outages.live
Live
ReplitIncident · 2026-09-17 20:40 UTC

Resolved: Degraded Agent Performance Due to Upstream Model Provider Errors

ResolvedOfficial update

We have resolved the incident related to degraded agent performance due to increase in errors from our upstream model providers.

The latest update from Replit.

State

Resolved

Started

45 d ago

2026-09-17 20:40 UTC

Lasted

52 min

until 2026-09-17 21:31 UTC

Worst impact

Partial outage

Timeline

2 updates
20:4020:5321:0521:1821:31
Partial outageUpdate postedTimes in UTC

Investigating

52 min 100%

Updates

Times in UTC

As posted by Replit

Resolved2026-09-17 21:31 UTC

We have resolved the incident related to degraded agent performance due to increase in errors from our upstream model providers.

Investigating2026-09-17 20:41 UTC

We are investigating degraded agent performance due to increase in errors from our upstream model providers.

Replit in the last 90 days

Full history
90 days agoToday

Incidents in 90 days

34

Days with an incident

46

Median duration

2 h 3 min

This incident

58% shorter than the median

How long each incident lasted, on the day it started. The outlined bar is this incident.

13 days
median 2 h 3 min
90 days agoToday

Other Replit incidents

All incidents

Replit·Agent and Workspace Issues

Replit reports a major outage that affects Agent and Workspace interactions. Replit is now monitoring the fix. Replit states that agent interactions should work again and asks users to update the browser tab.

Partial outageupdated 4 h ago

Replit·Investigating an issue related to the agent's ability to process images

We have resolved some of the earlier issues where connections to replit was disrupted.

Resolvedresolved 1 d ago

Replit·Investigating issues related to platform access

Access to Replit services has recovered.

Resolvedresolved 2 d ago

Replit·Users can't access privately deployed apps

Users are able to access their private apps again.

Resolvedresolved 9 d ago

Replit·Hubspot Connectors is not working

HubSpot connectors that use Replit’s default configuration are not working. We’ve identified the root cause and are currently working on a fix.

Resolvedresolved 9 d ago

Follow Replit

Your coding agent knows when Replit is down, and tells you when a failure is theirs, not yours. You can also get Replit incidents in a feed reader or in Slack.

Prompt
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 "replit" and tell me if Replit 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.

RSS
https://outages.cc/feed.xml?providers=replit
Slack
/feed subscribe https://outages.cc/feed.xml?providers=replit

FAQ

Go from tracking outages to fixing production issues with Polylane.

Try Polylane