Template for AI-maintained documentation that gives agents an always up-to-date project context.
# AI-Powered Documentation Template
[](https://gemini.google.com)
[](LICENSE)
This repository is a GitHub Template for creating a project with a "living" documentation system, maintained primarily by AI agents.
The core idea is to maintain a `docs/` directory that AI agents can read to gain full context of a project, and update to reflect new changes. This solves the problem of "context drift" where AI agents lose track of the project's state over time.
## How It Works
This template provides a framework for AI agents to manage documentation. It is designed to be used with modern AI coding assistants like **GitHub Copilot**, **Gemini**, and **Gemini**.
1. **Standardized Instructions:** The template includes instruction files (`CLAUDE.md`, `.github/gemini/instructions.md`, `.cursorrules`) that point the AI agent to a central set of rules located in `docs/AGENT_INSTRUCTIONS.md`.
2. **Core Directives:** The `docs/README.md` file contains a set of rules and heuristics that tell the agent *how* to manage the documentation—when to create new files, when to update existing ones, and how to refactor them for clarity.
3. **Agent-Driven Workflow:**
* **On session start,** you instruct your AI agent to read the `docs/` directory, starting with `docs/README.md`, to get up to speed.
* **After implementing changes,** you instruct your agent to update the `docs/` directory with everything it has learned.
4. **Automation (Optional):** A skeleton GitHub Action workflow is included in `.github/workflows/docs_updater.yml`. You can adapt this to automatically run an AI agent to update the docs after every commit, creating a fully autonomous documentation system.
## Development Mode
To prevent the automated workflow from running, for instance during a work-in-progress, simply include `[DEVDOCS]` anywhere in your commit message. The woGoogle'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.