AI Coding Assistant for Terminal

If you're researching AI Coding Assistant for Terminal, AI DevKit gives your AI coding agents one control plane for setup, console supervision, local-first memory, communication, workflow skills, and verification. AI DevKit works with a variety of AI coding agents and coding environments. This page lists supported environments and explains what AI DevKit installs for each one, so teams can keep setup, skills, memory, and verification consistent across tools.

Before selecting project environments here, complete the once-per-machine setup in Getting Started.

Support levels here describe setup and environment integration. Agent session discovery, agent console, and agent send depend on whether the local agent exposes a detectable running session. See Agent Management and Agent Console for the operational control-plane commands.

Status Legend#

Ready Environments#

These environments have stable setup integrations.

Cursor#

What AI DevKit provides:

• .cursor/skills/ — Project-level skills
• ~/.cursor/skills/ — Global skills
• .cursor/mcp.json — Project-level MCP server configuration

Claude Code#

What AI DevKit provides:

• .claude/skills/ — Project-level skills
• ~/.claude/skills/ — Global skills
• .mcp.json — Project-level MCP server configuration

GitHub Copilot#

What AI DevKit provides:

• .github/skills/ — Project-level skills
• .mcp.json — Project-level MCP server configuration
• ~/.copilot/skills/ — Global skills

Google Gemini CLI#

What AI DevKit provides:

• .gemini/skills/ — Project-level skills
• ~/.gemini/skills/ — Global skills
• .gemini/settings.json — Project-level MCP server configuration

Codex#

What AI DevKit provides:

• .agents/skills/ — Project-level skills
• ~/.codex/skills/ — Global skills
• .codex/config.toml — Project-level MCP server configuration

Grok Build CLI#

What AI DevKit provides:

• .grok/skills/ — Project-level skills
• ~/.grok/skills/ — Global skills

opencode#

What AI DevKit provides:

• .opencode/skills/ — Project-level skills
• ~/.config/opencode/skills/ — Global skills
• opencode.json — Project-level MCP server configuration under the mcp key

Antigravity#

What AI DevKit provides:

• .agent/skills/ — Project-level skills
• ~/.gemini/antigravity/skills/ — Global skills

Antigravity CLI#

What AI DevKit provides:

• .agents/skills/ — Project-level skills
• ~/.gemini/config/skills/ — Global skills

Junie#

What AI DevKit provides:

• .junie/skills/ — Project-level skills
• .junie/mcp/mcp.json — Project-level MCP server configuration
• ~/.junie/skills/ — Global skills

Cline#

What AI DevKit provides:

• .cline/skills/ — Project-level skills
• ~/.cline/skills/ — Global skills

Devin#

What AI DevKit provides:

• .devin/skills/ — Project-level skills
• .devin/config.json — Project-level MCP server configuration; AI DevKit updates only mcpServers and preserves other Devin config
• ~/.config/devin/skills/ — Global skills

Pi#

What AI DevKit provides:

• .pi/skills/ — Project-level skills
• ~/.pi/agent/skills/ — Global skills

Muse Code#

What AI DevKit provides:

• .agents/skills/ — Project-level skills
• ~/.config/muse/skills/ — Global skills

Experimental Environments#

These environments are under active development. They work, but you may encounter issues.

KiloCode#

What AI DevKit provides:

• .kilo/skills/ — Project-level skills
• ~/.kilo/skills/ — Global skills
• .kilo/kilo.jsonc — Project-level MCP server configuration under the mcp key

AMP#

What AI DevKit provides:

• .agents/skills/ — Project-level skills
• ~/.config/agents/skills/ — Global skills

Roo Code#

What AI DevKit provides:

• .roo/skills/ — Project-level skills
• ~/.roo/skills/ — Global skills
• .roo/mcp.json — Project-level MCP server configuration

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": "0.70.1",
  "environments": ["cursor", "claude", "github"],
  "phases": ["requirements", "design"],
  "createdAt": "2026-10-15T..."
}

Adding More Environments Later#

Want to add another environment after initial setup? Just run:

ai-devkit init

AI DevKit will:

1. Detect your existing environments
2. Ask once before replacing the selected environment templates in interactive mode
3. Ask separately before replacing each existing phase document

In non-interactive mode (--yes), existing environment templates and phase documents are skipped unless you also pass --overwrite. Template-driven initialization overwrites the selected artifacts without prompting.

Override Protection#

When an interactively selected environment is already set up, ai-devkit init shows a warning and asks whether to replace the selected environment templates:

Warning: The following environments are already set up: cursor, claude

The following environments are already set up and will be overwritten:
  Cursor, Claude Code

Do you want to continue?

Existing phase documents use a separate per-phase confirmation. This behavior belongs to init; the non-interactive ai-devkit install reconciliation flow does not show a general “existing install artifacts” overwrite prompt.

For Contributors#

Want to add support for a new AI environment? We welcome contributions!

1. Create Environment Definition — Add to packages/cli/src/util/env.ts
2. Add MCP Support If Needed — Add and register a generator in packages/cli/src/services/install/mcp/
3. Add Agent Detection If Needed — Add and register a harness under packages/agent-manager/src/harnesses/
4. Update Documentation — Add the environment to this guide
5. Test Integration — Verify skill paths, generated configuration, and any harness behavior

See our Contributing Guide for details.

AI Coding Assistant for Terminal with AI DevKit#

Use AI DevKit to keep AI Coding Assistant for Terminal consistent across features and teams: one config, one local console, shared memory, and the same verification workflow across supported agents.