Previous incidents
Website is down
Resolved Jan 22, 2026 at 07:03am UTC
Website recovered.
1 previous update
API Latency Degradation
Resolved Jan 20, 2026 at 03:19pm UTC
API response times are returning to normal levels. We are continuing to monitor the system.
1 previous update
API Service and AI Models are down
Resolved Jan 10, 2026 at 11:56am UTC
AI Models recovered.
3 previous updates
Log indexing has slowed down.
Resolved Dec 21, 2025 at 07:18am UTC
Pipeline has caught up. We are still monitoring the status
1 previous update
Dashboards are intermittently loading slower
Resolved Dec 18, 2025 at 08:09pm UTC
We have mitigated the issue and now monitoring the system continuously.
1 previous update
Dashboard and API Service are down
Resolved Dec 11, 2025 at 09:44am UTC
API Service recovered.
3 previous updates
Dashboard, API Service, and 1 other service are down
Resolved Dec 10, 2025 at 02:31am UTC
AI Models recovered.
3 previous updates
Dashboard, API Service, and 1 other service are down
Resolved Dec 05, 2025 at 03:03am UTC
Quick RCA
- Bitnami latest redis version pull started failing between a few restarts. We moved the setup entirely to our own mirror.
- We have moved the setup to our own mirror to avoid this from happening in future.
4 previous updates
[Cloudflare outage] Prompt executions and log ingestions are slowed down
Resolved Nov 18, 2025 at 03:24pm UTC
Cloudflare confirmed that the issue is completely resolved. We are still keeping an eye on the system.
1 previous update
Log ingestion has slowed down
Resolved Nov 11, 2025 at 06:46am UTC
The cluster is back to normal but we are still observing pipeline for the backlog created. We are in touch with Clickhouse team to get the detailed RCA and we will publish it as soon as we recieve it.
1 previous update