AI capability framework for Google Gemini and agentic workflows
# π Antigravity Config **Workspace Configuration Framework for Agentic Software Engineering** A standardized configuration framework to define architectural constraints, specialized skills, and operational workflows for AI coding agents (Gemini, Gemini, Gemini, Windsurf). <p> <a href="./readme.md">English</a> β’ <a href="./readme.es.md">EspaΓ±ol</a> β’ <a href="./readme.pt.md">PortuguΓͺs</a> </p> --- ## π― Overview This repository provides a standardized configuration structure for AI development environments. It ensures code consistency and adherence to architectural standards through three main components: ### Core Components 1. **Rules**: Global architectural constraints applied universally to all agent interactions. - *Example*: Enforcing thread-safe patterns or complexity limits. - *Location*: `rules/` 2. **Skills**: Specialized knowledge modules for specific domains. - *Concept*: Contextual information (e.g., `8-blockchain`) loaded only when relevant to the task. - *Format*: Standardized `SKILL.md` files organized by category. 3. **Workflows**: Automated procedures for multi-step tasks. - *Mechanics*: Pre-defined sequences for operations like `/deploy` or security audits. --- ## π Trilingual Support Main documentation is available in English, Spanish, and Portuguese. Technical skill instructions (`skill.md`) are maintained in English for cross-LLM precision and token efficiency. --- ## ποΈ Directory Standards This repository enforces **lowercase kebab-case** for file and directory names to ensure compatibility with CLI tools. ```text antigravity-config/ βββ install.sh # Installation script βββ docs/ # Project documentation βββ scripts/ # Internal utilities and scripts βββ template/ # Templates for new components βββ rules/ # Global architectural rules βββ skills/ # Domain knowledge (100+ Skills) βββ workflows/ # Automated operational sequences
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.