Supermemory SDKs changelog

Simpler search in the TypeScript SDK #

Call client.search() once instead of client.search.memories() and client.search.documents(). Pass searchMode to return memories, documents, or both.

TypeScript example calling await client.search with the query Simpler search! — One call replaces the nested memories and documents search methods.

Improvements

Pass searchMode as memories, documents, or hybrid on the same client.search() call.
Existing client.search.memories() and client.search.documents() calls keep working.

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',
})

Chrome extension imports, metadata filtering, and MCP graph fixes #

Fixes

The Python OpenAI integration now saves memories instead of returning a runtime error.

Claude Code status command, Nova chat history, and Console fixes #

Fixes

Codex plugin routes memories into project Spaces #

Codex can organize captured work into custom memory containers and keep project Spaces named from the context it sees.

Fixes

Fixed the Python OpenAI SDK injecting an empty system prompt when no memories were found.

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.

Persistent memory plugin for OpenAI Codex #

Install the Codex plugin to recall project and user memory, capture completed sessions, and explicitly search or save context.

Fixes

The AI SDK wrapper now continues without memory when retrieval fails or exceeds five seconds.

Choose which Google Drive folders and files sync #

Google Drive sync can be limited to selected folders and files instead of importing everything.

Fixes

The withSupermemory wrapper now supports models that expose metadata through getters.

Document ingestion reliability fixes and Nova improvements #

Improvements

The open-source LLM Bridge library now supports OpenAI Responses, cross-provider streaming, reasoning, and structured output.

Microsoft Agent Framework integration, Console and connector fixes #

Improvements

Microsoft Agent Framework now has a Supermemory integration for automatic recall, optional conversation storage, and explicit memory tools.

MemoryBench providers, Claude skills, and container tag filtering #

Improvements

The Supermemory repository now includes a Claude skill with setup guidance and TypeScript and Python examples for adding memory to applications.

AI SDK strict mode, MCP recall, and browser extension fixes #

Improvements

AI SDK memory tools now support strict schema validation for models that require every tool parameter.

Vercel AI SDK fix: duplicate memory fetches in multi-step turns #

Fixes

Multi-step AI SDK turns no longer fetch the same memories again after each tool call.

Console usage stats, AI SDK prompt templates, and OpenCode updates #

Improvements

The AI SDK now lets developers control how retrieved memories are formatted in model prompts.