Urgent.News

What's breaking now, across thousands of outlets.

AI

Cloud Run instances: hosting an AI agent that runs continuously

AI agents are no longer just answering a question. Some work in the background: a morning digest, the day's schedule in podcast form, nighttime alerts already sorted, Dependabot issues tracked repository by repository. Then they wait for the next task. It's very convenient. But when it comes to hosting them, a question quickly arises: where to run a program that...

Translated from French Read in French

A new type of resource, Cloud Run instances, has been tested as a hosting option for a permanent open-source agent. The agent requires continuous operation, memory retention, and simplicity. Cloud Run instances provide a container that is always on, with a fixed address and storage that survives updates and restarts, at a cost of $5.70 per month.

The test showed that the agent's memory and storage persisted through updates and restarts, and the instance can run generated code in isolated sandboxes. This option seems to meet the needs of the agent, and may be suitable for other similar use cases.

Written by urgent.news from Dev.to's report — not a translation of it. Machine-written — may contain errors; check the original before relying on it.

Read the original at dev.to →

More in AI

I Built a Personal AI That Remembers Everything I Type

What if your keyboard remembered everything — every conversation, every mood — and your AI talked back like you? I built exactly that: an Android app with a system-level AI keyboard where everything I…

  • Divyaraj Kush built an exclusive AI for personal use.
  • AI remembers all conversations typed on his phone.
  • AI can recall past conversations and moods.

NVIDIA's 64GB DGX Spark makes local AI a working-set decision

Illustrative photo by Sven Alleblas on Unsplash , free to use under the Unsplash License. This is not a product photograph.

  • NVIDIA introduces 64GB DGX Spark for local AI development
  • Configuration includes 20-core Arm CPU and 273 GB/s memory bandwidth
  • Memory usage and performance should be measured before purchase

I Built an AI System for 80+ Microservices. Six Months Later, My Whole Team Uses It.

In April I wrote about a system I built on Claude Code that takes an epic to PR-ready code across 80+ microservices. If you read that post, I sounded like someone who had finished something. I hadn't.

  • Author built AI system for 80+ microservices in April.
  • Consolidated rules into single file with short IDs to reduce drift.
  • Implemented read-only agents for safe functionality access.

Friday assorted links

1. How rich was Anglo-Saxon England? 2. New game theory paper on AI races. 3. Scott Sumner movie reviews, please note he is always correct and thus the greatest film critic in the world, at least by…

More from Friday 2 October →