Skip to content
Agents tracked: 492 Releases (7d): 545 Agent status: 1 with issuesSince last limit reset: Claude 9d · Codex 7d For AI agents: Markdown Updated Nov 20, 2026

Outage Report

Skyvern outage lasted 12 h 5 min, 6.2x its typical incident

Skyvern Cloud had a major incident from Nov 17, 12:22 UTC to Nov 18, 00:28 UTC, during which browser sessions and agents failed to start. It is the longest Skyvern incident in the past 12 months.

12 h 5 minSkyvern outage

What broke

Skyvern is an open-source platform that automates browser-based workflows with LLMs and computer vision. It can be self-hosted or run as the managed Skyvern Cloud. The incident, titled "Browser sessions and agents failing to start", was marked major and affected the Skyvern API, the Skyvern Cloud web application and Skyvern Async Workers. According to the official status page, it ran from Nov 17, 12:22 UTC until it was resolved on Nov 18, 00:28 UTC, a total of 12 h 5 min.

Skyvern: how long this outage lasted
Chart: AgentGid, from our tracked data.

How it compares

Skyvern's typical incident lasts 1 h 57 min, so this one ran 6.2x longer than usual. The status page lists 22 incidents over the last 12 months, and this was the longest of them. It was the only incident in the last 30 days. No other products are listed as affected by the same incident.

How it unfolded

The first update, at 12:22 UTC, said browser sessions and agent runs had been failing since 11:40 UTC and gave the cause as a database connectivity issue. At 12:50 UTC the issue was identified and a fix was being implemented; at 13:39 UTC a fix was in place and being monitored. At 13:48 UTC the status page said degraded performance was still showing in browser sessions and agent runs. The incident was closed on Nov 18 at 00:28 UTC.

What it means for you

  • If you run scheduled or customer-facing workflows on Skyvern Cloud, check runs between Nov 17, 11:40 UTC and Nov 18, 00:28 UTC and re-run the ones that failed.
  • Subscribe to Skyvern alerts on AgentGid or on the official status page.
The data behind this story
Also affected same incident
ComponentsSkyvern API; Skyvern Cloud (Web Application); Skyvern Async Workers
Duration12 h 5 min
Impactmajor
Incident titleBrowser sessions and agents failing to start
Incidents last 30 days1
Longest in 12 months12 h 5 min
ProductSkyvern
Resolved utcNov 18, 00:28 UTC
Started utcNov 17, 12:22 UTC
Status page incidents last 12 months22
Status page updatesThe issue has been identified and a fix is being implemented. / A fix has been implemented and we are monitoring the results. / We're still seeing degraded performance in browser sessions and agent runs / This incident has been resolved.
Times longer than typical6.2x
Typical incident duration1 h 57 min
What it isOpen-source platform that automates browser-based workflows with LLMs and computer vision, available as a self-hosted AGPL project with Python and TypeScript SDKs and as the managed Skyvern Cloud, which adds proxies…

Written by an AI model from these figures only, checked automatically against them and reviewed before publishing.

Share on X

Agents in this story

# Agent Gid Score Downloads 7d 7d 30d Stars Latest release
139
SkyvernSkyvern AI
34 8,843 up 6.0% up 15.5% 23.5K+12/day 1.0.585d ago

More analysis

All

Outage ReportSynthflow ElevenLabs voice incident ran 5 h 32 min, longest in 12 monthsAgentGid data · Nov 19, 2026 Outage ReportDroid's Gemini models were down for 39 h 51 min, 58.2x its typical incidentAgentGid data · Nov 19, 2026 Outage ReportFin outbound email delays lasted 21 h 20 min, 28.6x the typical incidentAgentGid data · Nov 17, 2026