Documentation

Get up and running with Claudio in under a minute.

Install

Requires Node.js 20+. Works on Linux, macOS, and Windows.

$ npm install -g @claudiolabs/claudio@latest

$ bun add -g @claudiolabs/claudio@latest

$ npx @claudiolabs/claudio@latest

Quick start

Run claudio to start. On first run, the /provider wizard opens automatically — pick a preset, enter your credentials, and start coding. No config files required.

claudio

Key commands available inside the REPL:

/provider          # add, edit, or switch provider profiles
/provider doctor   # health check: reachability, auth, model availability

Providers

Switch providers without changing your workflow. Use /provider inside the REPL to configure or switch at any time.

All providers

Provider	Preset	Auth
Anthropic	`anthropic`	API key or OAuth
OpenAI	`openai`	API key
DeepSeek	`deepseek`	API key
Gemini	`gemini`	API key
Mistral	`mistral`	API key
GitHub Copilot	`github-copilot`	GitHub OAuth
Codex (ChatGPT)	`codex`	ChatGPT OAuth
Ollama	`ollama`	None — local, free
AWS Bedrock	`bedrock`	AWS credential chain
Google Vertex	`vertex`	Application Default Credentials
Azure Foundry	`foundry`	DefaultAzureCredential
OpenRouter	`openrouter`	API key
Groq	`groq`	API key
LM Studio	`lmstudio`	None — local
Any OpenAI-compatible	`custom`	Base URL + optional key

Local models (Ollama)

Run Claudio fully offline with no API key using Ollama.

# Pull a model
ollama pull qwen2.5-coder:7b

# Launch claudio with it
ollama run qwen2.5-coder:7b

Any model available on ollama.com/library works — llama3, mistral, phi4, deepseek-coder, and more.