#llm-orchestration

Claude as subagents in Codex — scoped workers, resumable sessions, git-ignored logs.

Route implementation to OpenCode, Antigravity, Cursor, Codex CLI or Claude Code CLI, with Claude Code or Codex as architect and judge. Committed acceptance tests and verified integration gate delivery.

Local-first kanban board where Claude Code agents work your cards — dependency chains with merge gates, an AI manager that reviews real diffs and merges green PRs, group lanes, CI-gated. One runtime dependency.

Long-running delegation architecture for Claude Code: a delegator main session + full-power orchestrator subagents — nested agents that actually delegate, skill-driven spawning, gates, crash-safe resume. Probe-proven physics + cleanroom test harness.

YYC³ AI Family·Comic Drama — 8拟人Agent×ReAct-C九步闭环驱动「小说→分镜→图像→视频→成片→运营」六阶段全链路工业化漫剧生产系统 | Mac M4 + 双DGX Spark GB10 + NAS | 90天3集样片·≤2元/集·一致性≥80%

ChatGPT, Claude, Antigravity 등 다양한 AI CLI 도구들의 협업을 오케스트레이션하는 모두의 하네스(ModueHarness)

Cost-aware AI agent orchestration for coding projects: strong models decide, cheaper models execute bounded work, and one lead owns final acceptance.

AI-powered medical education system with LangGraph ReAct agent orchestrating 4 custom tools (hybrid RAG, PubMed API, medical calculator, web search). Features research mode for multi-source evidence synthesis. Built with LangChain, Pinecone, Google Gemini. 716 PubMed articles, 222 tests.

An operating system for a 32-agent AI software org — charters, a file-based board, a gated lifecycle, and Claude Code orchestration.