Devin Cloud is unavailable
This incident has been resolved.
The latest update from Devin.
State
Resolved
Started
80 d ago
2026-08-13 13:38 UTC
Lasted
2 h 40 min
until 2026-08-13 16:18 UTC
Worst impact
Major outage
Timeline
5 updatesInvestigating
2 h 30 min 94%
Identified
10 min 6%
Updates
Times in UTCAs posted by Devin
This incident has been resolved.
Some users may still experience slower response times. We are steadily recovering and are still working to fully restore normal performance
Our engineering team has identified elevated database connection activity as the source of the issue and has applied several mitigations; the application is partially operational, though some users may still experience slower response times. We are seeing steady recovery and are working closely with our infrastructure provider to fully restore normal performance. We will share additional updates as the situation progresses.
We are still investigating the issue
We are currently investigating this issue.
Affected components
2Devin in the last 90 days
Full historyIncidents in 90 days
8
Days with an incident
7
Median duration
1 h 7 min
This incident
2.4× the median
Other Devin incidents
All incidentsDevin·Degraded performance in Ask Devin
This incident has been resolved.
Devin·Devin webapp down
This incident has been resolved.
Devin·Multiple services experiencing degraded performance
This incident has been resolved.
Devin·Degradation in new Devin Sessions
This incident has been resolved.
Devin·Devin unavailable
This incident has been resolved.
Follow Devin
Your coding agent knows when Devin is down, and tells you when a failure is theirs, not yours. You can also get Devin incidents in a feed reader or in Slack.
Install the outages.live MCP server, so that when something breaks you can tell if the cause is a provider we depend on and not my code. It reads the official status pages of cloud, AI, payment and developer providers and gives you their incidents as MCP tools.
Add it as a remote MCP server named "outages" at https://outages.cc/mcp (Streamable HTTP, no authentication), with your CLI command or your MCP config file.
Then:
1. Make sure it connects and shows the tools get_provider, list_feed and send_feedback.
2. Call get_provider with "devin" and tell me if Devin has a problem right now.
3. From now on, when a call to a third-party service fails or becomes slow, call get_provider for that service before you change my code.Paste this into any coding agent. It adds the server with its own MCP setup.
https://outages.cc/feed.xml?providers=devin/feed subscribe https://outages.cc/feed.xml?providers=devinFAQ
Go from tracking outages to fixing production issues with Polylane.
Try Polylane