# Changelog.

Product updates across supermemory API, MCP, plugins, SDKs, local tooling, and research.

[All ](https://supermemory.ai/changelog) [API ](https://supermemory.ai/changelog/api) [Plugins & MCP ](https://supermemory.ai/changelog/plugins) [SDKs ](https://supermemory.ai/changelog/sdk)

SDK[TypeScript ](https://supermemory.ai/changelog/sdk/typescript) [Python ](https://supermemory.ai/changelog/sdk/python) [AI SDK ](https://supermemory.ai/changelog/sdk/ai-sdk) [OpenAI ](https://supermemory.ai/changelog/sdk/openai)

[MCP](https://supermemory.ai/changelog/mcp-retries-instead-of-signing-you-out) August 24, 2026

## [MCP retries instead of signing you out during an auth outage](https://supermemory.ai/changelog/mcp-retries-instead-of-signing-you-out) [#](https://supermemory.ai/changelog/mcp-retries-instead-of-signing-you-out)

A brief authentication outage used to return invalid\_token, the protocol signal to discard your credential, so every connected MCP client was logged out. Those requests now return 503 with Retry-After so clients wait and retry.

### Improvements

* withSupermemory in @supermemory/tools now takes an apiKey option instead of only reading the environment variable, so it works with secrets managers, edge runtimes, and per-request keys.
* The ai-sdk package re-exports PromptTemplate, MemoryPromptData, and WithSupermemoryOptions, so the documented custom-template example compiles.

`withSupermemory` now takes the key directly, so it works with a secrets manager, an edge runtime, or a different key per request:

```
import { withSupermemory } from "@supermemory/tools/ai-sdk"

const model = withSupermemory(openai("gpt-5.6"), "user-123", {
  apiKey: process.env.MY_VAULT_KEY,
})
```

Requires `@supermemory/tools` 2.2.0 or later:

```
npm install @supermemory/tools@latest
```

[Codex](https://supermemory.ai/changelog/memory-for-openai-codex) April 27, 2026

## [Persistent memory plugin for OpenAI Codex](https://supermemory.ai/changelog/memory-for-openai-codex) [#](https://supermemory.ai/changelog/memory-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.

[Connectors](https://supermemory.ai/changelog/choose-what-google-drive-syncs) April 16, 2026

## [Choose which Google Drive folders and files sync](https://supermemory.ai/changelog/choose-what-google-drive-syncs) [#](https://supermemory.ai/changelog/choose-what-google-drive-syncs)

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.

[API](https://supermemory.ai/changelog/2026-01-23-improvements-and-fixes) January 23, 2026

## [AI SDK strict mode, MCP recall, and browser extension fixes](https://supermemory.ai/changelog/2026-01-23-improvements-and-fixes) [#](https://supermemory.ai/changelog/2026-01-23-improvements-and-fixes)

AI SDK memory tools support strict schema validation for models that require every parameter, MCP recall results include the memory text next to each match percentage, and pages saved by the browser extension keep their original source link.

### Improvements

* [AI SDK memory tools now support strict schema validation for models that require every tool parameter.](https://supermemory.ai/docs/integrations/ai-sdk)

### Fixes

* [Multi-step AI SDK turns no longer fetch the same memories again after each tool call.](https://supermemory.ai/docs/integrations/ai-sdk)

[Web app](https://supermemory.ai/changelog/2026-01-07-improvements-and-fixes) January 7, 2026

## [Console usage stats, AI SDK prompt templates, and OpenCode updates](https://supermemory.ai/changelog/2026-01-07-improvements-and-fixes) [#](https://supermemory.ai/changelog/2026-01-07-improvements-and-fixes)

Delete a consumer organization and its stored data from Profile settings, control how retrieved memories are formatted in AI SDK prompts, and see token and search-query usage in Console for the current and previous billing periods.

### Improvements

* [The AI SDK now lets developers control how retrieved memories are formatted in model prompts.](https://supermemory.ai/docs/integrations/ai-sdk)

## 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/)