dsh-dual-model-eval
Compare multiple coding models side by side in DeepSeek Harness with isolated Git worktrees
124 results
Compare multiple coding models side by side in DeepSeek Harness with isolated Git worktrees
多 agent 团队协作:并行调试、并行功能开发、任务协调、沟通协议、团队构成。受 wshobson/agents(38k★ MIT)启发。
Composable multi-model agent roles and legacy Luna/Sol reasoning routing for DeepSeek Harness
Fork any session into a different agent preset — a UI button with preset picker in the conversation header.
AI 多角色协作开发框架:文件即通信 + 教训库 + 决策日志 + 一致性审计 + 复盘持续优化(REVIEW)。注册 ai_collab_init 工具。
DSH web plugin: multi-agent commander. Open Claude / opencode / codex agents with role & skill definitions, watch every agent's live terminal in a right-side radar panel, and let DeepSeek dispatch tasks through agent_* tools. Shared memory: 记忆库.md / 任务看板.md / 交接区 in the project directory.
Jujutsu version control skill provider for DeepSeek Harness agent teams
Automatic TMCRA recall, injection, and role-separated writeback for DeepSeek Harness
dev-team 多智能体技能包(43 技能 + 11 专家代理)的 DSH 一体化发行:启动自动部署技能、运行时注册,并附可视化管理面板(双语、调用短语复制)。
Community visual workflow and multi-model evaluation plugin for DeepSeek Harness
Design, observe, diagnose, and reuse evidence-backed multi-Agent work in DeepSeek Harness
DSH-native multi-AI group chat: the host (user) runs a chatroom of configurable AI agents with per-agent models, role cards, mute controls, and passive/active speaking modes — pure Node.js/Cordis, no Tauri/Rust
TeamFlow 团队研发流水线(TypeScript):需求→PRD→设计→架构→技术方案→并行开发→QA→验收;backlog 持久化 + 断点续跑 + 完成汇报 + 防假交付;Web 团队工作台(conversation.view tab + 拖拽看板)
队长来电(captain-call):AgentTeams 队员完成任务时,桌面助手 GINKA 替 Daisy 队长接听来电,语音汇报'是谁、是否按要求准时完成';点语音回复即直接申请麦克风,与真实队员语音办公对话。
项目 Agent 管理: a supervisor (主管) workspace + N dev-project workspaces, with logical isolation, task handoff, and a sidebar panel for DeepSeek-Harness agents.
A DSH port of obra/superpowers — the full multi-agent software-development methodology (TDD, planning, debugging, review) as native DSH skills
Jira-like Agent-native Project Management for DSH
DeepSeek Harness Web plugin for visualizing, arranging, branching, merging, and summarizing AI agent sessions on an interactive graph canvas
Danus-native DSH plugin suite: verifier-gated mathematical proof-search orchestration (fact graph, role-gated tools, cold-start verifier, worker swarm, orchestration tools, heartbeats).
智能体协作台 —— 多智能体房间/群聊/派单控制台(DSH 内嵌,可上插件市场)
Starship-bridge orchestration for DeepSeek Harness: the captain issues plain-language orders from the bridge; the XO drafts verifiable missions; away-team subagents (recon/engineer/medic/scribe) execute in isolated workspaces with evidence-based acceptance and an append-only campaign ledger.
Role-based AI swarm orchestration for DeepSeek Harness: duty-table model pinning per role, parallel task DAG with review loops, and a live Swarm dashboard tab in the web GUI.
Durable workstreams, peer collaboration and evidence-based delivery for DeepSeek Harness
DSH Web plugin for Agent execution quality diagnosis reports.