Skip to content
All tool news

Tool desk · Updated daily

Tool news·Vercel·

Vercel Makes Durable-Harness Resume AI Agents After Failures.

Vercel durable-harness keeps AI agent harnesses running for hours, days or months, with automatic recovery after failures.

CW

Create With tool desk

4 sources checked · 2 min read · 3 sections

ShareLinkedIn
Vercel Makes Durable-Harness Resume AI Agents After Failures

Vercel’s durable-harness lets AI agent harnesses run for hours, days or months, then automatically resume their work after failures. It supports several named coding agents and can also run a custom harness.

The launch covers Pi, OpenCode, Codex, Claude Code, eve and fx. According to the LinkedIn announcement, builders can run any of these durably on Vercel rather than treating each execution as a short-lived task.

What Vercel durable-harness can run

The launch is not tied to one agent or model provider. Vercel named six supported harnesses and included an option for teams to bring their own.

OptionHarnesses
Named supportPi, OpenCode, Codex, Claude Code, eve and fx
Custom supportYour own harness

A harness coordinates how an agent works through a task. With durable-harness, that process can continue over an extended period. If the run fails, the agent resumes its work automatically.

The duration is a central part of the update. Vercel says these agents can run for hours, days or months. That makes durable-harness suitable for work where the agent needs more than a single short execution to complete its task.

It also changes the recovery process. A failure does not end the agent’s work permanently. The harness is designed to resume it, reducing the need to restart the same run manually after an interruption.

Long-running agents on Vercel

The update gives builders two choices. They can use one of the named harnesses, including Claude Code and Codex, or deploy their own harness with the same durability behaviour.

Vercel has not described a separate workflow for each supported harness. The shared capability is durable execution: the agent keeps working over long periods and automatically returns to its task after failures.

This joins Vercel’s other late October releases, collected in What Vercel Shipped in Late October.

Frequently asked questions

What is Vercel durable-harness?

durable-harness is a Vercel capability for running AI agent harnesses over hours, days or months. Agents automatically resume their work after failures.

Which agents work with durable-harness?

Vercel named Pi, OpenCode, Codex, Claude Code, eve and fx. Builders can also run their own harness.

Which Vercel plan includes durable-harness?

The announcement does not give pricing or plan details. It also does not state whether usage limits differ between the supported harnesses.

Sources

4 checked

How we cover tool news: Create With's tool desk drafts these reports with AI from the sources listed above and checks them against those sources before publishing.

Worth passing on?

ShareLinkedIn

Go deeper on Vercel

Related reading, watching and going.

Everything on Vercel →

The briefing

19 May 2026

How to Migrate Your App from Lovable to Claude Code in 2025

Step-by-step guide to migrating your Lovable app to Claude Code. Learn how to move from Lovable's managed platform to a stack you own and control.

Read →

The briefing

10 Feb 2026

OpenClaw Review: 2 Weeks With This AI Agent

Honest 2-week review of OpenClaw — an autonomous AI agent powered by Claude. We test setup, safety, autonomy, and real value to see if it's worth using.

Read →
34 min

Podcast

My Daughter Built a Website Business, Claude Design First Look & Going All-In on Cloudflare

James and Kieran discuss practical AI-powered development through real-world examples, including a seven-year-old building a website business with Claude Code voice mode, Anthropic's new Claude Design tool, API security challenges in the AI agent era, and Cloudflare's expanding AI infrastructure offerings. The episode covers hands-on experiences with vibe coding, emerging design tools, and the evolving landscape of AI-assisted development.

Watch now ↗

Podcast

53. Why Your Vibe Code Needs Tests, Ditching SaaS & AI Agents That Work While You Sleep

James and Kieran discuss the practical realities of building AI-powered software, emphasizing the importance of testing in vibe-coded applications, exploring alternatives to traditional SaaS tools, and implementing autonomous AI agents for business operations. The episode covers technical topics like Convex databases, app store bottlenecks from AI-generated submissions, and using OpenClaw as a marketing automation agent.

Watch now ↗
38 min

Podcast

52. Your AI Co-Founder: OpenClaw, Manus & the Zero-Person Business

In this Create With podcast episode, James and Kieran are joined by Matt Roberts from Happy Operators for an in-depth discussion on using autonomous AI agents in production. The conversation covers practical experiences with OpenClaw, security considerations, comparison with emerging tools like Manus, and the broader shift toward AI-assisted development. They also discuss the VibeCoding Olympics results, Bubble's new AI capabilities, and research on Claude.MD file effectiveness.

Watch now ↗

Latest tool news

What else changed this week.

All tool news

The Create With Briefing

Don't watch forty changelogs. Read one email.

Every Tuesday: the tool changes worth knowing, real business use cases, and what's on near you. Free, unsubscribe any time.