Plugins

Peer channels between conversations at the same level: user-granted, symmetric, with durable grants that survive a restart and burst messages merged into one ordered delivery.

Overhead conversation background with five whale species formed from custom text or ASCII, shaded cells, frosted content cards, input-box avoidance, independent dives, spouts, ripples, wind, and cloud shadows.

Four palettes for the DeepSeek Harness web UI — solid, glass, volume and neon — each with light and dark halves. Neon adds a scene light field with a 46px circuit grid, a laser scan that sweeps the conversation column only while a turn is running, HUD-style workspace labels in the sidebar, embedded MiSans Latin chrome type, and a 125% sidebar type scale that stays fixed while the conversation area zooms.

One-click prompt refinement for the DSH composer: the ✦ button next to Send rewrites the draft into an agent-ready prompt in Standard or Light mode, with Revert and Retry; asks follow-up questions through the question card when the draft is missing information; checks that paths, identifiers, numbers, URLs, inline code and @mentions survive the rewrite and adds back any that were dropped; runs on the conversation model or a dedicated model chosen on the Plugins page.

In-conversation source deck for DSH Desktop (supports DSH 0.2.2-rc.2): the current chat model runs LLM search rounds, candidates render as GitHub-aware cards, and keep/exclude feedback, favorites, and the selected sources stay in the same conversation.

Shows the lyrics LX Music is playing in a floating panel on the right of the DSH conversation page, with previous / play-pause / next controls. Scroll the lyric window to read ahead, double-click a line to start the song there, and if the player is not running, pressing play starts it in the system tray. Windows only, and LX Music has to be installed with its local Open API enabled.

Runs the local Cursor CLI as a child coding agent from DSH - a `cursor_code` tool plus the native one-shot `cursor_subagent` tool, one mirrored DSH sub-session per run, per-task model choice, resumable conversations, a step timeline with real file diffs, and a usage, model and session panel.

An agent-kept daily journal: one sentence injected into the system prompt makes recording one of the agent's duties, so what you have done and what you intend to do is written as dated todos and memories, one JSON file per day under the DSH home, and drawn on the right sidebar's month calendar — a hollow ring while a todo is still open, a green dot once every todo is done, a blue dot when the day holds only memories; that injected sentence is rewritten from the calendar itself, which is how you set how eagerly and how the agent records; every entry carries one of five tags (work, study, life, health, other) drawn as a colour-coded chip, todos can be checked off from the card, titles and tags are searchable across every day, and clicking a memory opens the conversation that recorded it and stops at that turn; the ? beside the month heading opens the project on GitHub.

Long-term memory scoped to the DSH workspace. A session opens with a one-line-per-memory index - bodies are fetched on demand by the `memory` tool, so the same character budget holds about three times as many entries - and when a turn ends a purely local search over the last user message pulls the matching memories into the next briefing at no model cost. Optional auto-capture distils a stretch of conversation into structured memories; in draft mode they wait in an approval queue instead of landing directly. A portrait layer keeps a workspace and a global picture, rewritten from the journal and the records, with the same draft-or-direct choice. Settings → Memory holds the archive, list and timeline views, a health check (duplicate clusters, stale entries, broken links), the supersede version chain with rollback, and a read-only scan that imports existing WorkBuddy / Qoder memory files.

A configurable Liquid Glass theme for DeepSeek Harness with translucent surfaces, wallpaper, desktop transparency, window blur, custom cursors, click ripples, and per-side conversation contrast controls.

Keeps the images you pasted or attached in the composer, per session: they are mirrored locally in the browser and handed back through the official draft channel when you return to the conversation or the composer remounts, and dropped as soon as the message is sent or you remove them.

Todo sidecar for DeepSeek Harness: turn selected text into a todo, capture todos from a conversation, review them in a left sidebar panel, get due reminders as an in-app popup or an IM bot message, and export everything to HTML, Markdown, Excel, CSV or JSON.

Skill manager for DSH with a pack system. Installs skills as versioned packs and never overwrites files you have edited - upgrades skip your changes and report them. Also ships 6 built-in skills, a problem-grouped settings panel, and tools that let the agent read and write the skill library in conversation.

Adds a refresh button and a power menu (restart / close DeepSeek Harness) to the conversation header. Client-only, zero tokens, no dependencies. The power menu is Windows-only.

Browser provider for DeepSeek Harness: hand it a web task — open a page, click, type, fill a form, read what is on it — and it drives a real browser step by step, seeing an indexed table of what can be done on the current page instead of raw HTML or screenshots. Each step is one bundled-Jev decision rather than a full model turn (1.1 s median per step versus 2.8–3.6 s for chat-model turns in the repo benchmark), and the main conversation receives only the conclusion, so its context does not grow with the page. Targets come from the page it just read and a changed page is re-read rather than clicked blind, and it runs in the browser that Session owns, leaving your everyday Chrome untouched unless you switch to attach mode.

OpenAI-compatible image generation for DeepSeek Harness — text-to-image, image editing and batch generation, rendered straight in the conversation.

Delete one finished turn from a DSH conversation without deleting the session — the trash button next to the last assistant reply removes the question, that reply and the tool records of the turn from the conversation surface and from the model context, while the session id, title, later turns and the append-only log stay; the removal is written as a persistent tombstone, so it survives a reload.

Nai milk-frog mascot appearance layer for the DeepSeek Harness web GUI: wears the bundled milk-frog artwork as the GUI background (surface-token fade with opacity, blur, scrim and position controls), seats the matching square avatar as the sidebar and conversation brand mark, and edits it all from a Settings section; the host serves the artwork and config locally under /api/nai, and the config lives at $DSH_HOME/nai.json.

Persists unsent composer attachments per session, so images and files pasted into the input box survive page switches, conversation switches and app restarts: the bytes are mirrored in IndexedDB and handed back through the official createDrafts/addAttachments channel, and are dropped as soon as the message is sent or you remove them.

Long sessions get expensive, and the platform compacts the context on its own. This plugin adds an occupancy badge (hover to see how it is computed), writes a handover draft into HANDOVER.md from 45% — files changed, money spent, what recent turns were about — and reminds you once at 60% to wrap up. On compaction it records the reading from just before, so you can check it later. No model calls, nothing added to the conversation; it does not prevent compaction.

Save whole turns — the question plus the full answer — as plain Markdown inside the session workspace, promote the good ones into a cross-project personal knowledge base, and let the model search it on demand. No database and no runtime dependencies.

Read-only Skill inspector for DeepSeek Harness. It shows which Skills a conversation actually loaded — from observed loading evidence only — and which Skills the current environment can discover, and gives each Skill a detail page whose left column switches between the framework, the evidence, validation, evaluation, step evidence, run logic, the before/after of a modification when there is one, the definition facts and the raw SKILL.md. Declaration and run stay apart: the body is split into structure, declared workflow and progressive disclosure, the run logic is read from local receipts, and every declared step carries its own evidence — no observed evidence is reported as exactly that, not as executed or not executed, and the run's instruction hash sits beside the current definition as match, mismatch or unavailable. The evidence view gives each subject one of three states (declared, observed, unavailable), walks definition → load → use → outcome, names what each stage cannot reach, declines to attribute an outcome to the Skill, and can copy the snapshot out as byte-stable JSON. Validation checks the Agent Skills open standard and the platform profiles separately, each finding on a rule id and labelled standard compliance or platform compatibility. Evaluation keeps repeatable cases with the conditions each run was recorded under and the four stages of runtime evidence, comparing two runs of one case item by item without scoring them. The trigger boundary keeps should-trigger and should-not-trigger prompts, has you run them in a real new session, then records what was observed — whether a load record appeared and whether it was model-invoked or user-explicit; a typed /name is not a natural trigger, and an absent load record is reported as not observed, not as not triggered. The same projections are exposed to the agent as a read-only skill_review tool, which returns a structured review packet and says what it omitted when the packet will not fit whole. The inspector, the evidence chain and these reviews are computed on this machine from the definition and the session receipts; the Chinese reading version sends the body through the host's model when you ask for it, keeping code fences, paths and frontmatter verbatim and storing the result on this machine. A Skill can also be cloned into a local copy. It does not write back to the source Skill and does not run its scripts.

Windows toast and a chime whenever a conversation task stops: completed, waiting on your approval or answer, or failed. Clicking the toast reopens that session at your last question, and in DSH Desktop it also raises the window.

Shopping assistant for e-commerce: search, compare, pick and recommend products when buying things online, with price comparison, sales, service tags, product images and promotion links from the official Pinduoduo open-platform API, right inside the DSH conversation.