Changelog.

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

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.

Automatic memory recall and a live statusline in Claude Code#

Supermemory now pulls relevant memories into every substantive prompt on its own, and the Claude Code status bar tells you what it did: how many memories it loaded, captured, and recalled this session, and how long ago it last saved.

Improvements

  • The status bar cycles through what Supermemory has done in this session: a running tally like 6 loaded, 6 captured, 2 recalls, then how long ago it last saved, then how long ago it last recalled. A spinner shows while a save is in flight, so you can tell the difference between working and finished.
  • The statusline configures itself the first time the plugin runs. It never overwrites a status line you already set, and if you remove it, it stays removed.
  • Memories are now searched on every substantive prompt rather than only when the model decides to look, so relevant context arrives without you asking for it.
  • Each recalled memory leads with its title, the banner shows what the injected memories cost in tokens, and anything already in context is marked instead of being injected twice.
  • Every hook call is capped at 3 seconds and fails open, so an unreachable or slow Supermemory continues your session with a visible notice instead of stalling it.
  • Automatic capture keeps decisions and lessons, skips transient repo state that git already tracks, and runs in the background instead of holding up the end of a turn.
  • The status command probes the API with your key, so a revoked key no longer looks healthy.
  • Connect to the hosted MCP server with an existing Supermemory API key instead of going through OAuth.
  • Plugin login, uninstall, and version detection now ship in the Supermemory CLI.

Fixes

  • Fixed an issue where a failed save silently skipped that turn's content instead of recapturing it on the next stop.
  • Uninstalling a plugin now returns you to the shell instead of hanging.
  • Documents that have a usable summary no longer save with the title Untitled Document.
  • Cancelling the Company Brain add-on now returns the workspace to the normal app instead of leaving it locked.
  • Returning from checkout now keeps the company domain you confirmed instead of reseeding it from your email address.

The status bar rotates through these, roughly every four seconds:

6 loaded · 6 captured · 2 recalls
saved 12s ago
recalled 3m ago

Connect 500 integrations to Company Brain from Slack or the app#

Browse the integrations marketplace in the Supermemory app, or just ask Company Brain in Slack to connect an app and it deep-links you straight to setup. Notion, Linear, Figma, Slack, HubSpot, Airtable, Vercel, and Sentry are all in there.

Configure, then Integrations in the Supermemory app.

Improvements

  • Open Configure, then Integrations in the Supermemory app to search and filter the full marketplace by category, including Productivity, Developer Tools, Sales and Marketing, Data, and Communication.
  • Ask Company Brain to connect an app from Slack and it deep-links you to that app's setup, so you can start from either Slack or the Supermemory app.
  • Apps that support it connect in one click. The rest take your own API key, and Company Brain hands back a prefilled setup link instead of failing.
  • Company Brain can now tell you whether it is able to reach a given app before you try to connect it.

Sign in with AgentID, or let your agent create its own account#

Agents can sign in to the console and web app with their own AgentID identity instead of a shared human login, and the agent's verified owner is invited as an admin to any organization it creates.

Improvements

  • Company Brain's web research now returns in about two seconds instead of forty, so Slack answers that need the web arrive much sooner.

All coding agent plugins are now free, including OpenClaw#

No Supermemory plugin sits behind a paid plan any more. Claude Code, Cursor, Codex, OpenCode, and OpenClaw are all free on any account, including the free tier.

Improvements

  • OpenClaw is now free too, so no coding agent plugin sits behind a plan gate. Usage still counts toward your plan's included credits.
  • Billing lists every plugin under Free, and the plan-specific errors on connect have been replaced with the real reason a key could not be created.

One command detects Claude Code, Cursor, OpenCode, and Codex on your machine, installs the ones you pick, and asks you to approve OAuth once in the browser:

npx supermemory plugin

Already installed and only need to reconnect:

npx supermemory plugin login

Backfill historical documents with documentDate on ingest#

Set documentDate on each document so historical content lands on the date it actually happened instead of the date you uploaded it, which is what makes time-based search work on backfilled data.

Improvements

  • A new guide walks through backfilling dated documents through the batch ingestion API, with TypeScript and Python examples.
  • Company Brain admins can now change the company domain, and re-running research updates its findings in place instead of stacking duplicates.

Fixes

  • Fixed an issue where SDK responses dropped fields the API returned, across 15 endpoints.
  • MCP now shows the API's real reason for refusing a request instead of reporting that your account may be restricted or blocked. A read-only key now says so.

Send up to 600 documents per request to POST /v3/documents/batch, sorted oldest to newest:

{
  "documents": [
    {
      "id": "msg-2019-04-02-118",
      "content": "Decided to move the billing cutover to Q3.",
      "documentDate": "2019-04-02T09:15:00Z"
    }
  ]
}

Without documentDate a backfilled document is dated the day you uploaded it, so a question like "what did we decide in 2019" will not find it.

Company Brain pricing now starts at $100 a month on Max#

Company Brain is available on the $100 a month Max plan as well as Scale, and the 14-day trial takes a card in onboarding before the brain turns on.

Improvements

  • Company Brain workspaces on Max and above no longer have a seat cap.
  • React to a Company Brain reply with the stop emoji to mute it for that Slack thread, and remove the reaction to unmute.
  • Channel automations now flag apps that are connected only to your personal account, so a digest doesn't come back empty.

Fixes

  • Fixed an issue where disconnecting Slack from Company Brain failed instead of removing the workspace.
  • Company Brain now runs for teams that bought the add-on after their trial had already lapsed.