Supermemory changelog

Improvements

Fixes

  • New users connecting a plugin are now taken through onboarding first.
  • Fixed chat history not loading when opening the recent conversations sheet.
  • Fixed an error that broke adding documents in the web app.
  • The settings sidebar no longer overflows its layout.
  • Removed excessive bottom padding below the input bar on the mobile dashboard.

Polish

Usage-based API billing #

API billing now follows metered usage instead of relying only on fixed quotas.

Improvements

  • The file upload endpoint now accepts customId and entityContext, matching the memory add endpoint.
  • Usage analytics now report token usage per API key for tracking against plan limits.

Fixes

  • Fixed an issue where document metadata updates didn't appear in search results.
  • Fixed an issue where chat in the web app used the default model instead of the selected one.

Amp plugin: memory that persists across agent runs #

Amp can recall memory at the start of an agent run and save useful outcomes when the run ends.

Fixes

  • Fixed the plan downgrade dialog keeping the previous confirmation text when it reopens.
  • Fixed /v3/search errors on AND queries with multiple metadata filters.
  • Fixed an issue where skipping onboarding steps failed to create an organization.

Fixes

  • Deleting an account now removes its related data cleanly.
  • MCP clients can now load OAuth discovery metadata reliably.
  • Temporary billing-service outages no longer block API requests.
  • The space selector now opens and switches spaces reliably.

Use SMFS from sandboxed agents with TypeScript and Python SDKs #

SMFS bash SDKs give TypeScript and Python agents a virtual memory-backed filesystem when they cannot mount a real folder.

Fixes

  • Fixed an issue where the Codex plugin recalled only user memories and skipped project-scoped ones.
  • Fixed an issue where the Codex plugin never saved short sessions or turns after the last prompt.