플러그인
DeepSeek-Harness 플러그인을 찾아보고, 필터링하고, 설치하세요.
플러그인 356개 찾음
dsh-tool-visual-primitives
inkshadewoods/dsh-tool-visual-primitives
모드별 프롬프트(caption, UI, 문서, grounding, topology 등)를 통해 대화 이미지를 분석하고, 좌표 프리미티브(박스, 포인트, 참조)와 함께 구조화된 증거를 텍스트로 주입하며, 세션 수준 캐싱을 통해 replay 및 compaction을 거쳐 재사용할 수 있습니다.
bailinghub-dsh-plugin
bailinghub/bailinghub-dsh-plugin
로컬 DeepSeek Harness 에이전트가 BailingHub를 사용하여 데이터를 조회하고 레코드를 업데이트하며 온라인 스토어, SaaS 또는 기타 관리 시스템에서 허용된 작업을 실행할 수 있도록 합니다.
dsh-sidebar-files
fallen0543/dsh-sidebar-files
DeepSeek Harness용 사이드바 파일 트리: 확장자별 아이콘이 적용된 지연 로딩 트리를 갖춘 파일 패널로, 경로 복사 및 에이전트 전송 기능을 제공합니다.
dsh-cyber-pet
borisshaw6/dsh-cyber-pet
DeepSeek Harness용 사이버 고래 펫: shell.overlay 위에 떠 있고 먹이를 줄 수 있으며 색상을 사용자 정의할 수 있는 고래가 토큰 사용량, 쿼터, 상호작용, 세션 카운트를 보고합니다 — 호스트 채팅 브레인과 브라우저 표면을 갖춘 단일 dsh-plugin 번들
dsh-icon-theme
yzke/dsh-icon-theme
오프라인 SVG 팩과 원본 아이콘 보존 기능을 갖춘 DSH Settings 및 사이드바 작업용 자동화 및 사용자 맞춤형 Fluent 스타일 아이콘.
dsh-plugin-hub (dsh-skill-explorer)
wingsky-1/dsh-plugin-hub
DSH 웹 GUI의 스킬 센터: 로드된 스킬을 소스별(system / project / user / custom / runtime)로 그룹 표시하고 생성, 활성화/비활성화, 삭제(.trash로 이동)를 제공합니다.
dsh-power-button
huasheng33991/dsh-power-button
창 오른쪽 하단에 고정되는 원클릭 시작/중지 버튼: 분리된 헬퍼를 통해 정확한 부팅 호출을 다시 실행하여 DeepSeek Harness를 제자리에서 재시작합니다(loopback same-origin 보호). 선택적 중지만 수행하는 동작도 제공합니다.
pr-genius
zsxh1990/pr-genius
PR 평가 및 개선 컨설턴트: 과거의 안티패턴과 성공 패턴을 바탕으로 PR 성공 확률을 평가하고, 원클릭 점수 산정 및 실행 가능한 제안을 제공합니다.
dsh-youreyes
54xkeee/dsh-youreyes
텍스트 전용 DeepSeek용 비전 툴킷입니다. 모델 호출형 `vision` 도구, deepseek/opencode-go용 래퍼 어댑터(v4 flash/pro), Antigravity IDE 쿼터(default, flash/pro) / 모든 OpenAI 호환 VLM / Gemini / 로컬 Ollama 채널, 압축 재복원 기능이 있는 증거 메모리, 콘텐츠 해시 캐시, 그리고 이중 언어 클라이언트 패널을 제공합니다.
dsh-verify
263311487-ux/dsh-verify
에이전트 산출물을 위한 독립 브라우저 승인 테스트입니다. JSON 사양을 입력하면 실제 Chromium 판정이 출력됩니다.
dsh-telemetry-redactor
030611/dsh-telemetry-redactor
설정된 텔레메트리 백엔드가 받기 전에 `session-telemetry/record` 내보내기 사본에서 지원되는 비밀 정보 패턴을 마스킹합니다.
dsh-malko-prefs
malko/dsh-malko-prefs
Personal dsh preferences: a tunable companion to the official compaction engine (threshold, retention, summarization model/reasoning, turn-end compaction), llama.cpp model import for the Models page, and tab/notification helpers (status-light favicon, bro
dsh-toolong-warning
hjdd14/dsh-toolong-warning
DSH plugin: counts completed compactions per session and raises a floating reminder — with bilingual UI — only after repeated compactions plus heavy extra token spend.
dsh-context-management
plxloyzb/dsh-context-management
Windowed, reversible context management for DeepSeek Harness; replaces Basic compaction.
dsh-actions
pure-craft/dsh-actions
Deterministic project actions shared by people and agents: one actions.json, a right-sidebar run panel, and agent tools.
dsh-orca-glass
huzhengbang2007/dsh-orca-glass
DSH Web plugin that injects an SVG (feTurbulence + feDisplacementMap) refraction filter and applies it through backdrop-filter to panels, bubbles and the input card, and bundles the orca-scene skin with theme tokens plus light and dark backgrounds.
dsh-handoff-compaction
knighthongyu/dsh-handoff-compaction
Compresses older DSH context into a structured handoff, retains recent messages, and keeps session history searchable.
dsh-bigfish
gosomea/dsh-bigfish
Animated DSH Web pet with model-adaptive output pacing, tool-state reactions, replaceable character packs, and a bundled skill for creating or extending pet animations.
dsh-experience-memory
marquez807/dsh-experience-memory
Cross-session experience memory for DSH. Lessons are evidence-graded, injected when the turn is about the same thing, and shown just before an action only when the record declares which call it applies to. A rule that holds whatever the turn is about — "always answer in Chinese" — can be marked **standing** and is then carried every turn: measured on 24 isolated real-model turns, a standing rule is followed 6/6 against 0/18 for the controls (empty store, same record unmarked, unrelated standing record). A guess still cannot become always-on: a standing record needs a verified passage like any other. What nobody looks up is retired, reversibly. Five tools, seven slash commands, zero runtime dependencies.
dsh-simulated-life
john-walks-slow/dsh-simulated-life
Simulated life context for DeepSeek Harness: every turn injects the past 24h of simulated life events from the workspace .life/ directory (sliding-window filter, session-level deduplication with delta updates, world summary) as a collapsed context notice, and the life_react tool lets the agent record feelings, thoughts and actions back into its life log for the next round of world evolution — turning a DSH agent into a roleplay character with a persistent daily life.
context-guardian
luminarisoftwares/context-guardian
Compaction fallback for compaction-basic: when its LLM summary throws, comes back empty or cannot fit the window, the span is compiled deterministically with a seq pointer on every line (vendored dsh-compaction-instant compiler). Adds recall and search tools, /recall and /context commands, an idle trigger at 45% of the window and an on-disk span archive. The engine mounts as one row in the agent preset (docs/dsh-integration.md).
dsh-clear-mind
john-walks-slow/dsh-clear-mind
Model-autonomous context compaction for DeepSeek Harness: a mind_map tool surveys the agent context surface (stable seq ids, roles, token weights, clear-boundary markers, the clear-mind playbook), a clear_mind tool replaces a chosen conversation-history span with a model-written checkpoint through the native compaction transaction, call and result pairs self-collapse into one-line tombstones, and a proactive reminder nudges the model when the context grows long or a turn runs too many steps.
dsh-compact-agents
zhuto666/dsh-compact-agents
Model-callable compact_agents tool that force-compacts context in every live session (main session, ordinary sub-agents and AgentTeams members alike), queues busy targets and compacts them when the turn ends, reports the shadowed node count and estimated tokens per target, and ships a browser form for the trigger ratio, retained ratio, controlled-phase output budget, auto-continue budget and an end-of-turn pre-compaction ratio that compacts near the trigger line once a turn ends, so a reply no longer opens with a wait for the summarizer.
dsh-observational-memory
epcn-fla/dsh-observational-memory
Distills session work into background observations and reflections to preserve context across compaction.