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.

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

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.
  • 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.

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.

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.

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.

Security update for the Claude Code memory plugin#

Update the Claude Code plugin. During memory recall, a crafted Bash command could be approved automatically and run without your confirmation.

Re-run the installer to pick up the current version:

npx supermemory plugin

Build custom tools on top of Company Brain#

Use an API key from the Supermemory app to build custom tools and workflows on top of your Company Brain.

Fixes

  • The Codex plugin no longer opens browser sign-in after you explicitly log out.

Company Brain can learn new skills#

Teach Company Brain repeatable processes for triaging production failures, updating changelogs, or onboarding new employees. Admins can approve organization-wide skills in Slack and manage them from Settings.

Company Brain skills turn repeatable team processes into reusable playbooks.

Supermemory MCP Revamped#

Supermemory MCP brings clearer memory tools and interactive views to common workflows.

Inline interactive cards in Nova#

Nova shows interactive setup cards for coding agents and MCP clients directly in the conversation.

Improvements

  • Ask Nova what you can connect or how to set up a specific coding agent or MCP client.
  • Choose a setup option from an interactive card without leaving the conversation.

One memory workspace for coding agents#

Claude Code, Codex, Cursor, and OpenCode memories now come together in one Agents workspace, organized by project.

Improvements

  • Choose a project once to search its memories across supported coding agents.
  • Memories created by older Claude Code, Cursor, and OpenCode plugin versions remain available in Agents.

Claude Code, Cursor, and OpenCode plugins are now free#

The Claude Code, Cursor, and OpenCode memory plugins no longer require a paid plan. Connect one with any Supermemory account — free tier included — and your agent keeps persistent memory across sessions and projects, within your plan's usage.

Improvements

Chrome extension imports from ChatGPT, Claude, Grok, and Gemini, plus smarter memory profiles#

The Chrome extension guides imports from ChatGPT, Claude, Grok, and Gemini; long memory profiles preserve recent, frequently updated facts while summarizing older context; and shareable integration links open a specific connection ready to set up.

Nova message editing and prompt queue, Claude Code /supermemory:status, and Cursor session memory#

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.

Playground Auto-Learn, SMFS Docker quickstart, and plugin memory previews#

The console playground can save completed exchanges as memories with Auto-Learn, SMFS ships a Dockerfile and devcontainer quickstart with OpenAI and LangChain example agents, and memories saved by plugins and MCP render with rich previews.

Highlights

  • Memories saved by plugins and MCP now render with rich previews in the web app.

Improvements

Polish

Metadata filtering for ingestion, subscription cancellation in-app, and email notifications#

Scope which memories inform ingestion with filterByMetadata, cancel Pro and Scale subscriptions from billing settings, get email notifications for account and plan changes, and see connector sync status in Nova.

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.

Fixes

  • Fixed an issue where the Codex plugin recalled only user memories and skipped project-scoped ones.
  • Fixed an issue where the Codex plugin never saved short sessions or turns after the last prompt.

Console .docx import, SMFS Python tool, and search fixes#

The examples repository adds research-assistant, knowledge-base, and code-sandbox templates, Console's Import tab accepts .docx files, and the SMFS repository gains an alpha Python tool for file operations and semantic memory search.

Fixes

  • Codex capture no longer stores injected context or ingests the same fallback turn twice.

Organization reset and Console permission fixes#

Owners and admins can reset an organization while keeping members, billing, and the default project, CLI-created agents appear on Console's Agents page, and restricted members no longer see admin-only commands.

User Insights, memory list API, and MCP authorization fixes#

Console labels User Insights and team invitations as Scale or Enterprise features before setup, Notion connector docs clarify how documentLimit applies per sync, and User Insights now completes for larger organizations with visible processing state.

Fixes

  • Nova now separates free and Pro plugins so plan requirements are clear before you connect.

CLI setup command, Search API aggregation, and Console fixes#

Search API requests can set aggregate: true to combine related memory fragments into synthesized results, the CLI gets a guided setup command and interactive init, and several CLI fixes cover --no-browser, upload tags, and scoped keys.

Improvements

Fixes

  • Console now explains when a plugin requires a paid plan instead of silently redirecting to Billing.

Hermes plugin: persistent memory for Nous Research's agent#

Supermemory is now a memory provider in Hermes Agent: relevant memories load before each turn, full sessions are ingested into the memory graph when they end, and save, search, forget, and profile tools come built in. Run `hermes memory setup` and select Supermemory.

Document ingestion reliability fixes and Nova improvements#

Document ingestion can run up to three targeted searches to retrieve related memories as context, Nova explains region-unavailable models and offers alternatives, and the open-source LLM Bridge library supports OpenAI Responses and cross-provider streaming.

Fixes

  • Supermemory context loads correctly again in OpenCode 1.2.25 and later.

Memory expiration fields, plus Nova, MCP, and plugin fixes#

New v4 memories can carry an expiration time, a reason for forgetting, and document or event dates, sign-ups with unsupported email domains get a clear rejection, and usage limits account for full request size.

Fixes

  • OpenClaw no longer crashes on startup when the Supermemory store tool is registered.

Plugin sign-in approval, Console and Nova fixes#

Plugin sign-in now shows an approval page before returning an API key to the requesting app, OpenCode gains a /supermemory-logout command, OpenClaw builds memory from user messages while treating agent replies as context, and plugin sign-in works for users with multiple organizations.

Improvements

Fixes

  • Claude Code now shows actionable authentication, permission, rate-limit, and service errors instead of silently acting as if no memories exist.
  • OpenCode memory context no longer shows [object Object], [NaN%], or blank project-memory entries when fields are missing.
  • Fixed an issue where plugin sign-in failed silently for users with multiple organizations instead of letting them choose an organization and return to the connection.

Claude Code plugin: codebase indexing and Pro upgrade page#

The Claude Code plugin can explore a repository and save a reusable overview of its architecture, conventions, and key files, and free-plan connection attempts now lead to a dedicated Pro upgrade page.

Improvements

AI SDK strict mode, MCP recall, and browser extension 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.

OpenCode plugin fixes: memory deletion and context restore#

Three OpenCode plugin fixes: Forget mode deletes the selected memory correctly, context restore keeps the active agent after compaction, and JSONC configs containing URLs now load Supermemory properly.

Fixes

  • OpenCode's Forget mode now deletes the selected memory correctly.
  • OpenCode now keeps the active agent when restoring context after compaction.
  • OpenCode now loads Supermemory correctly when its JSONC configuration contains URLs.
  • OpenCode setup now disables the current Oh My OpenCode context-recovery hook instead of the obsolete hook name.
YOUR PRIVACY

Change or withdraw any time via Cookie settings in the footer. Read our cookie notice.