Plugins

Exposes the local DSH web GUI to one chosen CIDR range only (Tailscale by default) instead of binding 0.0.0.0: the proxy listens on addresses inside that range, rejects peers outside it, and admits clients by either a tokenised URL or a 4-12 character alphanumeric access code. Remote pages can be forced into a phone layout without changing the local UI, and the official appearance, font size, transcript view, code view and performance settings can be stored in the plugin config and re-applied on every remote page load.

Browses and plays the 6,454 videos Hacker News has recommended since 2007 inside a DSH panel, with a player, the HN discussion behind each pick, AI questions answered from subtitles, and 6,454 Chinese titles shipped with the package.

Turns Zhejiang University classroom replays (classroom.zju.edu.cn) into Markdown study notes plus a matching PDF typeset locally with Typst. Transcripts are public; slide capture is opt-in and needs a ZJU login. Scraping core: nzw806/zju-lecture-summerizer-. Optional fill-in notes use the MIT-licensed scholia Typst template.

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.

Per-step model router: named presets with ordered image/keyword-group rules route each agent step across every mounted provider and model, adding collaboration flows for image transcription, an image guard, a multi-plan quota panel, and per-step decision observability.

Office workspace & session dashboard: a floating 6-column sprite panel visualizing workspaces, sessions, token usage and subagents, plus Agent Mail and an office log tab. Feishu/Lark views (message feed, meeting schedules, transcripts) additionally require the `@larksuite/cli` tool installed and authenticated separately.

Publishes the running DSH host as a Model Context Protocol endpoint, so other harnesses such as Claude Code, Cursor, Codex or another DSH can start and continue sessions, read transcripts, wait on or cancel turns, and answer pending approvals; every call is attributed to its caller, and owner-scoped sessions keep callers apart.

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

Switches the running session's persona and speaking style in place, via the composer's persona button or `/role`; each persona can bind its own on-screen mascot, the persona is appended as its own prompt section after the deployment persona without touching tools or skills, and each switch is announced in the transcript.

Archived-conversation manager for DeepSeek Harness: view archived conversations grouped by workspace, restore them, and reveal their transcript folders.

Composer mic for the Web UI: tap-to-monitor live transcription and hold-to-talk, with host Edge TTS reply reading that streams while the model generates, echo-pause during reading, and tap-to-stop.

Bilibili live-room danmaku for DSH: read live chat, send messages only after explicit confirm, hang out in a room in the background, optionally let the model decide whether to reply, and optionally transcribe stream audio to text; no video understanding. Setup needs a Python 3 venv with the bundled requirements plus Bilibili cookies; transcription additionally needs ffmpeg and a Whisper engine.

Moves an existing DeepSeek Harness conversation into another workspace from the sidebar menu: the transcript and title carry over, a new workspace folder can be registered in the same dialog, and the original session is archived and restorable.

Pins passages selected in a conversation into a per-conversation right-sidebar panel, marks them in the transcript, jumps back to the source passage on click, and quotes a pinned passage into the composer from the selection toolbar or by typing @; the panel tags, searches, filters and exports the pins as a Markdown outline.

Makes the agent narrate its process: every turn opens with how it reads the message and what it will do first, then short interim notes between tool-call batches, with in-app settings for style, sentence cap and toggles.

Full-pipeline Chinese translation for the dsh web GUI: live translation of the model reasoning as it streams, in-place Chinese below each English reply, and one-line Chinese summaries for tool outputs and tool-call glosses — a standalone provider request that never enters the session transcript.

Voice tools: free edge-tts neural speech synthesis, OpenAI-compatible ASR transcription, voice list, batch voice preview and health self-check.

Adds Regenerate and Edit and resend to each message you already sent: Regenerate re-answers the same text in one click without going through the composer; Edit and resend retracts that message and everything after it in place — out of the transcript and out of the model context, in the same session with no new branch — then puts its text and images back into the composer, so the edited send rewrites the conversation from that point. Messages carrying files rather than images stay disabled.

Hold-to-talk dictation in the composer that ships no recognizer of its own and reuses the speech service the official voice-input bundle already mounts - long-press the input box with mouse or touch, release to write the transcript into the draft, slide up to cancel, and it never sends.

Turns each long dsh conversation into a three-level trail (topic to progress steps to milestone timeline) and shows it in a draggable overlay, where one click jumps back to the matching message in the transcript. Topics are distilled by the DeepSeek model with a zero-cost rule-based fallback, can be renamed, locked, merged by drag and drop, and support per-conversation notes plus a vector drawing board.

One leader, many sessions: tell the leader the goal and it splits the work into cards, runs persistent worker sessions in the background, collects their reports, and keeps the facts on a per-project board in the right sidebar, so several features move in parallel instead of one at a time. Project-level LEADER.md and SLOTS.md prompts shape every request, and `read_worker_session` replays a worker transcript read-only without waking it.

Multi-agent agent team of employee AI subagents for DeepSeek Harness — dsh-company: employee management, CEO bidding, n8n workflow orchestration, drag and drop canvas. DeepSeek Harness plugin with seven built-in roles (project director, product manager, tech lead, engineer, data analyst, QA, reviewer), each with its own persona, model and tool whitelist. Broadcast a mission and the employees bid for it themselves — the first line of their answer must be 【accept】 or 【decline】 — so accepted work runs in parallel instead of down a pipeline. The workflow canvas wires employee nodes with the start node, references each upstream result with {{input}}, and runs the graph in topological layers: parallel across employees, serial per employee, downstream skipped when upstream fails. Ships a web panel for the employee management tab, the mission board and each employee's transcript, the /dsh-company slash command, a live mirror into the built-in agent-team panel, deletable missions, and a private memory directory per employee.

Roleplay companion memory for DeepSeek Harness: per-conversation editable persona documents (1-100 weight per entry, AI may refine them in small story-driven steps), per-speaker favorability and bond in multi-person chats, active memories with AI-scored vectors, a nine-emotion table updated every turn, an AI self-evolution ledger, recent 48-hour transcript search, companion-style conversation compression, sleep-time compute that pre-guesses the next topics while a conversation is idle, per-conversation tone cards learned from its own past replies, a habit-hint small-model bridge that writes the user habits it extracts into this conversation memory, a date-archived local knowledge base with auto-packing by turns or tokens, and a unified integrations page that lists curated plugins and downloads their GitHub releases.

Layered long-term memory for DeepSeek Harness: each turn injects a persona frame plus a relevance-ranked memory index while full transcripts stay on disk and are expanded on demand, so the vault never floods the context window. Facts are slot-keyed, so a changed mind retires the old value instead of recalling two contradictory answers. The persona frame is derived from memory by the model itself, behind three anti-pollution gates (rejecting development chatter, blocking echoes of its own injection, and merging restatements by shared content words). Periodic consolidation merges near-duplicates, rolls long topics into digests, and archives low-value old entries by tagging only — raw text is never deleted. The append-only store is compacted in place (measured 4.7 MB to 355 KB). Zero third-party dependencies, no build step. Note: per-turn injection inevitably lowers prompt-cache hit rates, so this plugin is not recommended for work scenarios.