Live / Amp / Incident
Amp: Agents fail to start for some threads
Amp · ampcode.comMajor incidentResolved2026-10-01 04:00 UTC
Public — what happened
Summary
Amp reported a major incident beginning at 03:27 UTC on October 1, 2026, in which agents in a portion of threads could not start or reconnect, though the thread data itself kept loading. The company said it suspected elevated CPU load on certain nodes during a deployment was behind the problem. By 03:49 UTC Amp said recovery was widespread, with only a small number of threads affected and agents unavailable for at most a few minutes, though some CPU readings were still higher than desired. The incident was marked resolved at 04:00.
Timeline
- Started — 2026-10-01 03:27 UTC
- Investigating — 2026-10-01 03:27 UTC
- Monitoring — 2026-10-01 03:49 UTC
- Resolved — 2026-10-01 04:00 UTC · 32 min after it started
With SquidGrid — where it starts on the route
Independent path health
The status page is the symptom. SquidGrid measures the paths that reach Amp against their own baselines — whether the routes carrying your traffic degraded, at which handoff, and who owns that stretch.
🔒 Sign in to seeCustomers get the live Provider Assessment Report for Amp: its full incident track record, what tends to break, and recent public reports of problems.
Included with any paid plan.
Open the Amp report →
More from Amp
Covered in The Squid’s Ink, Week 41, 2026, our weekly internet health report.