We are investigating degraded performance in Claude Code on the Web sessions and related products (Cowork Remote, Routines, Claude Code Mobile)

We are investigating the issue for the listed services.

All systems and components are operating as expected, but due to a service outage for one of our model providers, agent surfaces using Anthropic Models Claude Mythos 5, Claude Fable 5, and Claude Sonnet 5 may run into issues.

We are investigating elevated errors on requests to Claude Mythos 5, Claude Fable 5, and Claude Sonnet 5. We will provide an update as soon as possible.

We are investigating an issue while creating custom RBAC roles for Enterprise users.

We are currently investigating this incident.

We are investigating a service degradation affecting Cloud Agents and Bugbot due to an ongoing GitHub outage. Users may see failures or delays when starting or running Cloud Agents and when Bugbot attempts to run.

We are investigating elevated errors on requests to multiple models. We will provide an update as soon as possible.

We are investigating degraded performance for requests that use Claude Fable. Users may see failed or retried requests in Automations, Cloud Agents, the CLI, and the IDE when Claude Fable is used. Other models are unaffected.

We are investigating degraded performance for requests that use Composer 2.5. Users may see failed or retried requests in Automations, Cloud Agents, and the IDE when Composer 2.5 is used. Other models are unaffected.

We have identified that users are experiencing elevated errors for the impacted services. We are working on implementing a mitigation.

We are investigating a service degradation affecting Automations, Cloud Agents, and IDE. Affected agent surfaces: Composer, Claude Fable 5

We are investigating the issue for the listed services.

We have identified that users are experiencing elevated errors for the impacted services. We are working on implementing a mitigation.

We have identified that users are experiencing elevated errors for the impacted services. We are working on implementing a mitigation.

We have identified that users are experiencing elevated errors for the impacted services. We are working on implementing a mitigation.

Some file downloads from our Singapore region (ap-southeast-1) failed with 500 errors during two short periods, starting at 15:14 UTC. Downloads are normal again now. The cause is not fully resolved, so short bursts of errors can return until our fix is in place. Other CDN regions are not affected. We are sorry for the disruption.

We are investigating an issue where users are unable to authenticate with MCP servers in Automations and Cloud Agents. Affected runs may fail to connect to their MCP tools.