Skip to content
AI News HubLIVE
More
Summary only

Why long-running AI agents break on HTTP and how Ably is fixing it

Ably's real-time infrastructure, originally built for human collaboration, now also enables long-running AI agents. HTTP fails for agents that need persistent connections, handle interruptions, and multi-device sync. Ably introduces a 'durable session' layer and AI Transport to solve these issues, allowing developers to integrate without changing existing architecture.

SourceThe New Stack AIAuthor: Frederic Lardinois
Why long-running AI agents break on HTTP and how Ably is fixing it
Report an error

The correction channel is not available yet. You can copy the article reference below for later.

Correction instructions

Summary only

Under the source content permission, this page provides an editorial summary, key points, and a link to the original article.

Key points and analysis

Article intelligence

InvestorsAdvanced

Key points

  • Ably's real-time platform, originally for human collaboration, now suits long-running AI agents.
  • HTTP struggles with connection drops, state sync, and interruptions for multi-step reasoning agents.
  • Ably proposes 'durable sessions' covering token streaming, live objects, and offline notifications.
  • Ably's AI Transport moves only the response path to a durable session, keeping client requests on HTTP for easy integration.

Highlights and analysis are generated automatically and may contain errors. Check the original source.

More recent stories on this topic · Agents