# 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)

[SDK](https://supermemory.ai/changelog/memory-for-eve) September 19, 2026

## [Memory for Eve](https://supermemory.ai/changelog/memory-for-eve) [#](https://supermemory.ai/changelog/memory-for-eve)

Give your Eve agent memory across conversations with Supermemory.

[Set up Eve with Supermemory](https://supermemory.ai/docs/integrations/eve).

Give agents built with [Vercel's Eve framework](https://eve.dev/) automatic memory capture and recall, so your agent remembers past decisions and picks up where you left off.

[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
```

[SDK](https://supermemory.ai/changelog/simpler-search) July 20, 2026

## [Simpler search in the TypeScript SDK](https://supermemory.ai/changelog/simpler-search) [#](https://supermemory.ai/changelog/simpler-search)

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

One call replaces the nested memories and documents search methods.

### Improvements

* [Pass searchMode as memories, documents, or hybrid on the same client.search() call.](https://supermemory.ai/docs/search)
* [Existing client.search.memories() and client.search.documents() calls keep working.](https://github.com/supermemoryai/sdk-ts)

```
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',
})
```

[Web app](https://supermemory.ai/changelog/2026-06-07-nova-message-editing-claude-code-status) June 7, 2026

## [Nova message editing and prompt queue, Claude Code /supermemory:status, and Cursor session memory](https://supermemory.ai/changelog/2026-06-07-nova-message-editing-claude-code-status) [#](https://supermemory.ai/changelog/2026-06-07-nova-message-editing-claude-code-status)

Nova adds message editing, a three-prompt queue, and Instant and Thinking modes; Claude Code gains /supermemory:status for authentication, project, and API key details; Cursor loads project memory at session start and saves it when the session ends.

### Fixes

* [The Claude memory tool no longer drops the last line when reading to the end of a file.](https://supermemory.ai/docs/integrations/claude-memory)

[Research](https://supermemory.ai/changelog/2026-02-25-improvements) February 25, 2026

## [MemoryBench providers, Claude skills, and container tag filtering](https://supermemory.ai/changelog/2026-02-25-improvements) [#](https://supermemory.ai/changelog/2026-02-25-improvements)

MemoryBench gains a Claude skill for scaffolding provider adapters and running benchmarks, new filesystem-memory and hybrid-RAG providers for comparison, and the Supermemory repository gets a Claude skill with setup guidance and TypeScript and Python examples.

### Improvements

* [The Supermemory repository now includes a Claude skill with setup guidance and TypeScript and Python examples for adding memory to applications.](https://github.com/supermemoryai/supermemory)

## 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/)