플러그인

DeepSeek Harness용 PTC 런타임입니다. 모델이 작성한 프로그램을 순수 Go로 구현한 JavaScript 엔진 moejs에서 실행합니다. dsh 파일 샌드박스 안의 장기 실행 사이드카 프로세스로 동작합니다.

Laya 타입 지정 결정(`noul` yes/no, `choice`, `score`)을 일급 Cordis 서비스(`ctx.laya`)로 제공하고 모델이 볼 수 있는 `laya_ask`와 `laya_plan` 도구를 추가합니다. 플러그인 자체는 아무것도 설치하거나 다운로드하지 않습니다: 직접 시작하는 `laya-mcp serve` 사이드카의 클라이언트이며, 첫 도구 호출에서 불분명하게 실패하는 대신 사이드카가 실행 중이 아니라고 보고합니다.

DeepSeek Harness용 호스팅형 무료 비전 사이드카로, 영구적인 세션 증거를 남깁니다.

Harness 자체 Agent Teams용 제어 플레인입니다. GUI와 같은 경로로 일반 독립 세션을 만들며 각 멤버는 모델을 따로 사용해 다른 대화처럼 열고 이어갈 수 있습니다. 사이드카 명단과 작업 보드가 조정하고 각 작업에 완료 조건을 둡니다. 멤버의 완료 보고는 Lead 검토를 기다리고 상태로 대기, 검토 대기, 최근 턴 실패를 구분합니다. delegationEngine=auto는 구성에 따라 독립 세션, 이어갈 수 있는 하위 에이전트, kernel roster를 사용합니다.

텍스트 전용 DeepSeek 경로에서 이미지 붙여넣기를 알리고, 비전 사이드카로 첨부 파일을 설명하며, 기본 비전 모델은 손대지 않습니다.

Backup, restore and machine-migration for DSH: packs skills (which live outside ~/.dsh, in ~/.agents/skills), plugin manifests, core config, memories, todos and optionally sessions into a tar.gz with a sha256 sidecar, then imports it on another machine as a three-way merge against a baseline, listing per-file differences instead of overwriting changes made there. Credentials never enter an archive (filename deny-list of 27 names plus 7 private-key suffixes plus a content gate, enforced again on the import side), every import writes a pre-restore snapshot first, and an archive can be uploaded to any WebDAV server and pulled back on the new machine. Also includes scheduled backups, a read-only viewer for individual files, and an in-panel cloud card; no npm runtime dependencies (packing uses the system tar).

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.

Select text in the DSH Web GUI and ask about it in place (floating button, or the Alt+Q shortcut): an independent subagent that inherits no parent context answers, streaming into a side card hosted by the native right sidebar, dsh-better-sidebar, or a built-in overlay — and the question can be routed to the main conversation instead.

dsh plugin: tool failure radar — error rates, retry clusters and slow tail per tool from the tool-trace sidecars.

Document review workbench: select text in a Markdown file, leave comments saved as MRSF sidecar files next to it, and let the agent read them with doc_review_* tools and propose edits you accept or reject.

Native Windows desktop control for DSH: window enumeration, UIA control tree, in-process GDI window capture, offline OCR text finding and clicking, background UIA invocation without moving the cursor, clipboard-based CJK typing and key chords, plus a course-playback helper. Ten tools, no driver, no extra runtime.

Agent Sidecar as a native DSH plugin: cross-agent monitoring, injection and bypass analysis / 跨 agent 监控、注入与旁路分析

MasterGo Canvas MCP bundle with a managed local sidecar for DeepSeek Harness

로컬 AI 에이전트 세션(cursor-ide, claude, codex, copilot, kimi 및 dsh 자체)을 위한 교차 에이전트 모니터링 보드로, 세션 타임라인과 기본 비활성 상태의 2단계 확인 게이트 뒤에 있는 메시지 주입 기능을 제공합니다.

DeepSeek Harness 웹 클라이언트 플러그인: 사이드바 워크스페이스를 구성 가능한 3단계 트리(분류→프로젝트→세션)로 그룹화합니다. Sidecar YAML 규칙. dsh-plugin.

agent-governance 사이드카를 기반으로 한 DeepSeek Harness(dsh) 승인 응답기 — 모든 승인/요청은 기본 거부(deny-by-default) 게이트, L0–L4 규칙 및 조직 감사 체인에 의해 결정됨.

Agent-team orchestration sidecar for DSH: teams with a configurable member cap, real sub-agent members with per-member model routing, task DAGs that dispatch automatically when their dependencies finish, a broker that enforces fs/exec/net/env permissions, and a live web panel over SSE.

Translate installed plugins' documentation into Simplified Chinese: README sections are translated with a persistent section-level cache, and an opt-in metaSidecars mode (off by default) writes a locale/zh.json sidecar for each Plugins list row so the list can render Chinese natively.

Connects a ComfyUI server to the agent through five draw_* tools (status, workflows, models, generate, reverse) and a sidebar panel. It ships no workflows and assumes nothing about your models: every API-format JSON you drop into the workflow directory is inspected to find where prompt, negative, width, height, steps, cfg, seed and LoRA live, and a sidecar file can override what was detected. LoRA injection splices into any graph. All paths are configuration, editable from the panel and saved to a settings file, so it works against a remote or already-running ComfyUI. Headless auto-start and idle shutdown are opt-in and off by default.

DocChain knowledge base and document conversion toolkit — filename, content and metadata search, locate-by-doc_id/name with content reading, topic listing, bulk document upload, document-to-Markdown conversion, image-similarity search, per-document image descriptions saved to a sidecar markdown, and a deep-research workflow. Every script-backed capability also ships as a native DSH tool executed in-process (doc search, content search, filename search, topic info, metadata search, upload, image search, image describe, doc2markdown). The configuration page keeps several docchain environments (each with its own address and credential), switches between them in one click, and pre-selects topics per environment. Needs a docchain service URL and API key (except doc2markdown); image descriptions additionally need an OpenAI-compatible multimodal endpoint (defaults to an internal gateway model, configurable).

Trip planning workspace for DeepSeek Harness: a map page with day-by-day stops, roam_* tools that draft, review and adopt an itinerary, and optional MCP sidecars for rail tickets and Xiaohongshu notes.

Harness-owned lifecycle for the dario proxy — starts it with your harness, readiness-gates it, and stops it when the harness stops, so subscription-backed (Claude/ChatGPT) model routes just work.

Composer attach button for DSH Web: multi-file picks become inline draft capsules, files are stored under the workspace uploads root with an auto-extracted UTF-8 .txt sidecar (txt/docx/xlsx/pptx/zip/odt, zero dependencies), and sent messages carry only the file name — never a raw path.

Free anonymous OpenCode Zen models inside DeepSeek Harness (DSH): native LlmAdapter, no API key, no child process; optional Go sidecar included