Major Outage — Services Unavailable
We have successfully brought back all the services. We’ll be doing a detailed postmortem to better understand what caused the issue so that we can prevent this in the future.
The latest update from Augment Code.
State
Resolved
Started
Lasted
5 h 36 min
Worst impact
Notice
Timeline
5 updatesInvestigating
1 h 57 min 35%
Identified
3 h 40 min 65%
Updates
Times in UTCAs posted by Augment Code
We have successfully brought back all the services. We’ll be doing a detailed postmortem to better understand what caused the issue so that we can prevent this in the future.
Cosmos and Core API services are mostly resolved. We are continuing to restore the remaining services. We'll share another update as recovery progresses.
Availability of Cosmos and our core API has improved. Some features remain affected, and we're continuing to work on restoring them. We'll share another update as recovery progresses.
We’ve identified the issue impacting service availability and are actively working with our cloud partners to resolve it. The issue is related to permissions following a recent infrastructure migration. We’ll share another update as soon as we have more information.
We are currently investigating an issue that's impacting multiple services.
Affected components
3Augment Code in the last 90 days
Full historyIncidents in 90 days
4
Days with an incident
4
Median duration
1 h 19 min
This incident
4.3× the median
Other Augment Code incidents
All incidentsAugment Code·Major outage - Cosmos & CLI unavailable
This incident has been resolved.
Augment Code·Cosmos session terminal tab doesn't render correctly for some users
We have deployed a fix to prod and confirmed that Terminal inside sessions work as expected.
Augment Code·Augment service is experiencing higher rate of 500
# Service Disruption on August 21 — What Happened On August 21, between 12:12 and 13:40 PDT, some customers experienced failed Chat and Agent requests. A routine software update exposed a dormant bug in how certain conversation histories were processed, causing roughly 12% of conversations to return errors; new conversations were largely unaffected. We rolled back the update within the hour and deployed a permanent fix the same day. Our internal review identified where our safeguards fell short, and our team is already putting in place a combination of agentic, programmatic, and human safeguards to ensure an issue like this cannot reach customers again. We're sorry for the disruption, and we thank the customers who reported the issue. Please reach out to your account contact or support if you have questions.
Follow Augment Code
Your coding agent knows when Augment Code is down, and tells you when a failure is theirs, not yours. You can also get Augment Code 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.live/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 "augment" and tell me if Augment Code 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.live/feed.xml?providers=augment/feed subscribe https://outages.live/feed.xml?providers=augmentFAQ
Go from tracking outages to fixing production issues with Polylane.
Try Polylane