command controls in the composer, and an opt-in developer-tools group (elements and CSS, page JavaScript, network requests) that is off by default and approved per call. The install is two halves: the bridge plugin comes from the prebuilt release tarball, and the companion extension ships as a tgz in the same release and is loaded unpacked, which is the only way Chrome accepts it. This project is a fork of omdsh-dev/dsh-browser: https://github.com/omdsh-dev/dsh-browser

HarmonyOS development suite for DSH: a right-sidebar HiLog inspector (live stream with level/logger/text filters) and an ArkUI Inspector (screenshot pick, collapsible component tree, node properties with search, box model), two tree sources — the DevEco debug channel (declared padding/margin/border and custom component names) and the uitest accessibility tree — an .ets viewer with ArkTS syntax highlighting, DevEco Studio/CLT toolchain and device management, plus the harmony_ui_tree agent tool. 21 remote methods, 82 unit tests.