Changelog.

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

See where your credits go #

The Usage page in Supermemory Console now shows what used your credits, broken down by source, member, and namespace.

Usage page

Spend by Source shows credits used by each API key, connected app, connector, and the console.
Spend by Member and Spend by Namespace show who used credits and where.
Pick this period, a past period, or a custom range of months from one date picker.
Breakdowns start from October 8. Earlier spend shows as Before tracking.
The Usage page is available to organization admins and owners.

Supermemory API v5 is here #

The memory API built for AI agents. Simpler responses, Markdown output, and namespaces to organize your data.

Supermemory Console in dark mode, with the API v5 namespace announcement open over the dashboard, framed by a blue and green mesh background.

Migrate from v3 or v4: run npx supermemory migrate to update your integration. Your existing data stays in place.

Get started with API v5: copy the setup prompt into your coding agent.
API v5 reference: explore endpoints, parameters, and response formats.

Integration guides: Supermemory SDK · Connectors.

Supermemory for OpenCode 2 #

The Supermemory plugin now works in OpenCode 2 as well as OpenCode 1. It is the same plugin and the same install.

Company Brain is open source #

Deploy the Company Brain Slack agent yourself on Cloudflare and keep control of your data. The hosted product has been discontinued, but its harness is now available to everyone.

Explore the source on GitHub or deploy it to Cloudflare.

Read how we designed the multiplayer harness, from proactive Slack participation and memory boundaries to approvals and recovery.

Supermemory Console updates #

A new sidebar, smoother memory graphs, and fixes for Notion sync and container merges.

Two-factor authentication

Secure your account with two-factor authentication (2FA). Available on Scale and Enterprise plans.
Admins can require 2FA across the organization. Team members must enable it before they can access the organization.

Improvements

Memory Graph now loads progressively, so you can explore connections before loading finishes.
Navigate Supermemory Console with a new sidebar for Data, Developer tools, and Settings.
Remove a connector and its synced documents together, or keep the documents in Supermemory.

Fixes

Notion page property and database row edits now sync to Supermemory automatically, without a manual re-sync.
Merge containers with overlapping customIds without errors. The incoming copy gets a _merge suffix.

Memory for Meta Muse Code #

Give Meta Muse Code memory across sessions with Supermemory.

Set up Muse Code with Supermemory.

Muse Code can recall decisions from the same project in Claude Code, so you can switch agents without repeating context.

Memory for Eve #

Give your Eve agent memory across conversations with Supermemory.

Set up Eve with Supermemory.

Give agents built with Vercel's Eve framework automatic memory capture and recall, so your agent remembers past decisions and picks up where you left off.

MCP retries instead of signing you out during an auth outage #

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.

Fixes

The MCP get_document tool now reads only from your active space, matching the other read tools.
Search and graph tools now bound their page and limit inputs, and whoAmI no longer returns the transport session id.

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

Agents can discover the API spec at /openapi.json #

The OpenAPI spec is now served from the conventional root path on both the API host and supermemory.ai, so an agent or crawler can find it without knowing the versioned URL.

Fixes

Unknown routes and thrown errors now return JSON error bodies instead of plain text, matching every other API response.

Both of these serve the live spec:

https://api.supermemory.ai/openapi.json
https://supermemory.ai/openapi.json

The versioned paths still work and are unchanged:

https://api.supermemory.ai/v3/openapi
https://api.supermemory.ai/v4/openapi

Connect apps to Company Brain from one Slack card #

Asking Company Brain to connect an app now posts a single card listing each app with what it covers, a privacy note, and its own Connect button, instead of three messages saying the same thing.

Fixes

Fixed an issue where a long Company Brain answer could be posted twice in the same Slack thread, and an answer that resumes after an interruption now runs to the end instead of stopping short.