# 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) [Console](https://supermemory.ai/changelog/2026-09-21-console-updates) September 21, 2026 ## [Supermemory Console updates](https://supermemory.ai/changelog/2026-09-21-console-updates) [#](https://supermemory.ai/changelog/2026-09-21-console-updates) A new sidebar, smoother memory graphs, and fixes for Notion sync and container merges. ### Fixes * Merge containers with overlapping customIds without errors. The incoming copy gets a \_merge suffix. [API](https://supermemory.ai/changelog/agents-can-discover-the-api-spec-at-openapi-json) August 23, 2026 ## [Agents can discover the API spec at /openapi.json](https://supermemory.ai/changelog/agents-can-discover-the-api-spec-at-openapi-json) [#](https://supermemory.ai/changelog/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 ``` [Plugins](https://supermemory.ai/changelog/automatic-memory-recall-and-a-live-statusline-in-claude-code) August 21, 2026 ## [Automatic memory recall and a live statusline in Claude Code](https://supermemory.ai/changelog/automatic-memory-recall-and-a-live-statusline-in-claude-code) [#](https://supermemory.ai/changelog/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 * Connect to the hosted MCP server with an existing Supermemory API key instead of going through OAuth. ### Fixes * Documents that have a usable summary no longer save with the title Untitled Document. The status bar rotates through these, roughly every four seconds: ``` 6 loaded · 6 captured · 2 recalls saved 12s ago recalled 3m ago ``` [API](https://supermemory.ai/changelog/backfill-historical-documents-with-their-original-date) August 14, 2026 ## [Backfill historical documents with documentDate on ingest](https://supermemory.ai/changelog/backfill-historical-documents-with-their-original-date) [#](https://supermemory.ai/changelog/backfill-historical-documents-with-their-original-date) 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. ### Fixes * Fixed an issue where SDK responses dropped fields the API returned, across 15 endpoints. 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. [Connectors](https://supermemory.ai/changelog/google-slides-sync-from-the-drive-connector) August 10, 2026 ## [Google Slides now sync and index from the Google Drive connector](https://supermemory.ai/changelog/google-slides-sync-from-the-drive-connector) [#](https://supermemory.ai/changelog/google-slides-sync-from-the-drive-connector) The Google Drive connector now indexes Google Slides presentations alongside Docs and Sheets, so slide content is searchable with the rest of your Drive. [API](https://supermemory.ai/changelog/build-custom-tools-on-top-of-company-brain) August 7, 2026 ## [Build custom tools on top of Company Brain](https://supermemory.ai/changelog/build-custom-tools-on-top-of-company-brain) [#](https://supermemory.ai/changelog/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. ### Improvements * [Open API Keys in Settings to create, copy, review, or revoke access.](https://app.supermemory.ai/?settings=api-keys) * [The forget-matching API can now delete the exact memory IDs returned by a dry run, keeping the reviewed set unchanged.](https://supermemory.ai/docs/recall/memory-operations) * The OpenAPI reference now documents how to list every container tag. ### Fixes * Large API document lists no longer fail while loading memory relations. [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) ``` 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', }) ``` [API](https://supermemory.ai/changelog/scoped-api-keys-work-with-v4-conversations) July 16, 2026 ## [Existing scoped API keys work with v4 conversations](https://supermemory.ai/changelog/scoped-api-keys-work-with-v4-conversations) [#](https://supermemory.ai/changelog/scoped-api-keys-work-with-v4-conversations) Scoped API keys that can add memories can now call the v4 conversations endpoint with the same container-tag and write-access protections as memory ingestion. ### Improvement * Scoped API keys that can add memories now work with POST /v4/conversations, so conversation ingestion can be limited to approved container tags without requiring a full-access key. * Existing scoped keys with memory-ingestion access inherit the conversations endpoint automatically because conversations follow the same access rules as add. [API](https://supermemory.ai/changelog/search-returns-sooner-during-provider-slowdowns) July 7, 2026 ## [Faster memory search during embedding provider slowdowns](https://supermemory.ai/changelog/search-returns-sooner-during-provider-slowdowns) [#](https://supermemory.ai/changelog/search-returns-sooner-during-provider-slowdowns) Memory search now avoids long retry chains, so queries stay under 600 ms even when an upstream embedding provider slows down. [Web app](https://supermemory.ai/changelog/review-suggested-memories-before-saving-them) July 4, 2026 ## [Review suggested memories before saving them](https://supermemory.ai/changelog/review-suggested-memories-before-saving-them) [#](https://supermemory.ai/changelog/review-suggested-memories-before-saving-them) Review inferred memories from the dashboard and approve, decline, skip, or undo each suggestion before it becomes durable context. [API](https://supermemory.ai/changelog/2026-07-03-dreaming-retries-mcp-reconnect) July 3, 2026 ## [Dreaming batch retries, MCP client reconnection fix, and the Cursor install guide](https://supermemory.ai/changelog/2026-07-03-dreaming-retries-mcp-reconnect) [#](https://supermemory.ai/changelog/2026-07-03-dreaming-retries-mcp-reconnect) Stalled or failed Dreaming batches now retry without blocking newer batches in the same container, reconnecting an approved MCP client reuses its API key, and the Cursor installation guide uses the published integration package. ### Highlights * Stalled or failed Dreaming batches now retry without blocking newer batches in the same container. * Reconnecting an approved MCP client no longer creates a new API key each time. ### Fixes * Fixed an issue where frequently updated facts were missing from memory profiles. * Large Dreaming queues no longer fail during background memory generation. [API](https://supermemory.ai/changelog/tell-supermemory-what-to-forget) June 29, 2026 ## [Forget memories by description with the Memories API](https://supermemory.ai/changelog/tell-supermemory-what-to-forget) [#](https://supermemory.ai/changelog/tell-supermemory-what-to-forget) Use the Memories API to describe what to remove, preview matches with a dry run, then send a second request to forget them. [API](https://supermemory.ai/changelog/search-memory-by-time) June 25, 2026 ## [Search memories by time using natural date phrases](https://supermemory.ai/changelog/search-memory-by-time) [#](https://supermemory.ai/changelog/search-memory-by-time) Search now understands phrases like last week, in March, and between two dates, along with common numeric date formats. Search with natural date phrases instead of setting a date range by hand. [Web app](https://supermemory.ai/changelog/2026-06-24-chrome-extension-imports-memory-profiles) June 24, 2026 ## [Chrome extension imports from ChatGPT, Claude, Grok, and Gemini, plus smarter memory profiles](https://supermemory.ai/changelog/2026-06-24-chrome-extension-imports-memory-profiles) [#](https://supermemory.ai/changelog/2026-06-24-chrome-extension-imports-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. ### Highlights * [Long memory profiles now preserve recent, frequently updated facts while summarizing older context.](https://supermemory.ai/docs/user-profiles) ### Fixes * [Documents and memories with numeric metadata now index correctly and remain filterable by number.](https://supermemory.ai/docs/concepts/filtering) * One malformed generated memory no longer fails an entire extraction batch. * Large PDFs no longer fail to process when text extraction takes longer than usual. * Cloud connections now load and connect correctly through the API. [CLI](https://supermemory.ai/changelog/one-command-installs-memory-in-coding-agents) June 20, 2026 ## [Install memory in Claude Code, Cursor, OpenCode, and Codex](https://supermemory.ai/changelog/one-command-installs-memory-in-coding-agents) [#](https://supermemory.ai/changelog/one-command-installs-memory-in-coding-agents) The Supermemory CLI can set up memory for Claude Code, Cursor, OpenCode, and Codex from one command. The dry run previews agent changes before writing plugin files. ### Improvements * [Container tags now keep an up-to-date description of the memories they contain.](https://supermemory.ai/docs/concepts/container-tags) [Web app](https://supermemory.ai/changelog/your-weekly-memory-digest) June 18, 2026 ## [Weekly memory digest emails and history in Nova](https://supermemory.ai/changelog/your-weekly-memory-digest) [#](https://supermemory.ai/changelog/your-weekly-memory-digest) Eligible Nova users receive a Monday recap after weeks with at least three new documents, with digest history and email controls in the web app. ### Fixes * [The Memories API now returns custom metadata, and metadata filters work on those values.](https://supermemory.ai/docs/concepts/filtering) * File uploads with invalid metadata now return a validation error instead of a server error. [MCP](https://supermemory.ai/changelog/approve-mcp-connections-before-they-use-memory) June 16, 2026 ## [Approve MCP connections before they access memory](https://supermemory.ai/changelog/approve-mcp-connections-before-they-use-memory) [#](https://supermemory.ai/changelog/approve-mcp-connections-before-they-use-memory) Review each MCP client's requested permissions and approve or deny access before it can read or write memory. ### Improvements * Connector sync history now shows which items failed and why. [Web app](https://supermemory.ai/changelog/2026-06-15-multi-link-memories-apple-shortcuts) June 15, 2026 ## [Multi-link Add Memory, Apple Shortcuts setup, and organization deletion](https://supermemory.ai/changelog/2026-06-15-multi-link-memories-apple-shortcuts) [#](https://supermemory.ai/changelog/2026-06-15-multi-link-memories-apple-shortcuts) Paste multiple links into Add Memory to create a separate memory per URL, set up Apple Shortcuts from a single dialog, browse Integrations before signing in, and delete an organization from the Settings danger zone. ### Improvements * [The API docs now include a guide to organizing and isolating memory with container tags.](https://supermemory.ai/docs/concepts/container-tags) ### Fixes * Rate-limited API requests now return HTTP 429 with Retry-After so clients know when to retry. [Local](https://supermemory.ai/changelog/run-supermemory-locally) June 10, 2026 ## [Run Supermemory locally: self-hosted server for macOS and Linux](https://supermemory.ai/changelog/run-supermemory-locally) [#](https://supermemory.ai/changelog/run-supermemory-locally) Install the self-hosted server from a published macOS or Linux binary with local authentication and encrypted embedded storage. ### Fixes * The Conversations API now appends turns without replacing, dropping, or duplicating earlier messages. [Web app](https://supermemory.ai/changelog/attach-files-to-nova-chats) June 8, 2026 ## [Attach files to Nova chats and choose what becomes memory](https://supermemory.ai/changelog/attach-files-to-nova-chats) [#](https://supermemory.ai/changelog/attach-files-to-nova-chats) Nova keeps attached files with the thread and lets you choose whether each file becomes memory. ### Improvements * Files, links, and notes added from Console now begin memory extraction immediately. [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 * Playground can now save memory guidance for a new container before it has memories. [Console](https://supermemory.ai/changelog/request-a-data-export-from-settings) June 4, 2026 ## [Export your documents and memories from Settings](https://supermemory.ai/changelog/request-a-data-export-from-settings) [#](https://supermemory.ai/changelog/request-a-data-export-from-settings) Request a JSON export of up to 25,000 documents and memories. Organization exports require owner or admin access, and download links expire after six hours. ### Improvements * [Gmail imports now preserve labels as searchable document metadata.](https://supermemory.ai/docs/connectors/gmail) [Console](https://supermemory.ai/changelog/manage-usage-and-credits-in-settings) May 30, 2026 ## [Manage usage, credits, and billing from settings](https://supermemory.ai/changelog/manage-usage-and-credits-in-settings) [#](https://supermemory.ai/changelog/manage-usage-and-credits-in-settings) Teams can buy more Supermemory usage and manage billing from settings instead of starting a support loop. ### Fixes * Forgotten memories no longer appear in homepage suggestions. [Web app](https://supermemory.ai/changelog/2026-05-28-improvements-fixes-and-polish) May 28, 2026 ## [Console billing status, chat space default, and MCP key fix](https://supermemory.ai/changelog/2026-05-28-improvements-fixes-and-polish) [#](https://supermemory.ai/changelog/2026-05-28-improvements-fixes-and-polish) The console billing page shows when a cancelled plan's access ends, organization names can be updated from web app settings, the chat input space selector defaults to Auto, and MCP clients reuse their active API key on reconnect. ### Fixes * Fixed an issue where MCP connections created a new API key on every request instead of reusing one. [Web app](https://supermemory.ai/changelog/connect-apps-from-one-integrations-page) May 27, 2026 ## [Connect apps, plugins, and knowledge bases from one integrations page](https://supermemory.ai/changelog/connect-apps-from-one-integrations-page) [#](https://supermemory.ai/changelog/connect-apps-from-one-integrations-page) The integrations catalog brings setup cards, categories, connection state, and deep links into one place. ### Fixes * Fixed an issue where deleting a large organization could fail. * [Fixed an issue where filtering /v3/search by a customId docId returned no results.](https://supermemory.ai/docs/search) [Plugins](https://supermemory.ai/changelog/codex-routes-memory-into-project-spaces) May 26, 2026 ## [Codex plugin routes memories into project Spaces](https://supermemory.ai/changelog/codex-routes-memory-into-project-spaces) [#](https://supermemory.ai/changelog/codex-routes-memory-into-project-spaces) Codex can organize captured work into custom memory containers and keep project Spaces named from the context it sees. ### Improvements * Memories now show a temporary title while they are still being processed. ### Fixes * Fixed conversations ingested from plugins being attributed to the API instead of their actual source. [Web app](https://supermemory.ai/changelog/nova-works-like-a-mobile-app) May 25, 2026 ## [Nova mobile redesign: bottom navigation and app-like layout](https://supermemory.ai/changelog/nova-works-like-a-mobile-app) [#](https://supermemory.ai/changelog/nova-works-like-a-mobile-app) Nova now behaves like a mobile-first app instead of a desktop layout squeezed onto a phone. ### Improvements * Team invites with restricted access now require the Scale plan, with an upgrade option shown on Pro. [Web app](https://supermemory.ai/changelog/2026-05-24-memory-generation-settings-redesign) May 24, 2026 ## [Smarter memory generation with timestamps, settings redesign, and Drive PDF previews](https://supermemory.ai/changelog/2026-05-24-memory-generation-settings-redesign) [#](https://supermemory.ai/changelog/2026-05-24-memory-generation-settings-redesign) Memory generation now uses timestamps and recent history so new information connects to related memories more accurately, the settings page is redesigned with billing in its own tab, and Google Drive PDFs preview inline in the document viewer. ### Highlights * Memory generation now uses timestamps and recent history, so new information connects to related memories more accurately. * [Google Drive PDFs now preview inline instead of failing to load in the document viewer.](https://supermemory.ai/docs/connectors/google-drive) ### Fixes * Fixed an issue where Memory of the Day could link to a deleted document and open a blank page. * Document processing now completes even when memory generation fails for part of a batch. [Web app](https://supermemory.ai/changelog/2026-05-19-playground-auto-learn-smfs-quickstart) May 19, 2026 ## [Playground Auto-Learn, SMFS Docker quickstart, and plugin memory previews](https://supermemory.ai/changelog/2026-05-19-playground-auto-learn-smfs-quickstart) [#](https://supermemory.ai/changelog/2026-05-19-playground-auto-learn-smfs-quickstart) 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. ### Fixes * Fixed an issue where Pro plan users were asked to upgrade before inviting their included teammates. * Fixed the memory of the day card opening the list view instead of its source document. * Large connector syncs now import documents up to your quota instead of failing the whole batch. * Fixed an issue where email-change confirmation emails sometimes never arrived. ### Polish * [You can now create container tags inline from the console playground composer.](https://supermemory.ai/docs/concepts/container-tags) [Web app](https://supermemory.ai/changelog/2026-05-14-metadata-filtering-subscription-cancellation) May 14, 2026 ## [Metadata filtering for ingestion, subscription cancellation in-app, and email notifications](https://supermemory.ai/changelog/2026-05-14-metadata-filtering-subscription-cancellation) [#](https://supermemory.ai/changelog/2026-05-14-metadata-filtering-subscription-cancellation) 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. ### Highlights * [Added a filterByMetadata option to scope which memories are used as context during ingestion.](https://supermemory.ai/docs/concepts/filtering) [Console](https://supermemory.ai/changelog/upload-markdown-files-in-console) May 9, 2026 ## [Upload Markdown files in the Console](https://supermemory.ai/changelog/upload-markdown-files-in-console) [#](https://supermemory.ai/changelog/upload-markdown-files-in-console) Console document uploads now accept Markdown files. ### Improvements * [File URLs returned by the API are now signed and expire after 24 hours, so leaked links stop working.](https://supermemory.ai/docs/document-operations) [API](https://supermemory.ai/changelog/usage-based-api-billing) May 8, 2026 ## [Usage-based API billing](https://supermemory.ai/changelog/usage-based-api-billing) [#](https://supermemory.ai/changelog/usage-based-api-billing) API billing now follows metered usage instead of relying only on fixed quotas. ### Improvements * The file upload endpoint now accepts customId and entityContext, matching the memory add endpoint. * Usage analytics now report token usage per API key for tracking against plan limits. ### Fixes * Fixed an issue where document metadata updates didn't appear in search results. [Plugins](https://supermemory.ai/changelog/supermemory-for-amp) May 7, 2026 ## [Amp plugin: memory that persists across agent runs](https://supermemory.ai/changelog/supermemory-for-amp) [#](https://supermemory.ai/changelog/supermemory-for-amp) Amp can recall memory at the start of an agent run and save useful outcomes when the run ends. ### Fixes * Fixed /v3/search errors on AND queries with multiple metadata filters. [Web app](https://supermemory.ai/changelog/2026-05-06-nova-redesign-week) May 6, 2026 ## [Nova redesign: new dashboard, timeline view, and connection management](https://supermemory.ai/changelog/2026-05-06-nova-redesign-week) [#](https://supermemory.ai/changelog/2026-05-06-nova-redesign-week) Nova gets a redesigned home dashboard, timeline view, refreshed onboarding, and expanded settings; connections move into the Add Memory modal; plus fixes for account deletion, MCP OAuth discovery, billing resilience, and the console. ### Highlights * MCP clients can now load OAuth discovery metadata reliably. ### Fixes * Deleting an account now removes its related data cleanly. * Temporary billing-service outages no longer block API requests. * [Fixed document list requests failing for very large documents; list responses now return a content preview.](https://supermemory.ai/docs/document-operations) [Local](https://supermemory.ai/changelog/mount-memory-as-a-folder-with-smfs) April 30, 2026 ## [Mount memory as a local folder with SMFS](https://supermemory.ai/changelog/mount-memory-as-a-folder-with-smfs) [#](https://supermemory.ai/changelog/mount-memory-as-a-folder-with-smfs) SMFS mounts a Supermemory container as a local folder that shells, editors, and agents can use through ordinary file operations. SMFS turns a Supermemory container into a folder tools already understand. ### Fixes * Fixed PATCH document updates returning a 409 conflict against the document's own filepath. [Console](https://supermemory.ai/changelog/2026-04-28-improvements-and-fixes) April 28, 2026 ## [Console .docx import, SMFS Python tool, and search fixes](https://supermemory.ai/changelog/2026-04-28-improvements-and-fixes) [#](https://supermemory.ai/changelog/2026-04-28-improvements-and-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. ### Improvements * [The examples repository now includes templates for a research assistant, knowledge base, and code sandbox.](https://github.com/supermemoryai/examples) ### Fixes * v4 search now reranks results when requested instead of silently returning the original order. [Codex](https://supermemory.ai/changelog/memory-for-openai-codex) April 27, 2026 ## [Persistent memory plugin for OpenAI Codex](https://supermemory.ai/changelog/memory-for-openai-codex) [#](https://supermemory.ai/changelog/memory-for-openai-codex) Install the Codex plugin to recall project and user memory, capture completed sessions, and explicitly search or save context. ### Improvements * OAuth clients can now discover Supermemory through /.well-known/openid-configuration. [MCP](https://supermemory.ai/changelog/2026-04-21-fixes-and-polish) April 21, 2026 ## [Connector sync cleanup, MCP project list refresh, and email polish](https://supermemory.ai/changelog/2026-04-21-fixes-and-polish) [#](https://supermemory.ai/changelog/2026-04-21-fixes-and-polish) Deleting an organization or account stops connector syncs and fully disconnects connections, MCP project lists refresh after a new project is used, and transactional emails use shorter layouts with plain links and one-time codes. ### Fixes * Deleting an organization or account now stops connector syncs and fully disconnects connections. [Connectors](https://supermemory.ai/changelog/choose-what-google-drive-syncs) April 16, 2026 ## [Choose which Google Drive folders and files sync](https://supermemory.ai/changelog/choose-what-google-drive-syncs) [#](https://supermemory.ai/changelog/choose-what-google-drive-syncs) Google Drive sync can be limited to selected folders and files instead of importing everything. ### Improvements * [Set taskType: superrag when adding a document to index it for retrieval without generating memories.](https://supermemory.ai/docs/add-memories) ### Fixes * MCP connections no longer fail while creating the API key used for a session. [API](https://supermemory.ai/changelog/2026-04-15-fixes) April 15, 2026 ## [Usage metering and Console onboarding fixes](https://supermemory.ai/changelog/2026-04-15-fixes) [#](https://supermemory.ai/changelog/2026-04-15-fixes) Organizations with overages off now stop at their included allowance, organization creation during onboarding reliably activates and continues, and document updates count only newly added content. ### Fixes * Organizations with overages off now stop at their included allowance instead of recording billable usage. * Updating a document now counts only newly added content instead of re-counting unchanged text. [Console](https://supermemory.ai/changelog/test-memory-search-in-console) April 14, 2026 ## [Test and tune memory search in the Console](https://supermemory.ai/changelog/test-memory-search-in-console) [#](https://supermemory.ai/changelog/test-memory-search-in-console) Run v3 or v4 searches, tune retrieval settings, and inspect scored results, timing, or raw JSON before integrating the API. ### Improvements * Markdown documents now keep headings, tables, and fenced code together when split for indexing. ### Fixes * New API keys now appear immediately in Console, and deleted scoped keys are removed completely. * Document processing now recovers from blocked generated output instead of failing memory generation. ### Polish * API key previews now preserve the recognizable prefix and use a consistent masked length. [Console](https://supermemory.ai/changelog/2026-04-13-improvements-and-fixes) April 13, 2026 ## [Console organization limits, memory graph, and connector fixes](https://supermemory.ai/changelog/2026-04-13-improvements-and-fixes) [#](https://supermemory.ai/changelog/2026-04-13-improvements-and-fixes) Console stops organization creation at the three-organization limit with guidance on requesting more, free organizations lose overage access after a paid plan is canceled, and the memory graph is readable in light and dark mode. ### Fixes * Free organizations no longer keep overage access after a paid plan is canceled. * The API now rejects connector documents without an access token instead of ingesting their URL as text. [Console](https://supermemory.ai/changelog/2026-04-10-improvements-and-fixes) April 10, 2026 ## [Organization reset and Console permission fixes](https://supermemory.ai/changelog/2026-04-10-improvements-and-fixes) [#](https://supermemory.ai/changelog/2026-04-10-improvements-and-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. ### Improvements * Owners and admins can reset an organization, clearing its data and connections while keeping members, billing, and the default project. ### Fixes * Starting User Insights twice no longer creates competing runs or clears the active report. [Console](https://supermemory.ai/changelog/2026-04-09-improvements-and-fixes) April 9, 2026 ## [User Insights, memory list API, and MCP authorization fixes](https://supermemory.ai/changelog/2026-04-09-improvements-and-fixes) [#](https://supermemory.ai/changelog/2026-04-09-improvements-and-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 * [Notion connector docs now explain that documentLimit applies per sync and selects the most recently edited pages first.](https://supermemory.ai/docs/connectors/notion) ### 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. [Console](https://supermemory.ai/changelog/understand-your-users-with-user-insights) April 7, 2026 ## [User Insights: reports on user segments and content patterns](https://supermemory.ai/changelog/understand-your-users-with-user-insights) [#](https://supermemory.ai/changelog/understand-your-users-with-user-insights) Generate Console reports about user segments, knowledge domains, and content patterns, with an optional prompt to focus the analysis. ### Fixes * You can now forget memories from a Console profile without getting a 404 error. * Usage emails no longer send the 80% warning after an organization has already reached its limit. [CLI](https://supermemory.ai/changelog/2026-04-06-improvements-and-fixes) April 6, 2026 ## [CLI setup command, Search API aggregation, and Console fixes](https://supermemory.ai/changelog/2026-04-06-improvements-and-fixes) [#](https://supermemory.ai/changelog/2026-04-06-improvements-and-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 * [Set aggregate: true in Search API requests to combine related memory fragments into synthesized results.](https://supermemory.ai/docs/search) [API](https://supermemory.ai/changelog/2026-04-02-fixes) April 2, 2026 ## [Video ingestion, Notion imports, and document processing fixes](https://supermemory.ai/changelog/2026-04-02-fixes) [#](https://supermemory.ai/changelog/2026-04-02-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. * 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. [Web app](https://supermemory.ai/changelog/2026-03-31-improvements-and-fixes) March 31, 2026 ## [Nova onboarding, API search, and OpenClaw plugin fixes](https://supermemory.ai/changelog/2026-03-31-improvements-and-fixes) [#](https://supermemory.ai/changelog/2026-03-31-improvements-and-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. ### Fixes * Image content sent as raw base64 is now recognized as JPEG, PNG, GIF, or WebP instead of failing during summarization. * Metadata filters containing null characters no longer cause search requests to fail. [Console](https://supermemory.ai/changelog/2026-03-29-improvements-and-fixes) March 29, 2026 ## [Console improvements: API key flow and request analytics](https://supermemory.ai/changelog/2026-03-29-improvements-and-fixes) [#](https://supermemory.ai/changelog/2026-03-29-improvements-and-fixes) 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.](https://console.supermemory.ai/) [Web app](https://supermemory.ai/changelog/2026-03-28-improvements-and-fixes) March 28, 2026 ## [Document ingestion reliability fixes and Nova improvements](https://supermemory.ai/changelog/2026-03-28-improvements-and-fixes) [#](https://supermemory.ai/changelog/2026-03-28-improvements-and-fixes) 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. ### 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. * 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. [Web app](https://supermemory.ai/changelog/2026-03-26-improvements-and-fixes) March 26, 2026 ## [Memory expiration fields, plus Nova, MCP, and plugin fixes](https://supermemory.ai/changelog/2026-03-26-improvements-and-fixes) [#](https://supermemory.ai/changelog/2026-03-26-improvements-and-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. ### Improvements * [New v4 memories can include an expiration time, a reason for forgetting, and document or event dates in the initial request.](https://supermemory.ai/docs/add-memories) ### Fixes * Sign-up attempts with an unsupported email domain now return a clear rejection instead of a generic server error. * Usage limits now account for the full size of each request and allow continued processing when organization overage is enabled. * Nova no longer intermittently shows an Upgrade to Pro prompt on plugin and connection pages for users with an active paid plan. * MCP connections authenticated with an API key no longer fail with a missing-organization error. [Web app](https://supermemory.ai/changelog/2026-03-24-improvements-and-fixes) March 24, 2026 ## [Nova and Console fixes: plan recognition and account settings](https://supermemory.ai/changelog/2026-03-24-improvements-and-fixes) [#](https://supermemory.ai/changelog/2026-03-24-improvements-and-fixes) New Nova accounts create and activate a workspace during onboarding, Console Advanced Settings adds an account-email change flow, and account role changes now require administrator permission. ### Fixes * Account role changes now require administrator permission. [Web app](https://supermemory.ai/changelog/2026-03-18-improvements-and-fixes) March 18, 2026 ## [Console documents page, scoped API keys, and connector fixes](https://supermemory.ai/changelog/2026-03-18-improvements-and-fixes) [#](https://supermemory.ai/changelog/2026-03-18-improvements-and-fixes) Scoped API keys can grant access to multiple container tags, Console's organization picker shows each organization's plan and usage totals, and empty Nova spaces offer direct actions to start saving content. ### Improvements * [Scoped API keys can now grant access to multiple container tags.](https://supermemory.ai/docs/authentication) * When removing a connection, you can now keep its imported documents. ### Fixes * Console's API key list no longer crashes when an existing key has no metadata. * Deleting or merging container tags no longer reports a failure after the operation has already succeeded. * Google and Microsoft connections now keep syncing when new sign-in credentials replace the old ones. * Updating only a document's metadata no longer reprocesses unchanged content. [Web app](https://supermemory.ai/changelog/2026-03-14-improvements-fixes-and-polish) March 14, 2026 ## [Console billing updates and Documents API audio transcription](https://supermemory.ai/changelog/2026-03-14-improvements-fixes-and-polish) [#](https://supermemory.ai/changelog/2026-03-14-improvements-fixes-and-polish) Paid Console users can open the billing portal from the Billing page, the Requests page gets adjustable page sizes, connector setup lets you choose a document limit, and the Documents API adds audio transcription. ### Improvements * [The Documents API can now transcribe MP3, WAV, AAC, FLAC, OGG, AIFF, and M4A uploads.](https://supermemory.ai/docs/concepts/content-types) ### Fixes * Container tags containing colons work again in API requests. * The Documents API can now retry a failed document with the same custom ID instead of returning the failed record again. [Console](https://supermemory.ai/changelog/control-overage-at-the-organization-level) March 11, 2026 ## [Control API overage at the organization level](https://supermemory.ai/changelog/control-overage-at-the-organization-level) [#](https://supermemory.ai/changelog/control-overage-at-the-organization-level) Pro and Scale organizations can choose whether API usage continues into overage from Billing; Enterprise overage remains enabled and cannot be toggled. [Web app](https://supermemory.ai/changelog/2026-03-10-improvements-and-fixes) March 10, 2026 ## [Microsoft Agent Framework integration, Console and connector fixes](https://supermemory.ai/changelog/2026-03-10-improvements-and-fixes) [#](https://supermemory.ai/changelog/2026-03-10-improvements-and-fixes) Microsoft Agent Framework gains a Supermemory integration with automatic recall, optional conversation storage, and explicit memory tools, Nova adds multi-select document deletion, and Console admins can copy pending invitation links. ### Improvements * Integrators can now disable a scoped API key when a user leaves without deleting that user's memories or container tags. * [Console now lets you choose which GitHub repositories to sync and shows connection details and destinations in sync history.](https://supermemory.ai/docs/connectors/github) ### Fixes * Container tags with spaces or symbols no longer prevent documents and memories from being indexed. [Web app](https://supermemory.ai/changelog/2026-03-08-improvements-and-fixes) March 8, 2026 ## [Plugin sign-in approval, Console and Nova fixes](https://supermemory.ai/changelog/2026-03-08-improvements-and-fixes) [#](https://supermemory.ai/changelog/2026-03-08-improvements-and-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 * Plugin sign-in now shows an approval page before returning an API key to the requesting app. ### Fixes * Container tags containing URL-sensitive characters can now be viewed, updated, and deleted correctly in Console. * Console now shows clear not-found states for missing documents and container tags. [Web app](https://supermemory.ai/changelog/2026-03-04-improvements-and-fixes) March 4, 2026 ## [ViaSocket guide, memory graph tag filters, and Console billing fixes](https://supermemory.ai/changelog/2026-03-04-improvements-and-fixes) [#](https://supermemory.ai/changelog/2026-03-04-improvements-and-fixes) A new ViaSocket guide covers Supermemory searches and profiles in no-code flows, Console's memory graph filters by container tags, and scheduled downgrades now show the correct billing actions. ### Improvements * [A new ViaSocket guide shows how to use Supermemory searches and profiles in no-code automation flows.](https://supermemory.ai/docs/integrations/viasocket) [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) * [The Documents API can now match either any or all selected container tags.](https://supermemory.ai/docs/concepts/filtering) [Web app](https://supermemory.ai/changelog/2026-02-19-improvements-fixes-and-polish) February 19, 2026 ## [OpenClaw custom memory containers, plus API and Nova fixes](https://supermemory.ai/changelog/2026-02-19-improvements-fixes-and-polish) [#](https://supermemory.ai/changelog/2026-02-19-improvements-fixes-and-polish) OpenClaw can route store, search, forget, and profile operations to custom memory containers, document listing matches any selected container tag, and throttled API keys get a proper rate-limit error. ### Fixes * Document listing now returns documents matching any selected container tag instead of requiring every tag. * The API now returns a rate-limit error for throttled keys instead of reporting them as unauthorized. * v4 profile searches and search requests now record search-query usage correctly. * Large documents now finish processing instead of failing midway or timing out during summarization. [API](https://supermemory.ai/changelog/search-can-return-documents-memories-or-both) February 18, 2026 ## [Search API can return documents, memories, or both](https://supermemory.ai/changelog/search-can-return-documents-memories-or-both) [#](https://supermemory.ai/changelog/search-can-return-documents-memories-or-both) The v4 Search API can return raw document chunks, extracted memories, or both for each query. [Web app](https://supermemory.ai/changelog/2026-02-16-improvements-fixes-and-polish) February 16, 2026 ## [OpenCode container tags, MCP forget fix, and Nova polish](https://supermemory.ai/changelog/2026-02-16-improvements-fixes-and-polish) [#](https://supermemory.ai/changelog/2026-02-16-improvements-fixes-and-polish) OpenCode can use exact user and project container tags reusable across teammates and machines, plus fixes for saving captured conversation transcripts and MCP's forget action. ### Fixes * Short notes and questions can now finish processing even when they do not need a generated summary. [Web app](https://supermemory.ai/changelog/2026-02-13-improvements) February 13, 2026 ## [Container tag merging and Nova multi-Space filtering](https://supermemory.ai/changelog/2026-02-13-improvements) [#](https://supermemory.ai/changelog/2026-02-13-improvements) The API can merge two container tags into one while preserving their documents and memories, and Nova can filter the document grid and memory graph across multiple selected Spaces. ### Improvements * [The API can merge two container tags into one while preserving their documents and memories.](https://supermemory.ai/docs/concepts/container-tags) [Web app](https://supermemory.ai/changelog/2026-02-12-fixes) February 12, 2026 ## [API fixes: safer array filters and organization scoping](https://supermemory.ai/changelog/2026-02-12-fixes) [#](https://supermemory.ai/changelog/2026-02-12-fixes) Array filters in search, memories, and connections now safely handle user-provided values, and related results stay within the active organization. ### Fixes * Array filters in search, memories, and connections now safely handle user-provided values, and related results stay within the active organization. [API](https://supermemory.ai/changelog/2026-02-06-improvements) February 6, 2026 ## [Search deduplication and container tag scoped API keys](https://supermemory.ai/changelog/2026-02-06-improvements) [#](https://supermemory.ai/changelog/2026-02-06-improvements) Search results deduplicate identical content down to the highest-scoring match, Console can create API keys scoped to a single container tag, and owners and admins can delete a container tag with its memories and documents through the API. ### Improvements * Search results now show one copy of identical content, keeping the highest-scoring match. * [Console can create API keys restricted to one container tag, limiting document, search, and profile access to that tag.](https://supermemory.ai/docs/concepts/container-tags) * Organization owners and admins can delete a container tag and its associated memories and documents through the API. ### Fixes * [Deleting a container tag no longer removes documents that are also shared with another tag.](https://supermemory.ai/docs/concepts/container-tags) [API](https://supermemory.ai/changelog/2026-02-04-fixes) February 4, 2026 ## [Memory extraction fix: dated plans now expire automatically](https://supermemory.ai/changelog/2026-02-04-fixes) [#](https://supermemory.ai/changelog/2026-02-04-fixes) Memory extraction now treats dated plans as expiring facts and records why they should expire. ### Fixes * Memory extraction now treats dated plans as expiring facts and records why they should expire. [API](https://supermemory.ai/changelog/2026-02-03-improvements-and-polish) February 3, 2026 ## [Attach project context to container tags for memory extraction](https://supermemory.ai/changelog/2026-02-03-improvements-and-polish) [#](https://supermemory.ai/changelog/2026-02-03-improvements-and-polish) Developers can attach project-specific context to a container tag so memory extraction uses it during ingestion, and the Startup Program application button opens a prefilled email. ### Improvements * [Developers can attach project-specific context to a container tag so memory extraction uses it during ingestion.](https://supermemory.ai/docs/concepts/container-tags) [Plugins](https://supermemory.ai/changelog/2026-01-31-improvements-and-fixes) January 31, 2026 ## [Console plugins page and automatic document ingestion retries](https://supermemory.ai/changelog/2026-01-31-improvements-and-fixes) [#](https://supermemory.ai/changelog/2026-01-31-improvements-and-fixes) Console gains a dedicated Plugins page for browsing and managing plugins, and documents stuck in the queue now retry automatically up to three times before being marked failed. ### Fixes * Documents that remain queued now retry automatically up to three times before being marked failed. [Connectors](https://supermemory.ai/changelog/2026-01-26-improvements-and-fixes) January 26, 2026 ## [Notion page properties in document metadata and append fixes](https://supermemory.ai/changelog/2026-01-26-improvements-and-fixes) [#](https://supermemory.ai/changelog/2026-01-26-improvements-and-fixes) Notion connections expose page properties like status, tags, dates, and assignees as document metadata for filtering and queries, and appending to a document now retains the full combined content with its total token count. ### Improvements * [Notion connections now expose page properties such as status, tags, dates, and assignees as document metadata for filtering and queries.](https://supermemory.ai/docs/connectors/notion) ### Fixes * Appending to an existing document now retains the full combined content and reports its total token count. [Console](https://supermemory.ai/changelog/2026-01-25-improvements-and-fixes) January 25, 2026 ## [Enterprise plan support in the console and web link import fix](https://supermemory.ai/changelog/2026-01-25-improvements-and-fixes) [#](https://supermemory.ai/changelog/2026-01-25-improvements-and-fixes) Console recognizes Enterprise plans across billing, invoices, usage, and the account menu, and web links that block automated availability checks can still be imported. ### Fixes * Web links that block automated availability checks can now still be imported. [API](https://supermemory.ai/changelog/2026-01-23-improvements-and-fixes) January 23, 2026 ## [AI SDK strict mode, MCP recall, and browser extension fixes](https://supermemory.ai/changelog/2026-01-23-improvements-and-fixes) [#](https://supermemory.ai/changelog/2026-01-23-improvements-and-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. ### Fixes * Pages saved by the browser extension now appear as webpages with their original source link instead of plain-text documents. [Web app](https://supermemory.ai/changelog/2026-01-18-improvements-and-fixes) January 18, 2026 ## [MCP updates: project listing and API key reuse fix](https://supermemory.ai/changelog/2026-01-18-improvements-and-fixes) [#](https://supermemory.ai/changelog/2026-01-18-improvements-and-fixes) The MCP server can list your projects and use their names when saving or recalling memories, and reconnecting an approved MCP client reuses its active API key instead of creating another one. ### Fixes * Reconnecting an approved MCP client now reuses its active API key instead of creating another one. [Web app](https://supermemory.ai/changelog/2026-01-14-fixes-and-polish) January 14, 2026 ## [PDF import reliability and console organization fixes](https://supermemory.ai/changelog/2026-01-14-fixes-and-polish) [#](https://supermemory.ai/changelog/2026-01-14-fixes-and-polish) PDF imports retry failed pages with a fallback extractor without truncating long documents, and Console no longer shows accepted invitations as pending or overflows on long organization IDs. ### Fixes * PDF imports now retry failed pages with a fallback extractor and avoid truncating long documents. * Fixed an issue that caused some multi-chunk documents to fail during processing. [API](https://supermemory.ai/changelog/2026-01-09-improvements-and-fixes) January 9, 2026 ## [Console container tag filters, Startup Program, and document fixes](https://supermemory.ai/changelog/2026-01-09-improvements-and-fixes) [#](https://supermemory.ai/changelog/2026-01-09-improvements-and-fixes) Console can filter recent documents by container tags, includes a Startup Program application with $1,000 in usage credits, and lets free organizations start a Pro upgrade from the sidebar. ### Fixes * Adding content with an existing custom ID now appends it to that document instead of replacing it. * [Updating a document through the API now replaces and reprocesses the full content instead of appending it.](https://supermemory.ai/docs/document-operations) [Web app](https://supermemory.ai/changelog/2026-01-07-improvements-and-fixes) January 7, 2026 ## [Console usage stats, AI SDK prompt templates, and OpenCode updates](https://supermemory.ai/changelog/2026-01-07-improvements-and-fixes) [#](https://supermemory.ai/changelog/2026-01-07-improvements-and-fixes) Delete a consumer organization and its stored data from Profile settings, control how retrieved memories are formatted in AI SDK prompts, and see token and search-query usage in Console for the current and previous billing periods. ### Improvements * You can delete the active consumer organization and its stored data from Profile settings. ### Fixes * Updating a document now processes and bills only newly added content instead of unchanged chunks. [API](https://supermemory.ai/changelog/2026-01-05-improvements-and-fixes) January 5, 2026 ## [MemoryBench parallel execution and MCP connection reliability](https://supermemory.ai/changelog/2026-01-05-improvements-and-fixes) [#](https://supermemory.ai/changelog/2026-01-05-improvements-and-fixes) MemoryBench can run benchmark phases concurrently with separate concurrency controls per phase, and MCP and streaming connections retry brief server overloads before returning a temporary-unavailable error. ### Fixes * MCP and streaming connections now retry brief server overloads before returning a temporary-unavailable error. [Web app](https://supermemory.ai/changelog/2026-01-04-fixes) January 4, 2026 ## [MCP memory limits and Google Drive connector fixes](https://supermemory.ai/changelog/2026-01-04-fixes) [#](https://supermemory.ai/changelog/2026-01-04-fixes) Memories added through MCP now count against the memory allowance instead of the API token limit, and the Add Memory connection picker opens Google Drive instead of returning a disabled-connector error. ### Fixes * Memories added through MCP now count against the memory allowance instead of the API token limit. ## 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/)