Template for AI-maintained documentation that gives agents an always up-to-date project context.

AI-Powered Documentation Template

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 wo