Andi AIRun

Run AI prompts like programs. Executable markdown with shebang, Unix pipes, and output redirection. Extends Claude Code with cross-cloud provider switching and any-model support - free local or 100+ cloud models.

# Claude Code: any model or provider
ai                                        # Regular Claude subscription (Pro, Max)
ai --aws --opus --team --resume           # Resume chats on AWS w/ Opus 4.8 + Agent Teams

# Codex CLI: OpenAI's coding agent
ai --codex                                # Codex with gpt-5.4 (default)
ai --codex --high                         # Codex with gpt-5.4 (flagship)
ai --codex --ollama                       # Codex with local Ollama models

# Run prompts like programs (works with any runtime)
ai --azure --haiku script.md

# Script automation
cat data.json | ./analyze.md > results.txt

Quickstart

Get started in 5 minutes with your first executable AI script

Installation

Detailed installation guide for all platforms

Executable Markdown

Create markdown files that run as AI programs

Provider Switching

Switch between AWS, Azure, Vertex, Ollama, and more

Overview

Choose your runtime — Claude Code or Codex CLI — and switch between clouds + models: AWS Bedrock, Google Vertex, Azure, Vercel + Anthropic API. Supports free local models (Ollama, LM Studio) and 100+ alternate cloud models via Vercel AI Gateway or Ollama Cloud. Swap and resume conversations mid-task to avoid rate limits and keep working.

Key Features

Executable Markdown

Create markdown files with #!/usr/bin/env ai shebang for script automation. Run them directly like any executable program.

#!/usr/bin/env ai
Analyze my codebase and summarize the architecture.

Make it executable and run:

chmod +x task.md
./task.md

Unix Pipe Support

Pipe data into scripts, redirect output, chain in pipelines — standard Unix semantics for AI automation.

cat data.json | ./analyze.md > results.txt    # Pipe in, redirect out
git log -10 | ./summarize.md                  # Feed git history to AI
./generate.md | ./review.md > final.txt       # Chain scripts together

Cross-Cloud Provider Switching

Use Claude on AWS, Vertex, Azure, Anthropic API + switch mid-conversation to bypass rate limits. Also supports local models and Vercel AI Gateway.

ai --aws                          # AWS Bedrock
ai --vertex                       # Google Vertex AI
ai --ollama                       # Ollama (local, free)
ai --vercel                       # Vercel AI Gateway

Model Tiers

Simple tier selection across all providers: --fable/--best, --opus/--high, --sonnet/--mid, --haiku/--low

ai --fable task.md                # Claude Fable 5 (top tier, Anthropic only)
ai --opus task.md                 # Opus 4.8 (default)
ai --sonnet task.md               # Sonnet 5
ai --haiku task.md                # Haiku 4.5 (fastest)

Session Continuity

--resume picks up your previous chats with any model/provider. Switch providers mid-conversation when you hit rate limits.

# Hit rate limit on Claude Pro
claude
# "Rate limit exceeded. Try again in 4 hours."

# Continue immediately with AWS
ai --aws --resume

Script Variables

Declare variables with defaults in YAML front-matter. Users override them from the CLI without editing the script.

#!/usr/bin/env -S ai --haiku
---
vars:
  topic: "machine learning"
  style: casual
  length: short
---
Write a {{length}} summary of {{topic}} in a {{style}} tone.

./summarize.md                          # uses defaults
./summarize.md --topic "AI safety"      # overrides one variable

Multiple Runtimes

Choose between Claude Code (Anthropic) and Codex CLI (OpenAI). Same flags, same shebangs — AI Runner handles the mapping.

ai --cc task.md              # Claude Code
ai --codex task.md           # Codex CLI
ai --codex --high task.md    # Codex with gpt-5.4

What it Does

Multiple runtimes: Claude Code and Codex CLI with a single ai command (--cc, --codex)
Executable markdown with #!/usr/bin/env ai shebang for script automation
Unix pipe support: pipe data into scripts, redirect output, chain in pipelines
Cross-cloud provider switching: use Claude on AWS, Vertex, Azure, Anthropic API + switch mid-conversation to bypass rate limits. Also supports local models and Vercel AI Gateway
Model tiers: --opus/--high, --sonnet/--mid, --haiku/--low
Session continuity: --resume picks up your previous chats with any model/provider
Non-destructive: plain claude and codex always work untouched as before

From Andi AI Search. Star the GitHub repo if it helps!

Supported Platforms

macOS 13.0+
Linux (Ubuntu 20.04+, Debian 10+)
Windows 10+ via WSL

Providers

Provider	Flag	Type	Notes
Ollama	`--ollama` / `--ol`	Local	Free, no API costs, cloud option
LM Studio	`--lmstudio` / `--lm`	Local	MLX models (fast on Apple Silicon)
AWS Bedrock	`--aws`	Cloud	Requires AWS credentials
Google Vertex AI	`--vertex`	Cloud	Requires GCP project
Anthropic API	`--apikey`	Cloud	Direct API access
Microsoft Azure	`--azure`	Cloud	Azure Foundry
Vercel AI Gateway	`--vercel`	Cloud	Any model: OpenAI, xAI, Google, Meta, more
Claude Pro	`--pro`	Subscription	Default if logged in
Codex CLI	`--codex`	OpenAI	OpenAI API, browser auth, or config.toml profiles

Get Started

Core Concepts

Guides

Providers

Advanced

Introduction

Andi AIRun

Quickstart

Installation

Executable Markdown

Provider Switching

Overview

Key Features

What it Does

Supported Platforms

Providers

Next Steps

Get Started

Install

​Andi AIRun

Quickstart

Installation

Executable Markdown

Provider Switching

​Overview

​Key Features

​What it Does

​Supported Platforms

​Providers

​Next Steps

Get Started

Install

Andi AIRun

Overview

Key Features

What it Does

Supported Platforms

Providers

Next Steps