플러그인

A prompt optimizer in the composer input tool row: pick a category and a template, then ✨ rewrites the draft in place with one-click undo. Pick from the Basic, Context and Image categories; you can cancel a run, and it shows elapsed time and token usage. Ships 15 templates covering task-instruction rewriting, step planning, safety-research framing, system-prompt role cards, and text-to-image / image-to-image prompts; context templates read the recent turns of the session for coreference resolution. Calls go through the host model service, and a settings section exposes the model and the budgets. Output guards check that user-written constraints survive, warning rather than auto-retrying. Adapted for dsh 0.1.7 and 0.2.

Role-play plugin for DeepSeek Harness: imports SillyTavern character cards (JSON/PNG) and world books (lorebooks), binds DSH skills to a character, and registers the combination as a native agent preset.

Chinese multi-agent workflow with per-role model fallback, versioned Mermaid task plans, independent Agent and Jev reviews, persistent expert collaboration, and pure-function calculation tools.

Dependency-ordered multi-agent team runner for DeepSeek Harness: define roles with their own model, persona and tools, run a node graph with an independent review gate and bounded rework, and watch progress in the web UI.

DeepSeek Harness native immersive roleplay studio & companion system. Unifies decoupled character cards with Hindsight graph memory.

File-defined subagent roles for DeepSeek Harness: roles live in project and global .dsh/roles files, a delegating agent sees one catalog line per role, and each role's tool policy decides which tools its child can see.

Fleet console for DeepSeek Harness: one local dsh page manages many remote dsh machines — live idle/running status, in-place switching without new tabs, keep-alive iframes, cross-device session reading, one-click refresh/restart, and a controller/managed role split.

Login gate for the dsh web UI: unauthenticated visitors get a login/register page and the first registrant becomes admin; includes user and role management plus login and access audit logs.

Context trimmer: lists the current session's context entries with role, preview and ≈token estimate (cl100k), highlights over-threshold items, and removes selected entries exactly without LLM summarization.

Cross-app project memory for DeepSeek Harness with role-separated writeback, a visual knowledge workspace, confirmed corrections, session controls, local Writer and organizer settings, and an account-free Windows local installation preview.

OpenAI-completions-compatible adapter for custom gateways (vLLM / LM Studio / self-hosted proxies): always role:"system", thinking driven by the model config, Qwen-style response split, and vision-model image input (single / multiple).

AI 코딩 에이전트용 브랜치 역할 보호 기능입니다. integration/preview/production/archive 역할을 설정하고 보호 브랜치의 직접 push, force-push, 삭제와 agent의 production/archive 병합을 차단합니다.

이름 있는 역할을 사용하는 플래너/실행자 위임: 강력한 플래너가 지휘하고 일회용 실행자 서브 에이전트(역할별 라우트와 프롬프트)가 구현합니다. 기본 역할과 위임별 재정의, 작성기 칩의 전역 추론 강도 노브, 역할 관리를 위한 설정 페이지를 제공합니다.

사고 모드를 지원하는 원클릭 OpenAI 호환 API(CodeBuddy/vLLM/프록시)로, developer 역할의 content_filter 거부를 방지합니다.

순위 기반 서브에이전트 위임: 역할 기반 모델 라우팅과 페일오버, 경로별 reasoning effort, 모델을 감추는 라벨, 포크 위임, 시각적 경로 편집기.

advisor, reviewer 및 designer 역할을 사용하는 헤드리스 Claude Code 컨설팅, 참조 답변으로 반환

이식 가능한 RoleHub 역할을 탐색하고 검증한 뒤, 각 번들을 정확히 고정하고 그 프롬프트와 번들 스킬을 Host가 승인한 도구 바인딩과 선택적 Agent Team Room 연결을 갖춘 격리되고 계속 가능한 DSH Session에서 실행합니다.

DSH 웹 UI용 무설정 모드: 고급 화면을 숨기고 최적 기본값(채팅 모드, 전체 접근, 계정 잔액)을 자동 적용하며, 원클릭 역할극 페르소나(메이드/집사)를 제공합니다.

Agentic roleplay for DSH with structured worlds, autonomous characters, persistent sessions, world authoring, speech, and image generation. Requires Firefox2100/dsh-agentic-roleplay#state to be installed and enabled.

Persistent SQLite session state, story memory and recall, repositories, and model-facing record tools for DSH roleplay plugins.

Imports SillyTavern AI presets as switchable, editable prompt layers: preserves the raw JSON, edits prompt order and sampler parameters, previews the injected System Prompt, exports back to SillyTavern-compatible JSON, and archives or permanently deletes presets with confirmation. Applies temperature and maximum output tokens to Harness requests; other sampler fields are preserved and exported but not applied.

Replaces the new-session hero with a combined picker: role cards for the agent presets and a workspace card, collapsed into capsule buttons that expand into two scrollable rows.

Three-player LAN Dou Dizhu (斗地主) played from a floating window: one machine opens a room on its own port, the other two join with a six-character room code plus an address. Empty seats can be filled by computer players in four switchable strengths (easy, medium, hard, hell), so one or two people can still play a whole hand; the deal starts as soon as the three seats are filled. 54 cards in four suits, bidding of 1/2/3 or pass, the landlord takes the three bottom cards and holds 20, play runs clockwise, and the first-bid seat rotates clockwise between hands. The rule engine is pure and covers 11 legal shapes, with big joker > small joker > 2 > A > K down to 3, suits never compared, straights, pair-straights and planes excluding the 2s and the jokers, and a rocket that beats everything. The table itself is built to be read at a glance: three seat cards side by side in play order (you, then your next and previous seats) with role, hand count and a bar that runs out, one line that says whose hand is on the table and what would beat it, the bottom cards as text, an in-place play history that folds into a single summary line and unfolds into every trick including the passes, plus hint and auto-play buttons that pick the cheapest legal answer out of the local rule enumeration. Nicknames can be changed mid-hand (twelve characters, duplicates get a suffix). Computers run inside the authority and are handed only their own hand, the public record and the seat counts, so no hand can leak; the authority is the only place that decides which card ids leave it. Computers are driven by the room itself, so a one-person table keeps playing with nobody else on the LAN port. Humans have no turn timer, the collapsed floating pill can be dragged around the screen, and 179 unit tests pin the rules, the wire format, the theme tokens, the drag gesture, the history grouping and the computer seats.

Zagent — unified three-role self-improvement loop with three operators. Data-RSI (daily cross-sectional cleaning: winsorize → cross-sectional standardization → median fill, plus experience extraction), Harness-RSI (evolves system prompt / memory / skills), and Model-RSI (evolves alpha training recipes via framework-native walk-forward with 2-day gap and multi-seed). Offline one-command run, GPU auto-detect. Ships one skill.