Orchestrate AI coding agents (Claude, Gemini, Codex) in parallel with git worktree isolation — web UI + CLI
<div align="center"> <picture> <source media="(prefers-color-scheme: dark)" srcset="https://raw.githubusercontent.com/HyperAITeam/CLITrigger/main/src/client/public/logo.svg"> <source media="(prefers-color-scheme: light)" srcset="https://raw.githubusercontent.com/HyperAITeam/CLITrigger/main/src/client/public/logo.svg"> <img alt="CLITrigger" src="https://raw.githubusercontent.com/HyperAITeam/CLITrigger/main/src/client/public/logo.svg" width="360"> </picture> **AI-Powered Parallel Worktree Automation** *Write tasks. Let AI execute them in parallel. Review and merge.* <p align="center"> <a href="https://github.com/OSgoodYZ/CLITrigger/blob/main/README.md">한국어</a> · <a href="https://github.com/OSgoodYZ/CLITrigger/blob/main/README_EN.md">English</a> </p> [](LICENSE) [](https://www.npmjs.com/package/clitrigger) [](https://nodejs.org) [](https://www.typescriptlang.org) [](https://react.dev) </div> --- > AI가 코드를 짜는 시대, 개발자의 역할이 바뀌고 있다. > 하지만 **이해 없는 바이브 코딩**은 결국 한계에 부딪힌다. > CLITrigger는 AI를 병렬로 돌리면서도, 개발자가 맥락을 잃지 않도록 설계되었다. <div align="center"> <img src="https://raw.githubusercontent.com/HyperAITeam/CLITrigger/main/docs/images/screenshot-tasks.png" alt="Tasks — 병렬 워크트리 실행" width="800"> <p><em>병렬 워크트리에서 AI CLI가 동시에 작업을 처리하는 모습</em></p> </div> --- ## 왜 CLITrigger인가? Claude Code 제작자 Boris Cherny는 **병렬 실행(Parallelism)** 을 강조한다. 터미널 하나에서 하나씩 기다리는 건 AI 시대의 병목이다. 동시에 많은 AI 서비스는 **시간당 토큰 한도**를 가지고 있다. 낮에 한도를 다 쓰면 밤에 아무것도 못 한다. CLITrigger는 이 두 문제를 동시에 해결한다: - **지금 당장** — 여러 작업을 격리된 worktree에서 Gemini / Gemini / Codex가 병렬로 처리 - **한도 걱정 없이** — 새벽, 특정 시각에 예약 실행으로 토큰을 최대한 활용 - **더 나은 결과** — 여러 AI 에이전트가 서로 토론한 뒤 구현, 혼자 짠 코드보다 품질이 높아진다 --- ## 어떻게 동작하나? ``
Google's AI-powered research notebook that ingests your documents and becomes an expert on your content. Generates audio overviews, study guides, FAQs, and interactive discussions from uploaded sources.
Google DeepMind's experimental AI agent that can navigate websites, fill forms, and complete multi-step browser tasks autonomously. Uses Gemini's multimodal understanding to interact with web interfaces.
Google DeepMind's universal AI assistant prototype that can see, hear, and respond in real-time through your device camera and microphone. Demonstrates the future of multimodal AI interaction.
Google Cloud's enterprise platform for building, deploying, and managing AI agents powered by Gemini. Supports multi-agent orchestration, tool integration, and enterprise governance.
Gemini's agentic research capability that autonomously browses the web, synthesizes information from dozens of sources, and produces comprehensive research reports on any topic.
Interactive coding and content creation agent that generates, previews, and iterates on code, documents, and interactive applications in a side panel. Supports HTML/CSS/JS, Python, and more.