dsh-agent-team-gui
Persistent multi-model squads for DeepSeek Harness with durable orchestration, DAG workflows, run history, and provider-reported token usage
19 results
Persistent multi-model squads for DeepSeek Harness with durable orchestration, DAG workflows, run history, and provider-reported token usage
Cortex — 低成本高质量多模型递归任务编排、模型评测与智能路由平台(DSH 插件):任务画像/策略匹配/递归拆解/动态路由/四级质量门控/批量监督/恢复引擎/预算控制/策略沉淀/KPI
Multi-agent orchestration and LLM model routing for DeepSeek Harness (DSH): semantic AI agent Specialists, exact model routes, declarative Cohorts and Strategies, and bounded subagent delegation.
A DeepSeek Harness (dsh) plugin: orchestrates complex tasks across multiple models — a 'main brain' decomposes the task and dispatches subtasks to GLM / Kimi / Qwen etc. sub-agents by each model's strengths, with per-model token usage.
Register models, assist with portraits, and select the Agent model from a secret-free catalog for DeepSeek Harness.
Isolated multi-model coding matches with deterministic verification, scoring, and reports
DeepSeek Harness multi-model routing plugin: route tasks to custom specialist agents (vision / image generation / translation / speech / subagent) with per-agent providers & models, multimodal account sign-in, OAuth account pools, and realtime usage stats
Message review (multi-model cross review) + quote (Q&A chips) for the DSH conversation UI
Two-tier model router for DeepSeek Harness — automatic execution/judgment routing with LLM Judge, multi-model fallback chains, and exponential-backoff runtime failover. A DSH adaptation of pi-shift-router.
DeepSee: DeepSeek Harness vision, multi-model routing, and Gemini visual self-checks before delivery
Multi-model governance, routing, fallback, quota, and usage for DeepSeek Harness
Compare multiple coding models side by side in DeepSeek Harness with isolated Git worktrees
Community visual workflow and multi-model evaluation plugin for DeepSeek Harness
Composable multi-model agent roles and legacy Luna/Sol reasoning routing for DeepSeek Harness
Explicit, evidence-first multi-model consultation for DeepSeek Harness
Evidence-first multi-model coding comparison workbench for DeepSeek Harness
多模型候选评审管线:调度智谱 GLM / Claude(CLI 无头,可走中转)/ Gemini(OpenAI 兼容口)/ Codex 四视角评审成长 artifact(教训/规则/审计板),输出严格 JSON(verdict/strengths/risks/suggestions/cannot_claim),结果只作 candidate_review_input,永不替代本地证据。适用:用户要求外部交叉评审、周期性仪式前自动评审、怀疑某条结论过度推广时。
DSH plugin: consult multiple expert advisor models in a retro chat-group card — auto-deepen consultation pipeline with real streaming, SSE replay, and 26 provider presets.
Flagship multimodal vision hub for DeepSeek Harness: ~40 tools, PDF drag-and-drop, LaTeX formulas, complex tables, QR codes, UI flow diagrams, and multi-model consensus.