dsh-rp-composer
三段式 RP 输入面板:台词/动作/心理分框填写,按模板组装后发送
57 results
三段式 RP 输入面板:台词/动作/心理分框填写,按模板组装后发送
给 DeepSeek Harness Web 主窗口加「工作角色」页签 + 对话区像素人办公室浮层(The Agency en / agency-agents-zh 255+ 角色,29 预设团队)。一条命令安装,不改 dsh 源码。
General APEX preset with a Minimal Pro anchor, role-bounded PTC implementation, verified handoffs, and evidence convergence
Ranked subagent delegation for DeepSeek Harness: role-based model routing with failover, per-route reasoning effort, fork delegation, transparent model labels, and a visual route editor in Settings.
Native RoleHub discovery, verified role Sessions, and Agent Team Room integration for DeepSeek Harness.
DeepSeek Harness plugin: role-based model routing — both roles default to deepseek-flash (V4.1 Flash, native multimodal) until V4.1-Pro launches.
Unified DeepSeek Harness plugin: role-based subagent routing + per-agent evolution — prefercmd/memory as knowledge allow/deny lists, so repeated tasks start from proven commands and save tokens
对角巷 · 角色面具 — 一键切换AI人格,定制专属对话角色
玩 · 酒馆模式完整插件:把 deepseek-harness 的酒馆模式一键打包为可分发、可安装的独立 DSH 插件。支持记忆系统、状态栏、立绘情绪、自定义变量表等功能。
DSH web extension: live subagent monitor + role-based subagent routing + Claude Code style .dsh/agents/*.md persona injection
DSH cross-session messaging plugin: reliable delivery + role addressing for the coding/review loop
DSH AI tabletop / GM plugin for DeepSeek Harness: dice rolls, check resolution, world books, character cards, and DiceFrame content-pack import. Play solo in DSH, play with friends in DiceFrame.
Role-based model routing for DSH subagent delegation.
Danus-native DSH plugin suite: verifier-gated mathematical proof-search orchestration (fact graph, role-gated tools, cold-start verifier, worker swarm, orchestration tools, heartbeats).
OpenAI-completions-compatible adapter for custom gateways (vLLM / LM Studio / self-hosted proxies): always role:"system", enable_thinking / chat_template_kwargs / reasoning_effort driven by the llm-pi-ai model config, and a </think> split on the receive side — no pi-ai behavior guessing.
Automatic TMCRA recall, injection, and role-separated writeback for DeepSeek Harness
Composable multi-model agent roles and legacy Luna/Sol reasoning routing for DeepSeek Harness
DSH-native multi-AI group chat: the host (user) runs a chatroom of configurable AI agents with per-agent models, role cards, mute controls, and passive/active speaking modes — pure Node.js/Cordis, no Tauri/Rust
DeepSeek Harness 角色扮演插件(恋爱向/朋友向/OC 原创向): 全局角色卡、亲密度三轴+里程碑+难度自选、养成商城、心跳想念、剧情档案、人格真实感(隐藏底线+增强)、ST生态(PNG卡/预设/世界书constant)、祛魅画像、桌宠(附加); DSH 0.1.1-rc.2 兼容。
Role-based AI swarm orchestration for DeepSeek Harness: duty-table model pinning per role, parallel task DAG with review loops, and a live Swarm dashboard tab in the web GUI.
Self-contained SillyTavern-style safe message renderer for DeepSeek Harness
AgentTeams for DSH (Wuxie233 fork): per-member model routing, read-only role deny lists
DeepSeek Harness (dsh) plugin: manage named roles, each with a preset system prompt. The active role is injected into the system prompt (replacing it before the conversation starts, appending afterwards). Ships a host service plus a Web client UI.
DeepSeek Harness (dsh) plugin: registers the agency-agents-zh Chinese AI expert agent library (268 roles across 20 departments) as native skills