Urgent.News

What's breaking now, across thousands of outlets.

Tech

Why this "Radio"

I recently found myself copying error messages between AI agents that couldn't talk to each other becoming a human API for my own tools. Most real work today involves multiple agents from different providers, running on different machines, but they're isolated from one another. Radio closes that gap. It's a unifier, a single, provider-agnostic layer that brings agents into one shared conversation…

Radio is a new tool that unifies multiple AI agents, allowing them to communicate with each other and with users in real-time. This is particularly useful in today's work environment, where most tasks involve multiple agents from different providers running on different machines. Radio acts as a provider-agnostic layer, bringing agents together into a single shared conversation instead of isolated windows.

To use Radio, users simply need to create a channel at radio.plasma.ai, copy the link, and share it with any agents that can fetch a URL. The agents can then join the channel and talk to each other and the user in real-time. Radio supports multiple agents, including Claude Code, Codex, Cursor, OpenCode, and Grok, and works across machines and between people.

It can be used for various scenarios such as team meetings, cross-functional meetings, and external meetings, where anyone with the link can read and post to the channel.

Written by urgent.news from Dev.to's reporting — not their text. Machine-written — may contain errors; check the original before relying on it.

Read the original at dev.to →

More in Tech

Learn PostgreSQL extensions through a gloriously bad idea: MM/DD/YYYY

This project teaches four of PostgreSQL's most powerful features by building something no sane person would ship: extensions — how you add new capabilities to PostgreSQL in C, expression indexes — how…

  • Create expression index for MM/DD/YYYY dates
  • Define custom type with operators for partial date searches
  • Use GiST index for efficient month, day, year component queries

A 4 GB Laptop GPU Beats a 12-Core CPU by 4.3x on Gemma 4

This article compares two ways of serving the same small language model on the same laptop: CPU-only, and on the 4 GB GTX 1650 Ti sitting in the same chassis.

  • Laptop GPU outperforms 12-core CPU by 4.3x on Gemma 4 model
  • 3.35 GB quantization-aware GGUF model served on both CPU and GPU
  • GPU memory holds 1598 MiB of model's 3.334 GB tensor bytes

More from Wednesday 16 September →