Install AI coding tools

Install and sign in to a supported AI coding tool so Multica can execute tasks on your machine.

A local runtime has two parts: the Multica daemon, and one AI coding tool it can invoke. Install only the tool you intend to use — you do not need all of them.

1. Choose a tool

A tool that is already installed and signed in needs no extra setup. Tools differ in models, MCP, session resumption, and skill support; the details are in AI coding tools comparison.

Multica currently detects these commands:

Tool	Detected command	Official install guide
Antigravity CLI	`agy`	Antigravity install and sign-in
Claude Code	`claude`	Claude Code quickstart
CodeBuddy Code	`codebuddy`	CodeBuddy quickstart
Codex CLI	`codex`	Codex CLI
GitHub Copilot CLI	`copilot`	Install Copilot CLI
Cursor Agent	`cursor-agent`	Install Cursor CLI
DeepSeek Harness	`dsh`	DeepSeek Harness
DevEco Code	`deveco`	DevEco Code
Grok Build	`grok`	Grok Build quickstart
Hermes Agent	`hermes`	Hermes quickstart
Kimi CLI	`kimi`	Kimi CLI
Kiro CLI	`kiro-cli`	Install Kiro CLI
OpenClaw	`openclaw`	Install OpenClaw
OpenCode	`opencode`	OpenCode quickstart
Pi coding agent	`pi`	Pi coding agent
Oh-My-Pi	`omp`	Oh-My-Pi install
Qoder CLI	`qodercli`	Qoder CLI quickstart
Qoder CN CLI	`qoderclicn`	Qoder CN CLI quickstart
Qwen Code	`qwen`	Qwen Code
QwenPaw	`qwenpaw`	QwenPaw
Reasonix	`reasonix`	Reasonix
TRAE CLI	`traecli`	TRAE official site

"Supported" means Multica can invoke that CLI. It does not mean Multica provides the tool's account, subscription, or model quota for you.

After installing, launch the tool once in a terminal on its own and complete its sign-in or model provider setup. If the tool cannot complete requests in the terminal, the daemon's invocations fail the same way.

For Reasonix, run reasonix setup and configure a default provider and model before starting the daemon.

For QwenPaw, choose the provider and model in QwenPaw's own configuration. Multica cannot override a QwenPaw model at run time.

For DeepSeek Harness, install Node.js 20+ and run npm install -g @deepseek-ai/dsh, then add the Multica runtime profile to it (dsh plugin --profile multica add <bundle>). The daemon registers DeepSeek Harness only after dsh --profile multica --probe succeeds. Set DEEPSEEK_API_KEY (or store it in dsh's own settings) before starting the daemon.

Those login credentials are stored locally by the tool itself. Multica never receives login tokens from Claude, Codex, Cursor, or any other CLI.

Claude Code requires 2.0.0 or later, Codex 0.100.0 or later, Copilot 1.0.0 or later, Grok 0.2.89 or later, and Qwen Code 0.20.0 or later. Below the minimum version, the daemon does not register the corresponding runtime.

3. Confirm the daemon can find the command

On macOS, Linux, or WSL, run:

command -v <command>
<command> --version

In Windows PowerShell, run:

Get-Command <command>
<command> --version

Replace <command> with a command from the table, such as claude, codex, or cursor-agent. The first command prints the executable path.

If the terminal finds the tool but Desktop or the background daemon does not, the two are usually using different PATH values. Restart the app, or set an absolute path through the matching MULTICA_<PROVIDER>_PATH environment variable; full configuration is in Environment variables.

4. Re-detect and confirm the runtime is online

Start the daemon with the CLI:

multica daemon start

If the daemon is already running, restart it after installing a new tool:

multica daemon restart

With Multica Desktop, quit and reopen the app.

Then open Multica's Runtimes page. The tool appears under the target computer and shows as online. You can now select this runtime when creating or editing an agent.

The daemon must detect at least one built-in supported CLI before it will start. Custom runtime profiles sync after the daemon is up, so they cannot be the sole startup condition on a blank machine.

No tools detected

Check in order:

Run the tool itself in a terminal to confirm installation and sign-in are complete.
Check the actual command name and path with command -v or Get-Command.
Run multica daemon logs -f and look for version, path, or authentication errors.
Restart the daemon so it re-reads the current environment.
Return to the Runtimes page and confirm the computer and the tool are online.

If the tool shows as online but runs still fail, open the issue's run record to see the exact error the CLI returned, or continue with Troubleshooting.

Next steps

Create and configure an agent — select the runtime you just connected.
Daemon and runtimes — online status, concurrency, and custom runtimes.
AI coding tools comparison — compare what each tool can do in Multica.