CARGO-AITools for independent computingGitHub
Open source · MIT licensed · Local-firstmacOS · Linux · Windows

Cargo-AI™

Your AI agent build tool.

Own your agents.
Create custom tools.
Share anywhere.

In Codex or Claude Code, simply say:

“Make this a Cargo-AI project, following the best practices at Cargo-AI.org.”
Watch demo

View full prompt
Make this a Cargo-AI project, following the best practices at https://cargo-ai.org.

First, read the installation and project guidance at https://cargo-ai.org/AGENTS.md.

Identify my operating system, architecture, shell, and existing project setup. Follow the appropriate installation instructions, reuse existing configuration where suitable, and apply the documented project best practices. Use the installed version's guidance and available commands. Verify the resulting setup and explain anything that still requires my input.

Why Cargo-AI

Real Inputs, Structured Results

Works with text, URL, image, and file inputs.

Use Your Existing ChatGPT Plan

Run with your Codex login, or bring your own API key or local model.

The Power to Create Your Own Tools

Create advanced Rust tools and integrate them directly with your agents.

Built on Your Machine

Run locally with your own profiles and keep control of the files, tools, and outputs.

Inspectable by Design

Keep agent behavior in JSON your team can read, diff, review, and improve.

Package Real Projects

Keep agents, custom tools, and assets together when a workflow grows beyond one file.

Choose the model path that fits your workflow.

Astra, Claude Opus, or local Ollama models like Gemma, Llama, and Mistral.

How It Fits Together

1. Define the Agent

Start with a small JSON definition for inputs, structured output, and allowed actions.

2. Run and Inspect

Run the JSON locally, inspect the result, and iterate before exporting anything.

3. Add or Create Your Own Tools

Create advanced Rust tools and make them part of the agent workflow.

4. Package and Share

Assemble agents, tools, and assets into a project that can move across machines.

Quick Start

Start with the installation and project guide for macOS, Linux, or Windows. The walkthrough below illustrates the macOS Codex path.

This setup walkthrough uses the Codex app on macOS. Cargo-AI also runs on Linux and Windows; see the GitHub documentation for other environments.

Before you start, install Rust and Cargo, Codex CLI, and the Codex app. This guide then installs Cargo-AI, connects your ChatGPT account through Codex CLI, and opens your first project in the Codex app.

First local setup

For the best authoring experience, use the Codex app. Codex CLI handles sign-in and remains available when you want a terminal workflow.

Setup commands

  1. Install Cargo-AIcargo install cargo-ai --locked
  2. Use Codex CLI as the auth bridgecodex login
  3. Add the default OpenAI profilecargo ai profile add openai-account --server openai --model gpt-5.4 --auth openai_account --default
  4. Authenticate that profilecargo ai auth login openai --profile openai-account
  5. Verify the profilecargo ai run adder_test --profile openai-account
  6. Create your first projectcargo ai new my-agent
  7. Enter the projectcd my-agent
  8. Add Codex guidancecargo ai add guidance --style codex
  9. Open the project in Codex (macOS)open -a Codex .

Start building

Now ask Codex what to build

Describe the workflow, inputs, outputs, and any files or APIs the agent should use.

Hey Codex, build me a Cargo-AI agent with any supporting Cargo-AI tools that can ...

Execution runs on your machine. This example retrieves a public sample and sends inputs to OpenAI. Codex/OpenAI sign-in is separate from a Cargo-AI account; account-backed publishing and sharing come later.

Ready for a Deeper Dive?

Use GitHub for the full developer path: README, demos, examples, install notes, tool authoring guidance, and release history.

Continue on GitHub

Explore cargo-ai on GitHub