What it does
FrontierAgent is an AI agent you run in a terminal for long research and file-based tasks. In one mode, a single agent researches, reads files, writes results and runs commands inside a safe sandbox.
In "Agent Team" mode, a coordinator breaks the job into parts, hands them to helper agents running in parallel, and combines their reports. A live task board shows progress, and changes need your approval unless you turn that off.
It works with any OpenAI-compatible AI service, or with models you host yourself on a Linux computer with an NVIDIA graphics card. It also includes tools for testing how well agents perform.
Who it's for
Developers and researchers who want an open agent for long, multi-step research and file work.
Can I use it without coding?
Developers only. It's installed and configured from the command line and needs an AI service key or a self-hosted model. New to this? Start here.
Can I run it?
- Cost
- Free, but needs an AI accountThe software is free, but it uses an online AI service (like OpenAI or Anthropic), which usually charges for use.
- Runs on
- Mac, Linux
- Computer
- An ordinary computer is fine
- Privacy
- Your choice: run it on your device or use an online service
- API key
- Needed. An API key is a password-like code from an online AI service. What's that?
Try it
Using Claude Code, Cursor or another AI coding assistant? Paste the prompt and it will walk you through the setup.New to this?
Before you install
- Only download from the official GitHub page. Copies with similar names exist for many popular projects.
- License (Apache-2.0): Permissive: free to use, change and share, including for business.
- Keep your API key private. Never paste it into websites or share it, and set a spending limit with the AI service.
- More on staying safe
Where people are talking about it
- Apodex tech reportResearch paper · Aug 2026