Plugins

Prompt enhancement for the composer: an "✨ Enhance" button rewrites your draft prompt into a clearer, more structured version with first-principles thinking, grounded in session context, memory and recent conversation; asks clarifying questions in a card when key info is missing, then previews the result before applying it to the input.

Brain-inspired cognitive plugin: episodic, semantic, procedural and emotional memory with reinforcement-learning signals, a goal stack with time triggers, curiosity-driven autonomous web research and proactive initiatives.

Draggable sticky notes with 9 skins, image notes, and agent-readable to-do lists for DeepSeek Harness.

A governed swarm of six specialist DSH agents — orchestrator, planner, knowledge-base bridge, developer and two reviewers — turns a requirement into a strict phase pipeline where every delivery must prove itself with structured evidence before the next phase may start; reviewers are read-only, code merges only after a review pass, and an append-only event log gives full replay and audit on a live kanban board. Its design draws inspiration from the Hermes Agent kanban.

Inline +N −M badges on edit/write tool rows and a collapsible per-turn file-change summary card with aligned diffs, review and undo — covers native edit/write, str_replace_editor and Code Dispatch sub-calls, no git required.

Smart subagent routing and evolution: bind roles to any provider/model registered in DSH, including models supplied by Codex and Claude Code provider plugins, with workspace learning.

Named subagent roster: manage role entries (model, persona, tool filter, depth, background mode) from a hot-reloaded settings page; the model picks one with list_subagents and dispatches by id with delegate — foreground, background, or continuable.

Stable, editable PPTX generation for AI agents — semantic IR in, native DrawingML out

Decentralized multi-device fleet: mDNS LAN discovery, key pairing, and SSH direct execution across networks.

Gated multi-agent pipeline for OpenSpec changes — six opx_* tools drive the phase state machine, two agent presets (developer and reviewer) carry implementation and review, and 23 bundled skills define the quality standards they are checked against; full mode runs analyze, implement, then tool, task and dimension-based quality review, while simple mode runs implement and one merged quality review.

Conversational Grafana operations: inspect live dashboard data across named sources, then make safe, reviewable dashboard changes with approval and version checks.

Local-first persistent memory for DeepSeek Harness: bounded pre-step hot-memory injection, exact and Chinese-bigram BM25 cold recall, six agent tools, approval-gated lease-lock writes with recovery receipts, and read-only governance and trajectory-review candidates.

Enhanced ACP server for DeepSeek Harness: block & reasoning streaming, usage telemetry, model/effort switching, permission presets, session resume/archive, per-session MCP servers, and Zed file/terminal forwarding.

Tracks the agent's state as Yogācāra mental factors over a durable seed store, and feeds it back into the prompt as first-person inclination.

Four-module session companion: smart conversation export (Markdown/PDF/JSON/PNG long-image with privacy redaction and batch ZIP), context handoff summaries with template save/import, API cost optimization (live official pricing, peak/off-peak scheduling, daily/monthly budgets, model routing), and global conversation search with in-chat find (Ctrl+F, CSS Custom Highlight API).

Semantic, multi-tab Playwright browser automation for DeepSeek Harness

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).

DeepSeek Harness 通知 + 状态栏插件：任务完成、需要输入、需要选择时弹系统通知（macOS / Windows / Linux）；macOS 与 Linux（含 UOS、Deepin、麒麟）状态栏常驻小图标，显示任务进度与花费。Windows 没有状态栏，只弹通知。

Drive a dsh agent from Telegram: one chat topic per project directory, voice and photo input, ordered per-topic job queue, per-topic goals and task checklists, session forks and branches, live progress message, command menu in en/ru/zh, and control commands for models, plugins, sessions and logs. Search the plugin registry, read a package card before installing, and update every plugin with one tap. Requires a Telegram bot token and your numeric user id in allowedUserIds.

Windows Computer Use for DeepSeek Harness with 21 tools and verified targeting: controls are addressed through their UI Automation identity and patterns, and numbered marks are checked against the live window before input, so a stale target is refused instead of clicked. A known sequence runs in one computer_batch call, one model round trip; incremental observations, compact receipts (normally no more than about 6 KiB extra), bounded handoff waits (HANDOFF_WAIT_TIMEOUT/HANDOFF_HELD_TIMEOUT as continuations), the desktop-block cycle boundary and a deterministic 100 s owner-scoped leave backstop keep context small and prevent a stuck handoff from waiting out the tool deadline. Approval modes settle an unanswerable ask honestly: in a danger-full-access session with no approval card the action runs under that grant, every other sandbox — and every delegated subagent session — refuses and names the unavailable channel instead of reporting a user rejection, and gate diagnostics land in policy.jsonl. Human handoff, a model-visible stop brake and prebuilt native workers.

Deterministic project actions shared by people and agents: one actions.json, a right-sidebar run panel, and agent tools.

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.

Humanized fork of @xmanrui/dsh-im (base 4.21.2): humanized message delivery with send-delay and typing two-phase, message_break + streaming coexistence, status reactions, reply quotes, per-bot humanize overrides, and a no_reply reclaim tool — across WeChat, Feishu, DingTalk, WeCom, QQ, Telegram, Slack and WhatsApp channels.

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.