Urgent.News

What's breaking now, across thousands of outlets.

AI

Using claude routines with github

Intro I've been using claude for some time now. I haven't touched on routines in claude yet, and thought that this would be a good opportunity to play around with them and explore them. The official claude docs say this: Put Claude Code on autopilot. Define routines that run on a schedule, trigger on API calls, or react to GitHub events from cloud infrastructure. I thought to myself "could I get…

Claude routines allow for automated tasks using Claude Code. They can be scheduled, triggered by GitHub events, or called via API. Routines run on Anthropic's infrastructure and can respond to API requests or GitHub events. To create a routine, log into the Claude Code web interface, give it a name, add a prompt, select a repository, and choose a trigger.

Triggers include schedule (simple, run on a schedule), GitHub event (respond to GitHub events like pull requests), and API (most flexible, allows calling via POST request). Notifications can also be included. After creating the routine, it runs on Anthropic's infrastructure and can respond to events, such as updating a README file when a pull request is created.

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 AI

Google Agent Development Kit for Kotlin Reaches Feature Parity with Python, Supports On-Device AI

Google has released the Agent Development Kit (ADK) for Kotlin 1.0, a production-ready framework for building AI agents across Kotlin, Android, and JVM/server applications. It brings Kotlin to feature parity with Google's ADK for Python and Java, while adding Android-specific capabilities for on-device and hybrid AI. By Sergio De Simone

  • Google's Agent Development Kit (ADK) for Kotlin 1.0 reaches feature parity with Python.
  • Supports Android-specific functionalities for on-device and hybrid AI.
  • Introduces hierarchical multi-agent systems and context compaction features.

More from Sunday 20 September →