Call client.search() once instead of client.search.memories() and client.search.documents(). Pass searchMode to return memories, documents, or both.
const memories = await client.search({
q: 'What did we decide about pricing?',
searchMode: 'memories',
})
const documents = await client.search({
q: 'onboarding checklist',
searchMode: 'documents',
})
const both = await client.search({
q: 'Simpler search!',
searchMode: 'hybrid',
})The Claude Code, Cursor, and OpenCode memory plugins no longer require a paid plan. Connect one with any Supermemory account — free tier included — and your agent keeps persistent memory across sessions and projects, within your plan's usage.
Scoped API keys that can add memories can now call the v4 conversations endpoint with the same container-tag and write-access protections as memory ingestion.
The self-hosted server now turns your documents into richer, more reliable memories, and uploads spend less time queued before they become searchable.
Choose the embedding model your local server uses: the built-in local model, OpenAI, any OpenAI-compatible endpoint, or Google.
Memory search now avoids long retry chains, so queries stay under 600 ms even when an upstream embedding provider slows down.
Review inferred memories from the dashboard and approve, decline, skip, or undo each suggestion before it becomes durable context.
Use the Memories API to describe what to remove, preview matches with a dry run, then send a second request to forget them.