radiant
by templetongroup
Radiant is a free Mac desktop app that lets you chat with AI coding agents, using either cloud models or models running on your own Mac. It shows every action the agent takes in a live feed and includes a built-in terminal, task board and tools for longer jobs.
- Stars
- 117
- Licence
- MIT
- Runs on
- Your computer
- Setup
- Moderate
- Language
- JavaScript
- Age
- 72 days
What you can do with it
- Chat with coding agents that read, edit and run commands in a project folder, switching between cloud and local models
- Queue longer jobs on a task board, or set up loops and graphs that check their own work
- Review and undo the agent's file changes, and commit selected files from a changes panel
Could replace
- Cursor
- GitHub Copilot
Our suggestion based on what it does, not a feature-by-feature comparison.
Make money with it
A freelance developer could use it to deliver client coding projects faster, taking on more fixed-price work.
An idea, not financial advice. Check the licence before charging for anything built on it.
Ways a business could use it
- Speed up building and maintaining a website or app in-house instead of paying for extra developer hours
- Use existing AI subscriptions or cheaper local models for coding work, avoiding separate paid coding tools
Can you use it commercially?
Free to use, change and sell, including in paid products. Keep the copyright notice.
Not legal advice. Read the project's licence file before building a product on it.
Getting it running
It is an Electron desktop app for macOS, and you sign in with a model subscription or paste an API key (the install steps are not shown in the README excerpt).
Follow the official instructions in the project README.
Things to check
- Mac only
- Cloud models need paid API keys or subscriptions
- Agents can run shell commands and edit files, so permission settings need care
- Computer control and subscription access are opt-in features with extra risk
- Fairly new project with modest adoption
Who's talking about it
Checked 29 Oct 2026. Summary drafted by AI from the project's README.
