Plugins

Pairing-code remote access for DSH: a phone-first PWA with Web Push, plus a client role that operates the host's shared sessions in the native DSH interface, behind your own reverse proxy or Cloudflare Tunnel.

Honcho memory plugin by Plastic Labs: injects the user profile, session summary and relevant conclusions at session start, uploads each turn to Honcho in the background with secrets redacted, and adds honcho_search / honcho_chat / honcho_remember tools plus a /honcho status command; configured through the ~/.honcho/config.json shared with the other Honcho integrations, against hosted honcho.dev or a self-hosted instance.

Long-term cross-session markdown memory with an LLM-Wiki structure and a SOUL.md persona, injected at session start (by default only after the first user message and only in the active session), plus remember/recall/consolidate/forget workflows, an embedded memory skill, pack/unpack migration tooling, and an idle-time first-person recall nudge that surfaces real memories in a companion voice. Also gives the store observability and upkeep it lacked: a per-file boot-block budget that keeps the index routing table from being truncated, automatic last_access stamping so salience decay actually works, a read-only memory health dashboard (size, freshness, lint-parity checks), a declarative index compiler (pages declare summary:, one command re-lines the index), an interactive memory graph (page links plus shared tags, draggable, wheel zoom), structured queries (tag/type/salience/hot/stale filters), cross-link suggestions for pages that have no relationship yet, and a `checkup` report that ends in a prioritised action list. The boot payload was also cut by ~23% by moving operational detail into the on-demand skill. Its settings section now carries its own navigation mark (a brain half wired to a node cluster, since the shell offers no icon slot to plugins) and a feedback entry that opens this repository. Requires DSH session format v4 (official DeepSeek Harness 0.1.7+): injected messages declare the producer-owned source kind plugin:memory. v0.11 added a bilingual settings panel whose copy and sidebar label follow DSH language setting (中文「记忆」/ English "Memory"); v0.12 added the shared cross-plugin speech floor, a context-sensitive tone section and a weekly growth recap; v0.13 declares its DSH compatibility via engines.dsh (official 0.2.1-rc.5 series; older hosts are refused by the gate), adds a "Review now" button (POST /api/memory/control, action growth-now) that sends one growth recap immediately while still respecting the speech floor, panel accessibility (aria labels, status and alert roles, focus-visible rings), and the public PROACTIVE-PROTOCOL.md.

A shared kanban board that lets people and DSH agents manage workspace tasks through a Board tab and kanban tools.

Login gate for the dsh web surface: password or shared-token authentication, session cookies, rate limiting, and a user-management CLI (dsh.bundle manifest since 0.4.1, one-command `dsh plugin add` mounting).

ShiGuang Memory Engine (SGME) bridge: multi-agent shared long-term memory via HTTP — L0/L1/L1.5/L2 distillation, scenario-based injection, unified search, and proactive care signals (memory_search / wiki_search / signal_pull / signal_claim / signal_ack), installable as `dsh-sgme`.

Continual self-refinement loop: persistent memory, periodic review-and-refine, cross-session shared knowledge, and automatic rollback through a model-callable harness_refine tool.

Agent teams: spawn named long-lived teammates, coordinate them with a shared task list, member mailbox, and virtual workspaces, and watch the team live in a team-room tab.

Design workbench in the right sidebar. When the model builds web pages, app screens, posters, slides or emails, each HTML file shows up as a screen on a canvas inside a device frame and refreshes when the file changes; local dev servers are proxied with hot reload intact. Click an element or drag a region to put its selector, source file and styles into the composer. It can extract a brand design system from your website or project (colors by role, fonts, type scale, radius, shadows, buttons, inputs and cards) and use it for every new design. The model adds a few tweak sliders to each design (spacing, radius, brand color, layout variants) that update all screens live and write back to the stylesheet in one click. A finished design can be turned into React, Vue, Next.js or plain HTML code, with each built screen diffed pixel by pixel against the design. Also has a design tokens panel, nine style presets, a style panel (font size, colors, radius, padding and more) that writes back to the HTML or hands the change to the model together with the CSS rule and line behind each property, versions saved before and after each turn with drag-to-compare and restore, export to images, PDF and PPTX (links between screens stay clickable), a LAN QR link for viewing on a phone, link arrows and a click-through demo mode, a multi-size view, in-place text editing, reference-image palettes, and a design check (overflowing, clipped or overlapping text, contrast, tap target size and more). Bundles a ui-design skill and six tools: preview_page opens a preview; check_design measures every screen at real sizes in a hidden local Chrome or Edge (bars covering content, script errors, missing assets, dead links; CSS file and line for contrast and font-size issues; cropped screenshots of serious problems); look_design hands real screenshots to the model; extract_design_system builds a design system from a site or project; handoff_design writes a handoff pack (screenshots, routes, tokens, shared components); compare_design diffs the built local page against the design and marks what differs. Adds a Design mode for new sessions (Standard mode's tools plus the skill, the six tools and a design persona); each part has its own switch on the Plugins page. When DSH is opened from a phone or another computer, local-file designs are bundled into a sandboxed frame so they still show.

Visible Electron browser for DSH with one shared BrowserWindow, isolated task views, explicit human-Agent handoff, snapshot-reference and native navigation tools, operation trails, demand-driven page thumbnails, keyed session recovery for reliable tab switching and closing, and site-scoped cookie clearing for login maintenance.

Lazy-loading router for MCP servers: auto-discovers compatible MCPs and keeps only a shared router in the tool catalog, revealing a server's schemas when a turn needs them and hiding them again at turn end, so many installed MCPs stop costing context on every request. Falls open to normal visibility on any uncertainty, and the original MCP keeps ownership of execution, permissions and process lifecycle. Also supports explicit lazy connections with warm reuse, bounded reconnection, stdio and Streamable HTTP.

One shared Obsidian vault for every agent: dependency-free Python core (search/promote/adjudicate/forget), vault template, dsh plugin (memory_search/show/submit/status).

Deterministic project actions shared by people and agents: one actions.json, a right-sidebar run panel, and agent tools.

Unofficial Grok integration for eligible X Subscription, SuperGrok, or X Premium accounts: shared Grok CLI OAuth, chat with optional main-loop web/X search, and experimental image generation, image editing, and video generation (all media features disabled by default).

Multi-agent orchestration preset: a lead agent dispatches subagents from a built-in role roster over separate read and write lane pools with per-role model binding, and collects each subagent report on a shared board; adds go_work/continue/need_help/forward tools, a tree-view panel and a settings page.

Turns the main model into a dispatcher: six pools (economy/mechanical/main/hard/vision/review) route each subtask to the right model, with ranking and per-route reasoning-effort pins. A context watermark (50k/90k/130k) nudges delegation early and, at the force level, forks a backup session, writes a handover doc, compacts, and continues without losing in-flight subagent work; /ctx-pause, /ctx-resume and /ctx-handover pause, resume or trigger the same machinery by hand. Optional Agent Teams mode adds persistent teammates and a shared task board; /vision lets text-only models handle images via the vision pool; tiered verification sends bigger diffs to a tester and an independent reviewer. Settings UI, READMEs and the conversation / code-comment / document language preferences all cover the same 11 languages (en, zh, zh-TW, ja, ko, de, es, fr, it, pt, ru); the plugin UI follows the DSH app locale unless forced otherwise. Bundles three skills: read-only MySQL/Redis verification, commit-message generation, and a requirements/design document convention.

Run several DeepSeek Harness sessions side by side, hand work from one to another, and watch the whole collaboration on one read-only canvas.

Migrates skills from other agents (Cursor, Claude Code, Codex, OpenCode, and more) into DSH: scans 14 agent platforms plus the shared ~/.agents skills layer, detects duplicate names across sources, lets you pick the best source per skill, copies them into the DSH skills directory, and rolls back previously migrated skills.

Worktree Space: puts a workspace task that spans one or more Git repositories in its own task space directory - each repository in it gets its own worktree on one shared task branch; the space is registered as a DSH Workspace so sessions start right there, and multiple tasks run side by side without interfering. Finishing a task can merge the work back into each repository's target branch, remove the worktrees, and file whatever Git does not track in an archive directory you choose.

Drive a local DeepSeek Harness agent from QQ and other IM channels through AstrBot: send tasks with /dsh, continue by quoting or @-mentioning the bot, answer approvals and ask_user_question prompts from chat (in parallel with the DSH web UI), and get results, inline images and file cards back. Ships session / workspace / model / permission commands, /compact and /last recovery, three progress-display modes, and group-shared or per-user session scoping.

Passcode marketplace inside DeepSeek Harness: enter a six-character code to unlock and install plugins shared by creators, plus themes, backup, updates and diagnostics.

Multi-channel IM bridge for DeepSeek Harness: each QQ (SnowLuma / OneBot v11, official QQ Bot) or Discord group and private chat becomes its own agent session, bound to a role card whose domain carries knowledge bases with draft approval, shared memory, a read-only GitHub reader and group trigger rules; two built-in personas (customer support, group chat), unified push with broadcast, and human hand-off.

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.

Cross-harness agent memory for DSH: one plain-file store shared by the DSH and pi adapters and the harnmem CLI, so a memory written in one harness is available in another; injected as a byte-stable hot index, with five harnmem_* tools, session-end extraction, and a read-only memory browser panel.