# API: Faster memory search during embedding provider slowdowns

[Changelog](https://supermemory.ai/changelog) · [API](https://supermemory.ai/changelog/api)

APIJuly 7, 2026

## Faster memory search during embedding provider slowdowns[#](https://supermemory.ai/changelog/search-returns-sooner-during-provider-slowdowns)

Memory search now avoids long retry chains, so queries stay under 600 ms even when an upstream embedding provider slows down.

## Start building with supermemory.

Memory and continual learning for any model, any harness. Available through our API, plugins, and MCP.

[Build with supermemory ](https://console.supermemory.ai/)