Plugins

NextTavern is a long-form roleplay plugin for DeepSeek Harness 0.1.7-rc.2 Web, with character-card import and creation, worldlines, worldbooks, layered long-term memory, keyword/semantic/hybrid retrieval, character agents, and card or novel export. SillyTavern character-card import is supported; v0.2.9 fixes distribution and installation.

SillyTavern-compatible roleplay with character cards, presets, world books, and swipe branches that restore their continuations alongside native DSH conversations.

A DeepSeek Harness (dsh) plugin — turns dsh web into a SillyTavern-style roleplay frontend: character cards, prompt presets, lorebooks, personas, BM25 long-term memory, world-state deltas, and rollback-able floor operations, all on the dsh agent runtime.

Role-play conversations with character cards, in-chat character-card authoring and editing, and image generation through configurable backends.

Custom modes / assistant manager: give each mode its own system prompt in the settings page — a custom prompt that is a plain file the agent loop re-reads before every model step, so an edit applies to the running session on its next step — and start it from the official standard / PTC / minimal / Cordis composition, toggling the plugin rows it mounts one by one (a custom plugin composition per mode), renaming it as you like. Several assistants coexist with their own prompts, so one machine can keep a coding assistant, a chat companion and a roleplay (RP) persona side by side — a multi-agent setup you pick from per new session. Rows left untouched stay byte-identical to the shipped ones, platform conditions included.

Host-level proactive wake-ups for DeepSeek Harness: the model schedules its own alarms (once, recurring interval, or cron, with optional random jitter), cold sessions are woken on time by session resume, model-initiated follow-ups are gated by quiet hours and a daily delivery budget, silent wake turns end with proactive_reclaim and fold out of model context as tombstones, declared schedule files glob-sync JSON schedules into host alarms idempotently, min_idle_seconds defers wakes until the destination session quiets down, and a web panel (settings section plus per-session tab, SSE live refresh) manages alarms and wake history — the heartbeat engine for AI companions and roleplay characters with their own daily routines and world evolution.

Every night generates the companion character's schedule for the next day with DSH's configured model, from the persona (AGENT.md by default) and a weighted day type (work, rest, outing, home, overtime, slacking, or your own); injects the date, time, current activity and what comes next into the system prompt, with a speaking-style note so the character does not recite a timetable; adds schedule_view and schedule_adjust tools and a /life command that turns the injection on or off per session. With aa1355721445-lgtm/dsh-image-studio installed, each entry gets an outfit, scene and props from its libraries. A settings page shows today's and tomorrow's timelines and edits day types.

Adds a configurable humanized whale-girl maid persona with immersive roleplay, speaking modes, and a lightweight layered memory with query-triggered recall.

Memory for long-form RP and companion chats: three fading layers, per-turn recall, source labels, character and world boundaries, a relationship graph, image attachments and a WebUI.

Character cards for DeepSeek Harness: inject a persona section into the system prompt, or rewrite the user message through rule cards before the model sees it. Ships a preset card library, single-file card packs that carry artwork, and a Character tab in the conversation view.

DSH-native Tavern character-card, opening and worldbook runtime.

Long-term memory written by the character itself. A sorting plugin watches the workspace and, once conversations have been quiet past a threshold, opens its own session to run the bundled extraction script and turn the recent exchanges into memory files; a heartbeat plugin later re-opens sessions on a probability curve that rises with the time since the last exchange, with quiet hours and a random delay. Ships the memory templates, the sorting guide and the extraction script. Needs Python 3.8+ with zstandard, plus manual setup after install (a preset with agent-instructions, templates copied into the workspace, defaultPreset/sortPreset set to real preset ids; a wrong id fails silently with one log line). Plugin-opened sessions run with full permissions by default. Tested on DSH 0.2.0-rc.2.

AI companion skill for DeepSeek Harness: persona configuration (8 presets + custom), six-type long-term memory, emotion recognition and feedback, and multi-turn emotional conversation with tone post-processing. The skill body must be placed in the agent's skills directory (~/.dsh/skills/love-companion/SKILL.md), and the persona/memory pipeline runs on a local Python 3 (standard library only).

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.

Custom modes / assistant manager: give each mode its own system prompt in the settings page — a custom prompt that is a plain file the agent loop re-reads before every model step, so an edit applies to the running session on its next step — and start it from the official standard / PTC / minimal / Cordis composition, toggling the plugin rows it mounts one by one (a custom plugin composition per mode), renaming it as you like. Several assistants coexist with their own prompts, so one machine can keep a coding assistant, a chat companion and a roleplay (RP) persona side by side — a multi-agent setup you pick from per new session. Rows left untouched stay byte-identical to the shipped ones, platform conditions included.

Injects a persona into the system prompt and a past conversation into context, with a settings page and a conversation picker.

Tavern Helper (JS-Slash-Runner) compatible script-runtime API for DSH (self-written re-implementation, no upstream source)

DeepSeek Harness 的「便携酒馆」插件：RPG 式 SillyTavern V2/V3 角色卡生成器 + 酒馆角色扮演聊天。支持世界书、角色卡 JSON/PNG 导入导出、面板主题与本地音乐。独立插件，仅依赖官方 @deepseek-ai SDK。

Roleplay companion memory for DeepSeek Harness: per-conversation editable persona documents (1-100 weight per entry, AI may refine them in small story-driven steps), per-speaker favorability and bond in multi-person chats, active memories with AI-scored vectors, a nine-emotion table updated every turn, an AI self-evolution ledger, recent 48-hour transcript search, companion-style conversation compression, sleep-time compute that pre-guesses the next topics while a conversation is idle, per-conversation tone cards learned from its own past replies, a habit-hint small-model bridge that writes the user habits it extracts into this conversation memory, a date-archived local knowledge base with auto-packing by turns or tokens, and a unified integrations page that lists curated plugins and downloads their GitHub releases.

femo (Flow Emerges Mag Opus) — 用写剧本的方式编排多智能体世界。dsh 插件版：引擎、桥接器、可视化编辑器全在一个文件夹里，自包含，整个文件夹搬走即用。

Local-first long-term companion plugin suite for DeepSeek Harness

Personas, memory and opt-in proactive chat that resumes after restart for DeepSeek Harness Desktop. 社区预发布插件：白饭鱼女儿、角色记忆与重启恢复主动聊天。

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.