dsh-multi-model-orchestrator
Multi-model orchestrator: the main brain decomposes complex tasks and dispatches subtasks to GLM / Kimi / Qwen sub-agents by each model's strengths, with per-model token usage.
多模型主脑编排器：主模型将复杂任务拆解，按各模型优劣分派给 GLM / Kimi / Qwen 子代理执行，并按模型统计 token 用量。
How to install
dsh plugin add dsh-multi-model-orchestrator About
dsh-multi-model-orchestrator A DeepSeek Harness (dsh) plugin that turns your primary AI into a **multi-model "main brain"**. When a task is complex, it decomposes the task into subtasks and dispatches each to the sub-agent model best suited for it (GLM / Kimi / Qwen / any OpenAI-compatible route you configure), while tracking **per-model token usage**. Features 1. **Multi-model orchestration guidance** — a system-prompt section coaches the main brain to decompose complex tasks, inspect available routes with list_subagent_models, and dispatch each subtask via subagent with an explicit provider …
Recommendation signals
Meta
- License
- MIT
- Language
- JavaScript
- GitHub stars
- 4
- mo. downloads
- 294
- Last push
- 2026-09-07
- Created
- 2026-09-05
Basic safety check
- Findings
- None
- Sources
- curated:awesome-dsh-plugin.com, curated:awesome-dsh-plugin/awesome-dsh-plugin
- Topics
- deepseek-harness, dsh-plugin
Related plugins
dsh-plugin-subscriptions
V1ki/dsh-plugin-subscriptions
Use ChatGPT (Codex), Claude, and Grok subscriptions as DeepSeek Harness LLM providers, with Settings login, model catalogs, usage, plus image_generate, video_generate, and x_search tools.
dsh-workbuddy-connect
corrinehu/dsh-workbuddy-connect
Brings the models in the WorkBuddy desktop app straight into DeepSeek Harness — zero configuration in the DSH chat.
claude-code-router
musistudio/claude-code-router
One local control plane for every AI agent: route across models, fuse new capabilities, orchestrate tools, and stay fully in control.
dsh-thinking-effort
hytime/dsh-thinking-effort
Configure reasoning-effort levels and sub-agent defaults for custom DSH models.