All Plugins

Bring your existing Agent Skills (SKILL.md) library to DSH: discover skills across Claude/Codex/Cursor/Gemini paths, inject a progressive-disclosure index, and load bodies on demand.

DeepTutor tutoring bridge: deep explanations, self-test questions, learning-path planning, personal knowledge-base search (RAG), and note archiving via deeptutor_run / deeptutor_kb / deeptutor_note tools.

Microsoft cross-platform sandbox support.

Web Components support.

Build auditable KB packs (SQLite FTS5) from md/txt/docx/pdf with deterministic retrieval and original-text reading.

Project .pack.json/.pack.zip into .agent-pack/modpacks/ and expose skills via a workspace allow-list.

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

Agent-tree token budget management.

Incremental diff reviewer for DSH: after approving a batch, only new changes since the checkpoint are shown, with a Web review panel and `/review` command that inject feedback back to the agent.

Telemetry backend exporting turns, model steps, and tool calls to yiTrace.

Mobile-first DeepSeek Harness UI with an installable PWA, responsive navigation, and Web Push notifications when an agent completes successfully.

Turns the iterate skill into an autonomous closed-loop harness — plan, parallel review, atomic fixes, validate, loop, auto-stop — plus a dry-run review-only mode and a meta-review that audits the report and emits a final review report.

DeepSeek wallet balance at the sidebar foot: a credit-card icon with the amount tinted by remaining balance (green over ¥2, amber ¥0–2, red below), refreshed on mount, per turn-end, and on click; a signed delta floats up and fades on each balance change.

Layered memory pipeline for DSH: auto-distills conversations into atomic facts, scene summaries and a persona profile (L0–L3), with hybrid BM25 + vector retrieval, chat/work family separation, and context injection before each model step.

Multi-window wall for the DSH Web UI: run and monitor N conversations side-by-side in one screen, with auto-discovery, per-window controls, and an authenticated LAN gateway for phone/tablet access.

Focus mode with a full-screen reading overlay that hides the header and composer and folds AI tool calls into summaries.

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.

Ollama Cloud native chat adapter: direct NDJSON translation of the Ollama /api/chat wire format, model discovery with context windows and capabilities, and web search/fetch providers under the ollama-cloud id, plus a Web settings card.

Draggable floating cat-or-dog companion for the dsh web GUI that changes expression with the session and is configured on a Companion settings page.

Live-tune the DSH Web conversation UI from Settings: message font size, Claude Desktop-style markdown tables, dialog width, an optional timeline rail, and a GitBar with branch management, per-file diff, and commit & push.