CLI

Configure your AI coding tools to use open-source models in seconds.

Overview

The CLI configures your favorite AI coding assistants to use open-source models hosted by Cast AI. No API keys from Anthropic or OpenAI needed — just your Cast AI API key.

Supported Models

Model	Best For	Context	Output
glm-5-fp8	Reasoning, planning, analysis	160K tokens	32K tokens
kimi-k2.5	Agentic coding, image analysis	260K tokens	32K tokens
minimax-m2.5	Code generation, debugging	160K tokens	16K tokens

Quick Start

One-Line Install

bash

curl -fsSL https://github.com/getkimchi/kimchi/releases/latest/download/install.sh | bash

This downloads and installs the CLI, then launches the setup wizard automatically.

Manual Install

Download the latest release for your platform:

Platform	Architecture	Download
macOS	Intel	kimchi_darwin_amd64.tar.gz
macOS	Apple Silicon	kimchi_darwin_arm64.tar.gz
Linux	x86_64	kimchi_linux_amd64.tar.gz
Linux	ARM64	kimchi_linux_arm64.tar.gz

Download and extract:

bash

curl -fsSL https://github.com/getkimchi/kimchi/releases/latest/download/kimchi_linux_amd64.tar.gz | tar xzf -

Make executable and move to PATH:

bash

chmod +x kimchi

bash

sudo mv kimchi /usr/local/bin/

Getting Started

1. Get Your API Key

Go to Kimchi → API Keys and click Create API key. Copy the key and store it securely.

2. Run the CLI

bash

kimchi setup

The interactive wizard will guide you through:

Auth — Enter and validate your Cast AI API key
Detect Tools — Automatically finds installed AI tools
Select Tools — Choose which tools to configure
Scope — Global (all projects) or project-specific
GSD Setup — Optional: Install Goal-Driven Development agents
Configure — Writes configuration files
Done — Ready to code!

Supported Tools

Tool	Description	Config File
OpenCode	Agentic coding CLI	~/.config/opencode/opencode.json
Codex	OpenAI's coding CLI	~/.codex/.env
Zed	High-performance editor	~/.zed/settings.json
Cline	VS Code extension	~/.cline/data/globalState.json
Generic	Environment variables	Prints to stdout

Usage

Launch interactive setup:

bash

kimchi

Show version:

bash

kimchi version

Enable debug output:

bash

kimchi --debug

Generate shell completion:

bash

kimchi completion bash > /etc/bash_completion.d/kimchi

bash

kimchi completion zsh > "${fpath[1]}/_kimchi"

bash

kimchi completion fish > ~/.config/fish/completions/kimchi.fish

How It Works

The CLI configures each tool to use the inference endpoint:

text

Your AI Tool ──► CLI Config ──► Inference Endpoint ──► Open-Source Models
                                        │
                                        ▼
                               https://llm.kimchi.dev

Configuration Example (OpenCode)

json

{
  "provider": {
    "kimchi": {
      "name": "Kimchi",
      "options": {
        "baseURL": "https://llm.kimchi.dev/openai/v1",
        "apiKey": "your-api-key"
      },
      "models": {
        "glm-5-fp8": { "reasoning": true },
        "minimax-m2.5": { "reasoning": false }
      }
    }
  }
}

FAQ

Will this break my existing config?

No. The CLI preserves your existing tool configurations and only adds its provider settings.

Can I switch back?

Yes. Simply remove the kimchi provider from your tool's config file, or re-run the tool's original setup.

Where is my API key stored?

Config file: ~/.config/kimchi/config.json (permissions: 600)
Environment variable: KIMCHI_API_KEY

📘

For the latest releases and source code, visit the GitHub repository.