Плагины
Находите, фильтруйте и устанавливайте плагины DeepSeek-Harness.
Найдено плагинов: 161
dsh-ai-company
dsm-dsm/dsh-ai-company
Multi-workspace agent federation with persistent ticket trees, parallel worker sessions, structured evidence reports, independent acceptance checks, retry/stop and restart recovery. Workers get shell and file tools in the ticket's directory, company_verify re-runs the ticket's acceptance commands in a shell on the host, and scope lists are task authorization rather than a sandbox. State is stored in ~/.dsh/ai-company; the optional company_repo_* tools run separately installed aoci/codegraph commands on any path they are given.
dsh-plugin-antigravity-agents
domush/dsh-plugin-antigravity-agents
Native Google Antigravity agents loader and subagent orchestration engine with model selection and Web UI settings integration. Loads agent definitions from ~/.agents/agents and the workspace's .agents/agents; the selected main agent's instructions go into the system prompt, and a matching agent's instructions are prepended to DSH's own subagent and spawn_teammate calls. Settings are written to .agents/agents/settings.json in the workspace.
dsh-devlead (bundle)
yankeguo/dsh-devlead
DevLead mode for DeepSeek Harness: a human-only switch turns one ordinary session into a lead with eight devlead_* tools to register workspaces and create, read, continue and watch other ordinary sessions; it dispatches work to those sessions, reviews the delivery and reports, is woken through a durable notification digest when a watched session's turn settles, and can give a dispatched writing session its own Git worktree when the host provides the experimental worktree service.
oh-my-dsh
sevenology7/oh-my-dsh
Agent orchestration for DeepSeek Harness, aligned with oh-my-openagent 4.19.4: eleven agent roles, planning, delegation, adversarial review, and durable .omd state.
subagent-orchestrator-dsh
turambarr/subagent-orchestrator-dsh
Experiment-orchestration SOP skill for long-running experiments. A top-level model drafts a decomposition plan — subtasks, the model for each, an acceptance figure with tolerance, and dependency order — and dispatches only after the user confirms that plan; each subtask then goes to a lightweight executor subagent as a self-contained prompt, and its report is confined to measured facts and the delta from the agreed figure, with judgement and decisions staying at the top level. Ships one plan template and five task templates (gather, execute, consistency check, read-only review, mechanical transform), acceptance gates split into a task layer and an experiment layer, and three rules that stop internal-consistency evidence from being presented as independent or external validation.
dsh-model-router
yunxiao11xie/dsh-model-router
Serial model orchestration: a delegate tool over a built-in catalog of current Chinese-market models (DeepSeek, GLM, Doubao, Hunyuan, MiniMax, MiMo, Kimi, Qwen, GPT). The main agent splits work, picks a model per subtask with a required reason, waits for each result, and falls back to a default model; every route is checked against the Session model-selection policy before a child starts. Needs Plugins → Subagent → Model selection enabled for the routes you want (new sessions only) and each model's provider configured. Uses the same plugin id as other model-router plugins, so install only one of them.
dsh-conductor
lucagiftzek/dsh-conductor
A Conductor tab and commands for a chat's context: /new replaces the context in place with a model-written handoff, /rewind restores the chat and the agent's file edits to an earlier prompt, plus /drop, pins, an automatic compaction level, recovery after failed turns, silent messages between chats and agent and task orchestration. Supersedes dsh-orchestrator, dsh-force-compact and dsh-continue, so do not install it alongside them. Requires DSH >= 0.2.1-rc.5, Node >= 22.5, the web profile and dsh-better-sidebar.
dsh-project-cockpit
boris-boomer/dsh-project-cockpit
Floating cockpit panel (draggable, resizable, default 400x600) with five tabs — orchestration, matching, cost, signal, graph — aggregating four engines into unified /__dsh/project-cockpit/* webServer routes. Opens via a built-in launcher button; dsh-icon-grid icon is an optional extra entry.
dsh-workflow-library
wilshi/dsh-workflow-library
Reusable workflows: orchestration scripts saved as files under .dsh/workflows, discovered from the project, and run by name with arguments, so they live in git and can be shared. Four tools: list, show, run, save.
dsh-coding-agents
wilshi/dsh-coding-agents
Drive locally installed Codex CLI and Claude Code from DeepSeek Harness through a settings page and agent tools, exposing their sessions, configuration and run state.
agent-control-tower (dsh-tower)
evolution301/agent-control-tower
Control tower tools: dispatch a task to a role agent, read its report, verify and accept or send it back. Requires the separate agent-control-tower Python CLI (tower; it is not on PyPI — install it with pip install -e from the same repo) on the DSH process's PATH plus a tower init-ed workspace; without it every tool call fails with ENOENT.
dsh-card-workbench
xiaoxue-car/dsh-card-workbench
Card-based task orchestration for DeepSeek Harness: splits work into cards, dispatches and monitors tasks, handles stalls, verifies results, and adopts work conversations.
taskboard-workbench
silenzerorz/taskboard-workbench
Agent-team task workbench for DeepSeek Harness: a sidebar board and requirement view track tasks across backlog, execution, review and done, dispatch work to coding agents, and run multi-role team orchestration on a local SQLite store.
baton
lumos-789/baton
Runs an approved OpenSpec change to completion while the model stays a mechanical forwarder: a bundled Python CLI computes the ticket DAG frontier, claims tasks atomically, prepares one git worktree per assignment, and returns exact actions. The session delegates each action with the DSH subagent tool and reconciles the completion notice against a hash-bound receipt produced by re-running verification commands on a clean, advanced HEAD, so free-text "done" never counts. Runtime scope changes are plain tasks.md edits. Liveness is observable, not guessed: status returns a relay block (elapsed and lease budget, receipt presence, heartbeat and activity age, a suggested action); abandoning a plausibly-still-working attempt is refused with the judgment data unless --force; a late sealed receipt is revived by adopt after full re-verification instead of rebuilding the ticket; dispatched subagents refresh a progress heartbeat outside the worktree. Requires Python 3.10+ on PATH and a git project that uses OpenSpec.
dsh-orchestrator
lucagiftzek/dsh-orchestrator
An Orchestrate tab in dsh-better-sidebar and 14 orch_* tools to spawn, prompt, fork and cancel agent chats, run command, scrape, http and agent tasks on local, ssh or remote runners, show provider status cards, and serve a secret-protected machine API. Requires DSH >= 0.1.1-rc.1, Node >= 22.5, the web profile and dsh-better-sidebar.
dsh-member-manager
smpcosy/dsh-member-manager
Управляйте агентами DSH как компанией на базе ctx.agents/subagents: отделы, распределение заказов, учётные данные попыток, журнал аудита и расходов, а также рабочая доска, оргструктура и планирование задач DAG — без нативного слоя команд.
dsh-team-autopilot
wooden-tan/dsh-team-autopilot
Детерминированная автораздача для нативных DeepSeek Harness Agent Teams: пробуждает простаивающих участников при готовности задачи и превращает рекомендательные write scopes в действующий soft lock.
duck-fleet
new-sailfish/duck-fleet
DuckFleet: стая машин, одна команда. Добавьте машину один раз — появится инструмент делегирования ACP; управляйте одной, несколькими или всеми машинами на естественном языке.
dsh-agent-graph
wrc093/dsh-agent-graph
Лёгкая графовая оркестрация для DeepSeek Harness: ограниченные узлы Agent, контракты передачи, ограниченная доработка и многоуровневый общий журнал.
agents-in-the-loop
markelayan/agents-in-the-loop
Межсессионный центр связи агентов DSH. `session_message` передаёт сообщения между сессиями: простаивающую будит с полным текстом; занятой отправляет безопасное уведомление посреди хода и заметки контекста выполнения. Находит адресата по зарегистрированному имени контакта. (stale-id-proof).
dsh-zcode-farm
bowluna/dsh-zcode-farm
Оркестрация нескольких экземпляров ComfyUI: проверяет GPU, свободную VRAM и длину очереди каждого настроенного endpoint и отправляет генерацию на наименее загруженный подходящий экземпляр. Три инструмента: comfyui_farm_status/comfyui_farm_pick/comfyui_farm_run. Экземпляр подходит, только если доступен, имеет не меньше запрошенной свободной VRAM и очередь не превышает лимит. Рейтинг: свободная VRAM минус длина очереди × вес, поэтому простой экземпляр с короткой очередью предпочтительнее. Runtime-зависимостей нет. Повтор после сбоя проверки необязателен: единичный timeout через SSH-туннель не доказывает отказ экземпляра.
dsh-orbit
kasenri/dsh-orbit
Детерминированная среда оркестрации разработки для DeepSeek Harness: orbit_controller и OrbitService запускают дочерние Commander, Executor и Smart Watchdog через PLAN, EXECUTE, EVALUATE, ограниченную коррекцию и восстановление во время работы. Состояние сохраняется в <project>/.cx/state.json.
dsh-cx-browser-plugins
kasenri/dsh-cx-browser-plugins
Сообщественный плагин для DeepSeek Harness: детерминированная инженерная оркестрация с Commander, Executor и Smart Watchdog (CxService + инструмент cx_controller).
dsh-orbit-browser-plugins
kasenri/dsh-orbit-browser-plugins
Детерминированная инженерная оркестрация для DeepSeek Harness: Commander, Executor, Smart Watchdog, ограниченное восстановление и сохраняемое состояние выполнения.