Plugins

DeepSeek Harness plugin for organizing AI discussions into research topics, traceable knowledge cards, and reusable research materials on an interactive graph

Group-chat multi-agent orchestration console for DSH: autonomous decision-making, task dispatch, verification and iterative optimization for long tasks; bundles its own backend, installs with `dsh plugin add`.

Persistent project memory, event-sourced task lifecycle, context budgeting, and cooperative multi-agent handoffs.

Actionable quality diagnostics for DSH agent sessions, with tool-call evidence and next-step recommendations.

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.

Conversation-level multi-agent workbench for editable task planning, real child-session observation, plan-versus-runtime comparison, and evidence-backed recovery previews; tested with DSH 0.1.1-rc.2.

User-defined agents with automatic routing, model failover, and squad orchestration: six model tools (agent_dispatch / agent_followup / agent_list / agent_squad / agent_import_skill / agent_upsert), no built-in agents, a native right-tab panel (Overview / Agents / Squads / History), and a floating action ball.

Workflow One - Visual AI workflow orchestrator for DeepSeek Harness (dsh), with multi-agent DAGs, live execution, recovery, and Feishu integration

Multi-agent dashboard skill for DeepSeek Harness -- status reports, task tracking, progress visualization

DeepSeek Harness (DSH) plugin that delegates coding tasks to the Claude Code and Codex agent CLIs and streams the whole run live — autonomous control, multi-account, automatic install, git worktrees, and any Anthropic-compatible endpoint.

Respondedor de aprovações do DeepSeek Harness (dsh) apoiado pelo sidecar agent-governance — toda aprovação/requisição é decidida pelo gate de negação por padrão, pelas regras L0–L4 e pela cadeia de auditoria organizacional.

Execute Claude Code e Codex como painéis de terminal ao vivo ao lado do dsh: uma visualização dividida na interface web, botões para posicioná-los e ferramentas que permitem ao agente dsh delegar trabalho a eles e ler suas telas.

Protocolo de colaboração multiagente independente de projeto para o DeepSeek Harness: guardas de laço que param laços descontrolados de agentes, um formato de passagem de seis campos, roteamento de revisão por nível de risco e uma sequência fixa verify→commit→push→review→close. Uma skill em vez das mesmas regras copiadas nas instruções de cada agente.

Descobre e verifica papéis portáveis do RoleHub, fixa cada pacote exato e então lança seu prompt e suas skills empacotadas numa sessão DSH isolada e continuável, com vinculações de ferramentas aprovadas pelo Host e anexo opcional ao Agent Team Room.

Passe o contexto focado adiante sem esperar ou interromper o Agent ativo: congele um snapshot limitado da Session, resuma-o assincronamente com um LLM isolado sem tools e entregue uma cápsula com proveniência a outra Session ou Room autorizado — silencioso por padrão para Sessions, com wakeup explícito disponível.

Descoberta e comunicação entre Sessões no mesmo runtime para o DeepSeek Harness

Lightweight graph orchestration for DeepSeek Harness: scoped agent nodes, handoff contracts, bounded rework, and a layered global ledger.

Role-based subagent delegation for DeepSeek Harness: one delegate tool over a folder of role files, with a roster that ships and stays overridable

Feishu multi-agent robot console: start, stop and reconnect the daemon, view status and recent activity, and jump to the task workspace.

ETeams for DeepSeek Harness: captain-led multi-agent team collaboration with execution chains, task slots, member dialogs and persistent state

AI 主持人驱动的多角色群聊插件（DSH Host）：自动生成主持人 + 3~6 专家团队、动态调度讨论、成员 subagent 深度推理、总结结论并导出 md 到工作区

Peer communication between conversations in one DeepSeek Harness process: list the conversations the workspace shows, link one under a nickname, message it without waiting for its turn to end, read its progress without waking it, and declare rules for your own tool calls.

DeepSeek Harness Agent 团队的信任指数插件 —— 为 spawn 出的 teammate 做实时信任评分：四维 EWMA 信任账本（按 agent 类型指纹跨会话累积）DeepSeek Harness Agent teams plugin — live trust scoring for spawned teammates: a four-dimension EWMA ledger keyed by agent-type fingerprint (cross-session)

Multi-agent frugality defense plugin: read-ledger dedup metrics, compaction-immune rules, completion gate, cheap-model review lane.