Command Line Artificial Intelligence

Test coverage: 91.5% 😍👌

Get started

Installing:

curl -fsSL https://raw.githubusercontent.com/baalimago/clai/main/setup.sh | sh

You can also install via go:

go install github.com/baalimago/clai@latest

Then run:

clai | clai query Please give a concise explanation of clai

Either run bare clai (or clai <command> -h) or look at the examples for how to use clai. Prompt text starting with - is read as a flag, so pass it after --: clai q -- -why does this fail. If you have time, you can also check out this blogpost for a slightly more structured introduction on how to use Clai efficiently.

Install Glow for formatted markdown output when querying text responses.

Use clai as a Go library

Embed the agent loop in a Go program with github.com/baalimago/clai/pkg/agent:

// Supports strucutred output via types
// Support all things the CLI does
review, err := agent.NewTyped[Review](agent.WithModel("gpt-5.2")).Query(ctx, chat)

The agent runs silent and returns typed errors. See pkg/agent for the option surface, the command ban list and the token stoploss, and pkg/tools for the tool catalog.

Features

• Shell context injection - Inject shell context into the system prompt via configurable templates.
• Seamless conversation import - Ran out of session? Continue in clai!
• Agent Skills - Import skills from custom global directories, or project-level .agents/skills.
• Profiles - Pre-prompted profiles enabling customized workflows and agents.
• MCP client support - Add any MCP server you'd like by pasting their configuration.
• Unix-like - Clai follows the unix philosophy and works with data piped in and out.

All of these features are easily combined and tweaked, empowering users to accomplish very diverse use cases. See examples for additional info.

Supported vendors

Vendor	Environment Variable	Models
Jev	TYPESAFE_API_KEY	System One evaluation, model jev-latest, questions from -rf
OpenRouter	OPENROUTER_API_KEY	Text models, use prefix or:
Ollama	OLLAMA_API_KEY	Use format ollama: (defaults to llama3), server defaults to localhost:11434
HuggingFace	HF_API_KEY	Text models, use prefix hf:
Mistral	MISTRAL_API_KEY	Text models
OpenAI	OPENAI_API_KEY	Text models, photo models
DeepSeek	DEEPSEEK_API_KEY	Text models, key is optional, no prefix (defaults to deepseek-chat)
Berget AI	BERGET_API_KEY	Text models, use prefix berget:
Gemini	GEMINI_API_KEY	Text models, photo models
xAi	XAI_API_KEY	Text models
Inception	INCEPTION_API_KEY	Text models
Anthropic	ANTHROPIC_API_KEY	Text models

---

Shell completions are also available:

# bash
mkdir -p ~/.local/share/bash-completion/completions
clai completion bash > ~/.local/share/bash-completion/completions/clai

# zsh
mkdir -p ~/.zsh/completions
clai completion zsh > ~/.zsh/completions/_clai

For zsh, ensure your fpath includes the completions directory before compinit, for example:

fpath=(~/.zsh/completions $fpath)
autoload -Uz compinit && compinit

Then restart your shell or reload your shell configuration.