AI CLI Tools

AI assistant CLI tools including GPT, GitHub Copilot, and other AI-powered development utilities.

38 commands

Browse by Topic

Getting Started

Quick setup and installation

3commands

Codex CLI

OpenAI Codex terminal

5commands

Shell-GPT

GPT in terminal

8commands

Aider

AI pair programming

9commands

Copilot CLI

GitHub Copilot CLI

6commands

API

OpenAI API commands

7commands

Install OpenAI CLI

$ pip install openai

Install the OpenAI Python package and CLI via pip

Check OpenAI version

$ openai --version

Display the installed OpenAI CLI version

Install LangChain

$ pip install langchain

Install the LangChain framework for building LLM applications

Run with prompt

$ codex "create a Python script that..."

Execute Codex CLI with a natural language prompt.

Dry run mode

$ codex --dry-run "delete all .tmp files"

Preview commands without executing them.

Use specific model

$ codex --model o1-mini "explain this error"

Use a specific OpenAI model for the request.

Full auto mode

$ codex --full-auto

Enable full autonomous mode for multi-step tasks.

Set approval mode

$ codex --approval-mode suggest

Set approval mode (suggest, auto-edit, full-auto).

Ask a question

$ sgpt "What is the difference between REST and GraphQL?"

Ask Shell-GPT a general question.

Generate shell command

$ sgpt --shell "find all files larger than 100MB"

Generate a shell command from description.

Generate code

$ sgpt --code "function to validate email in Python"

Generate code with syntax highlighting.

Execute generated command

$ sgpt --shell --execute "list all running docker containers"

Generate and execute a shell command.

Use custom role

$ sgpt --role devops "how to optimize nginx config"

Use a predefined role for specialized responses.

Create custom role

$ sgpt --create-role security_expert

Create a new custom role interactively.

Start chat session

$ sgpt --chat myproject "help me debug this"

Start a named chat session for context.

Continue chat

$ sgpt --chat myproject "now add error handling"

Continue an existing chat session.

Start Aider session

$ aider

Start Aider in the current Git repository.

Aider with specific files

$ aider src/app.py src/utils.py

Start Aider with specific files in context.

Add file (in session)

$ /add filename.py

Add a file to the chat context during session.

Drop file (in session)

$ /drop filename.py

Remove a file from the chat context.

Use architect mode

$ aider --architect

Use architect mode for complex refactoring.

No auto-commits

$ aider --no-auto-commits

Disable automatic Git commits.

Use Claude model

$ aider --model claude-3-5-sonnet-20241022

Use a specific model (Claude or GPT).

Undo last change

$ /undo

Undo the last AI-made change.

Show diff

$ /diff

Show diff of pending changes.

Suggest command

$ gh copilot suggest "find large files in git history"

Get shell command suggestions from Copilot.

Explain command

$ gh copilot explain 'git rebase -i HEAD~5'

Explain what a command does.

Suggest for specific shell

$ gh copilot suggest -t shell "compress all PDFs"

Get suggestions for a specific target (shell, git, gh).

Suggest Git command

$ gh copilot suggest -t git "undo last commit"

Get Git-specific command suggestions.

Suggest GitHub CLI command

$ gh copilot suggest -t gh "create PR from current branch"

Get GitHub CLI-specific suggestions.

Configure Copilot CLI

$ gh copilot config

Configure Copilot CLI settings.

Chat completion

$ curl https://api.openai.com/v1/chat/completions -H "Authorization: Bearer $OPENAI_API_KEY" -H "Content-Type: application/json" -d '{"model":"gpt-4","messages":[{"role":"user","content":"Hello!"}]}'

Make a chat completion API request.

List models

$ curl https://api.openai.com/v1/models -H "Authorization: Bearer $OPENAI_API_KEY"

List available OpenAI models.

Create embeddings

$ curl https://api.openai.com/v1/embeddings -H "Authorization: Bearer $OPENAI_API_KEY" -H "Content-Type: application/json" -d '{"model":"text-embedding-3-small","input":"Hello world"}'

Generate text embeddings via API.

Generate image (DALL-E)

$ curl https://api.openai.com/v1/images/generations -H "Authorization: Bearer $OPENAI_API_KEY" -H "Content-Type: application/json" -d '{"model":"dall-e-3","prompt":"A cute cat","n":1,"size":"1024x1024"}'

Generate an image using DALL-E.

Stream completion

$ curl https://api.openai.com/v1/chat/completions -H "Authorization: Bearer $OPENAI_API_KEY" -H "Content-Type: application/json" -d '{"model":"gpt-4","messages":[{"role":"user","content":"Tell me a story"}],"stream":true}'

Stream chat completion response.

Check API key

$ curl https://api.openai.com/v1/models -H "Authorization: Bearer $OPENAI_API_KEY" | jq '.data[0].id'

Verify API key is valid by listing a model.

Set API key (bash)

$ export OPENAI_API_KEY='sk-...'

Set OpenAI API key as environment variable.

Discussion

Loading comments...