Changelog.

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

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.

Improvements

Console now labels User Insights and team invitations as Scale or Enterprise features before setup.
Notion connector docs now explain that documentLimit applies per sync and selects the most recently edited pages first.

Fixes

User Insights now completes for larger organizations and shows its processing state immediately.
The v4 memory list endpoint now returns results from every requested container tag.
MCP connections now resume authorization after browser login instead of losing the client's request.
Nova now separates free and Pro plugins so plan requirements are clear before you connect.

RBAC for organizations: member access by container tag #

Organization owners and admins can grant members full access or restrict them to selected container tags with read or write permissions.

Improvements

User Insights reports can now be exported as PDFs.
Nova's Connect to AI flow now provides client-specific MCP setup, including a guided Claude Desktop walkthrough.

Fixes

The MCP memory graph no longer gets stuck on Loading graph data.

Polish

The MCP memory graph now has clearer relationships, hover states, zoom controls, and an expandable legend.

User Insights: reports on user segments and content patterns #

Generate Console reports about user segments, knowledge domains, and content patterns, with an optional prompt to focus the analysis.

User Insights graphic with the text your users, understood.

Improvements

Hermes is now available in Nova and Console plugin setup, with API key creation and installation steps.

Fixes

You can now forget memories from a Console profile without getting a 404 error.
Organization invite links now guide signed-out users through login, require approval, and explain account mismatches.
Usage emails no longer send the 80% warning after an organization has already reached its limit.

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

The CLI now honors --no-browser, preserves upload tags, formats document lists correctly, and marks scoped API keys.
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.

Improvements

Hermes is Nous Research's open-source agent that runs across Telegram, Discord, Slack, WhatsApp, Signal, and the CLI.
Profile-scoped and multi-container setups let each Hermes profile keep its own memory space.
The plugin accepts a custom base URL, so Hermes can use a self-hosted Supermemory server.
Memories written by Hermes appear in their own Hermes Space in the Supermemory app, alongside Codex and Claude Code.

Run the CLI with npx, delete accounts and documents #

Run the Supermemory CLI with npx supermemory, permanently delete your account and owned organizations from account settings, and delete completed or failed documents from their detail page in Console.

Improvements

You can now run the Supermemory CLI with npx supermemory.
Account settings in Console and Nova can now permanently delete your account and every organization you own.
You can now delete completed or failed documents from their detail page in Console.

Video ingestion, Notion imports, and document processing fixes #

API video ingestion no longer fails while extracting transcripts and descriptions, Notion imports explain unshared or linked databases and how to continue, and documents with large memory batches finish processing.

Fixes

API video ingestion no longer fails while extracting transcripts and descriptions.
Notion imports now explain when a page contains an unshared or linked database and tell you how to continue.
Documents that produce large memory batches now finish processing instead of failing during memory generation.
Documents no longer fail when a generated memory references another memory that was filtered out.

Nova onboarding, API search, and OpenClaw plugin fixes #

Empty Nova spaces can switch to All Spaces to find memories stored elsewhere, raw base64 images are recognized correctly during summarization, and OpenClaw recognizes Supermemory as its active memory backend.

Improvements

When a Nova space is empty, you can switch to All Spaces to find memories stored elsewhere.

Fixes

Image content sent as raw base64 is now recognized as JPEG, PNG, GIF, or WebP instead of failing during summarization.
OpenClaw 2026.3.28 now recognizes Supermemory as its active memory backend instead of showing memory as unavailable.
Nova onboarding now converts generated username separators to underscores, so names that previously produced invalid hyphens can complete setup.
Metadata filters containing null characters no longer cause search requests to fail.
Privacy Policy and Terms links on Nova and Console sign-in pages now open the correct pages.

Console improvements: API key flow and request analytics #

Console's API key flow gets a guided side panel for expiry and scope with the key shown once, and the Requests page summarizes request volume, success rate, average search latency, and request types with per-key filtering.

Improvements

Console's API key flow now uses a guided side panel for choosing expiry and scope, then shows the key once with copy and setup links.
Console's Requests page now summarizes request volume, successful calls, average search latency, and request types, and can filter activity by API key.

Fixes

The graph's All Tags button now reliably opens the container-tag filter after tags load.

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.

Improvements

During document ingestion, Supermemory can now generate up to three targeted searches to retrieve related existing memories as context.
When Gemini is unavailable in your region, Nova now explains why and offers other models to switch to.
The open-source LLM Bridge library now supports OpenAI Responses, cross-provider streaming, reasoning, and structured output.
Nova chat now shows the active space beside the model selector and in chat history.

Fixes

Documents no longer remain permanently stuck in processing after a workflow stops; Supermemory retries them once and marks a second failure clearly.
When scheduling a batch document upload fails, only the affected batch is marked failed instead of every queued document.
API and MCP quota errors now name the limit reached and explain how to continue with overage.
Truncated model output during ingestion no longer discards every generated memory when only relation data is incomplete.
Updating a document with the same custom ID no longer creates duplicate memories from facts already extracted.
Supermemory context loads correctly again in OpenCode 1.2.25 and later.
Console onboarding now advances after you choose a plugin and shows its installation steps instead of No integration selected.
Web links that return an authentication, paywall, or rate-limit response during metadata lookup no longer fail the entire import.
Search requests with an empty query or an out-of-range limit now return a clear client error instead of a server error.
Invitation links now explain when you're signed into the wrong account and let you sign out to continue with the invited email.