DEDUPED Hot AI repos, turned into use cases Get the Monday 5

How to use Radiant: what you can do with it

Radiant is a free, MIT licensed local coding harness for Mac that runs chat with coding agents, a live activity feed, and a real terminal in one window.

Trended earlier

View repo on GitHub

Third-party repos we don't own. AI-written use cases can be wrong. Disclaimer

What do you want to do?

5 use cases

  • Chat with a coding agent inside your project folder

    Install Radiant on a Mac and have an agent read, edit and run commands in one project folder.

    View prompt
    Using the repo templetongroup/radiant, install the Radiant Mac app from its latest release DMG, set the workspace folder to <project folder>, and ask the agent to explain the main entry file of that project. Expected output: a chat reply that names the files it read. Verify that the Activity panel lists each file read as a tool call.

  • Code with a local model that never leaves your Mac

    Use Ollama or LM Studio on your Mac so no key is needed and no code is sent to a cloud model.

    View prompt
    Using the repo templetongroup/radiant on a Mac with a local model running in Ollama or LM Studio, start a Radiant session on the folder <project folder> and ask the model to list the top-level modules. Expected output: a list of modules from a local model with no API key set. Verify that the composer bar names the local model as the one answering.

  • Run a build loop that retries until a test command passes

    Give each step a shell check, and let failed steps retry with the reason until the check exits 0.

    View prompt
    Using the repo templetongroup/radiant, set up a loop in a Radiant session on <project folder> where each step must pass a shell test command that exits 0, and run it. Expected output: a loop report showing the rounds each step took and whether each check passed. Verify that the report lists the spend against the budget you set.

  • Run several coding jobs in parallel with a token budget

    Build a graph of jobs where only real dependencies wait, and stop a repeating graph at a token budget.

    View prompt
    Using the repo templetongroup/radiant, build a graph in a Radiant session on <project folder> with three independent jobs and run it. Expected output: a run view listing the tokens and dollar cost for each job. Verify that the independent jobs started at the same time, not one after another.

  • Review and commit only the changes you approve

    Check each file an agent changed with diffs, commit the ticked files, and undo if needed.

    View prompt
    Using the repo templetongroup/radiant, open the Changes panel for a Radiant session on <project folder>, tick the files that pass review, and commit them with a message you write. Expected output: a local commit containing only the ticked files. Verify that the unticked files still show as changed in the Changes panel.

Quick start with Radiant

  1. Check you have what it needs: A Mac. The release DMG is for Apple Silicon; Either a cloud model API key (for example Anthropic or OpenAI) or Ollama or LM Studio running on the Mac; A project folder to point the agent at.
  2. Open templetongroup/radiant on GitHub and read the README and license.
  3. Download Radiant for Mac (Apple Silicon) from https://github.com/templetongroup/radiant/releases/latest/download/radiant.dmg.
  4. Open the DMG and drag Radiant into Applications, then open it.
  5. If Ollama or LM Studio is running, a local model is picked automatically. For cloud models, open ⚙ Settings and paste an API key next to a provider.
  6. Click the path chip in the top bar and point the workspace folder at your project.

These steps come from our top use case, Chat with a coding agent inside your project folder, which also has a copy-paste agent prompt.

Use this in your AI agent

Ask your agent

Using the Deduped MCP, get the setup steps for templetongroup/radiant

Add Deduped to Claude Code once

claude mcp add --transport http deduped https://dedupedai.com/mcp

Cursor, ChatGPT, others

Radiant alternatives · Best AI repos for Software and DevOps

About this repo

  • Who it is forMac developers who want one local window to chat with coding agents, watch their tool calls, and run checked, multi-step builds.
  • Why it is hot115 stars, launched 66 days ago
  • LanguageJavaScript
  • Sourcegithub.com/templetongroup/radiant · Back to Hot repos

Requirements

  • A Mac. The release DMG is for Apple Silicon.
  • Either a cloud model API key (for example Anthropic or OpenAI) or Ollama or LM Studio running on the Mac.
  • A project folder to point the agent at.
  • npm, only if you build from source instead of using the DMG.

Add this badge to your README

Maintain Radiant? Show readers where to find these use cases. Use cases on Deduped

Markdown 

[![Use cases on Deduped](https://dedupedai.com/badge/templetongroup/radiant.svg)](https://dedupedai.com/use-cases/templetongroup-radiant/?utm_source=github&utm_medium=badge&utm_campaign=templetongroup-radiant)

HTML 

<a href="https://dedupedai.com/use-cases/templetongroup-radiant/?utm_source=github&amp;utm_medium=badge&amp;utm_campaign=templetongroup-radiant"><img src="https://dedupedai.com/badge/templetongroup/radiant.svg" alt="Use cases on Deduped" height="20"></a>

A static image, no tracking script. About the badge

Questions about Radiant

What is Radiant?

Radiant is a free, MIT licensed local coding harness for Mac that runs chat with coding agents, a live activity feed, and a real terminal in one window. It is an open-source project on GitHub: https://github.com/templetongroup/radiant.

Who is Radiant for?

Mac developers who want one local window to chat with coding agents, watch their tool calls, and run checked, multi-step builds.

What can I do with Radiant?

5 use cases so far, for example: Chat with a coding agent inside your project folder; Code with a local model that never leaves your Mac; Run a build loop that retries until a test command passes. Each has steps and a copy-paste agent prompt.

What do I need to run Radiant?

A Mac. The release DMG is for Apple Silicon; Either a cloud model API key (for example Anthropic or OpenAI) or Ollama or LM Studio running on the Mac; A project folder to point the agent at; npm, only if you build from source instead of using the DMG.

What are alternatives to Radiant?

Other hot AI repos in Software and DevOps: Codex LB Enhanced, Reuse Before Build, Aibuildai LLM Posttrain Agent, FlowX, Codex Guard.

Is Radiant safe to run?

Deduped does not own, audit or vouch for it. Read the README and license, run it on your own systems first and review every command before you run it.