Supported AI Agents & Environments
Environments supported by AI DevKit
AI DevKit works with a variety of AI coding assistants. This page lists all supported environments and explains what AI DevKit provides for each one.
Status Legend
| Status | Meaning |
|---|---|
| Ready | Fully supported and tested. Safe for production use. |
| Experimental | Works but may have issues. We're actively testing and improving support. |
Ready Environments
These environments are fully supported with stable integrations.
What AI DevKit provides:
AGENTS.md— Agent instructions for Cursor.cursor/commands/— Custom slash commands for the AI DevKit engineering workflow.cursor/rules/— Editor rules for consistent coding standards
What AI DevKit provides:
CLAUDE.md— Claude Code workspace instructions and context.claude/commands/— Custom slash commands
What AI DevKit provides:
.github/prompts/— GitHub Copilot custom prompts with VSCode
What AI DevKit provides:
GEMINI.md— Context file for providing instructional context to the Gemini model.gemini/commands/— Gemini custom commands
Note:
ai-devkit initandai-devkit installset up Codex project files such asAGENTS.mdand.codex/commands/. If you also want globally available Codex prompts, runai-devkit setup --globalto install them to~/.codex/prompts/.ai-devkit setup --global
What AI DevKit provides:
AGENTS.md— Codex-specific configuration and context.codex/commands/— Commands tailored for Codex's code-focused capabilities
What AI DevKit provides:
AGENTS.md— OpenCode custom instructions.opencode/commands/— OpenCode custom commands
Note: Antigravity requires global setup.
ai-devkit setup --global
What AI DevKit provides:
.agent/workflows/— Workflow for Antigravity's advanced features
Experimental Environments
These environments are under active development. They work, but you may encounter issues.
What AI DevKit provides:
AGENTS.md— Windsurf environment configuration.windsurf/commands/— Commands optimized for Windsurf's interface
What AI DevKit provides:
AGENTS.md— KiloCode configuration for large project handling.kilocode/commands/— Commands designed for large-scale development
What AI DevKit provides:
AGENTS.md— AMP configuration for accelerated workflows.agents/commands/— Commands optimized for rapid development cycles
What AI DevKit provides:
AGENTS.md— Roo Code configuration and context.roo/commands/— Commands optimized for Roo's advanced features
Environment Setup
Interactive Multi-Selection
When you run ai-devkit init, you can select multiple environments at once:
ai-devkit init
This presents an interactive checklist where you can:
- Spacebar — Select or deselect an environment
- Enter — Confirm your selections
- Select any combination of the supported environments
Configuration Storage
Your selections are saved in .ai-devkit.json:
{
"version": "0.21.1",
"environments": ["cursor", "claude", "github"],
"phases": ["requirements", "design"],
"createdAt": "2026-04-04T...",
"updatedAt": "2026-04-04T..."
}
Adding More Environments Later
Want to add another environment after initial setup? Just run:
ai-devkit init
AI DevKit will:
- Detect your existing environments
- Ask before overwriting any existing configurations
- Add new environments alongside existing ones
Override Protection
When re-running ai-devkit init, you'll see a warning before any existing files are overwritten:
Warning: The following environments are already set up: cursor, claude
Do you want to continue?
For Contributors
Want to add support for a new AI environment? We welcome contributions!
- Create Environment Definition — Add to
src/util/env.ts - Add Templates — Create
templates/env/{code}/directory - Update Documentation — Add to this guide
- Test Integration — Ensure proper initialization and configuration
See our Contributing Guide for details.
Getting Started Guides by Tool
Choose your AI tool for a tailored setup guide.