CATEGORY
Verified manifests and exact versions in this category.
dsh-im-companion
dsh-im-companion: Enhances dsh-im with the concepts of assistants and homes—see at a glance which workspaces have assistants managing them and who is online or offline; move them with a simple drag.
dsh-model-fusion
Fusion for DeepSeek Harness: one model entry backed by a frontier Lead that reads, briefs and reviews, and a much cheaper Sidekick that writes the code.
martty
Terminal-native ACP client UI; Cordis client tree, any ACP agent
dsh-proactive
Host-level proactive wake-ups for DeepSeek Harness: let the model schedule its own alarms (once / interval / cron with random jitter), wake cold sessions on time, gate model-initiated follow-ups with quiet hours and a daily budget, and reclaim silent wake
dsh-maze
The execution maze for DeepSeek Harness agents: see how the agent actually worked — main path, detours and backtracks on one timeline, with data tracks, deterministic analysis, and multi-session comparison
huashu-nuwa
女娲: Distill anyone into an executable thinking Skill.
dsh-advisor
dsh plugin bundle porting the omp advisor subsystem: a per-session reviewer model that observes the primary transcript and injects severity-ranked advice (nit/concern/blocker).
dsh-agent-studio
DSH graphical Agent configuration console: visually assemble prompts, tools, skills, sub-agents, and fallback models; bind a preset to take over; create custom presets through the platform’s preset registration entry; all configurations are stored in the plugin’s own data and are restored to their o
dsh-routing-suite
A lightweight, selectable smart-routing mode for DeepSeek Harness.
@goodandready/dsh-moa
Mixture of Agents (MoA) plugin for DeepSeek Harness with /moa slash command
rainskills
Agent Skills for deploying, troubleshooting, and verifying applications on Rainbond from Codex, Claude Code, and other AI coding agents
dsh-harness-one
Workflow One - Visual AI workflow orchestrator for DeepSeek Harness (dsh): multi-agent DAGs, live execution, recovery, and Feishu integration (single-package edition)
@sakura12/oh-my-deepseekharness
Multi-agent orchestration layer for DeepSeek Harness — 49 skills, 58 MCP tools, graph DAG runtime, team pipeline & HUD (OMC/OMX adaptation)
dsh-agent-persona
Workspace personas for DeepSeek Harness (DSH): create many system-prompt personas and scope each one by workspace path or session id (exact / prefix / regex / contains), managed from a Web settings page with Markdown editing and AI tuning.
dsh-open-dream-rsi
Let your coding agent dream: strategies must survive counterfactual replay before they earn trust. An offline self-improvement loop over an evolving world model — no fine-tuning, the LLM stays frozen. Speaks MCP. Ships its Python server inside the package
dsh-plugin-subagent-director
Subagent Director: choose an LLM provider/model for each subagent (call args > role binding > plugin default > inherit parent) and plan main-agent/subagent responsibilities with role templates, plus a settings UI.
@aiwayds/dsh-subagent-registry
dsh plugin: register locally-defined custom agents (~/.dsh/agents/*.md) as callable subagents via the use_agent tool, with continuable background dispatch and ask_agent follow-ups
@openma/deepseek-harness-tui
dsh-agent-skills
Discover and manage Claude Code, Codex, Gemini CLI, and other Agent Skills inside DeepSeek Harness.
@dsh-suite/plugin-team-board
DSH plugin: a shared task board for multi-agent / subagent collaboration — create, claim, transition, and query tasks via a Cordis service key.
dsh-expert-orchestrator
Expert Orchestrator — multi-agent orchestration agent preset for DeepSeek Harness (dsh): triage → PM planning → delegate implementation to domain experts via a merged roster (summon_expert), dependency-DAG taskboard, file message bus, tiered delivery gate
dsh-eval-control
DSH plugin for aeval evaluation control and realtime, projection-based personal trajectory analytics.
@morehao/dsh-skills-console
统一管理本地技能的安装、更新、删除与接入,让同一份技能在多个 Agent 间复用。A skill manager for DeepSeek Harness: install, update, remove, link and toggle agent skills.
@sputnikzaychik/dsh-qq-bot
Plugin connecting QQ to DSH Agent (community-maintained): sends and receives messages via NapCat / OneBot 11, with one DSH Agent per QQ conversation.
@zaimokuza/dsh-acp-adapter
Use AI agents from the DSH session UI.
@xiaoso/dsh-workflow-lite
Lightweight agent workflow for DeepSeek Harness: one workflow = one JSON (React Flow native) with prompts inline, compiled into a dispatch plan the model executes itself. No execution engine; optional per-workflow run state kept by the model in a YAML file.
whale_craft
DSH-native Minecraft Agent plugin: an independent bot for each session + mc_* / mc_kit_* / mc_admin_* tools + per-conversation watchdog + browser UI + workspace .whale-craft memory
dsh-novel-solo
novel-solo helper for DeepSeek Harness: a subagent-count setting (1-12) card on the plugin page, saved into the host settings, mirrored to disk and consumed by the novel-solo preset to cap parallel subagent fan-out.
dsh-ronge-adaptive-skill-archive
DSH-native skill intelligence cockpit: task decomposition, cross-domain multi-skill composition, skill authoring, local recommendations and safety scans for DeepSeek Harness.
dsh-plugin-mesh
把跑不完的活交给另一台电脑;跑完,结果回到你面前。两台装了 DSH 的电脑各装一次,自动互相发现,任务派过去由对端的 agent 执行,结果派回来。Hand a long task to another machine: your DSH instances find each other, the peer runs it, and the result comes back. No pairing codes, no IPs, no Tailscale client.