apps/docs/changelog/overview.mdx
<Update label="March 18, 2026" tags={["API", "SDK", "Console", "CLI"]}>
New command-line tool for managing memories, documents, profiles, tags, connectors, and API keys directly from the terminal.
@supermemory/tools v1.4.1Now exposes raw searchResults in MemoryPromptData, giving full control over how retrieved memories are formatted in prompts.
PowerPoint files (.pptx) are now a supported content type. Audio files are automatically transcribed via Gemini 2.5 Flash, chunked, and indexed.
Scoped API keys can now be assigned to multiple container tags — one key, multiple spaces.
New dedicated documents browser in the console for viewing, filtering, and managing all ingested content.
</Update><Update label="March 9, 2026" tags={["API", "SDK", "MCP", "Integrations"]}>
New DELETE endpoint to disable scoped API keys programmatically.
supermemory-agent-framework Python PackageOfficial Python package for using Supermemory with Microsoft's Agent Framework — memory tools and middleware out of the box.
The MCP server now includes an interactive graph visualization app for exploring memory connections from any MCP-compatible client.
customId.extends relation type in memory graph for richer knowledge graph connections.<Update label="March 2, 2026" tags={["API"]}>
Bring your own vector store — Supermemory now supports pluggable vector backends beyond the default.
New GET /v3/documents endpoint with pagination, filtering by container tag, status, and metadata.
<Update label="February 26, 2026" tags={["API", "Console"]}>
Run the full Supermemory stack on your own infrastructure with Docker.
Complete redesign of the developer console with new navigation, improved billing, and a unified project view that merges consumer and developer organizations.
The previous cap of 120 memories per container tag has been removed. Store unlimited memories.
</Update><Update label="February 22, 2026" tags={["API", "SDK", "CLI"]}>
Install with npx skills add supermemoryai/skills — teaches Claude to proactively recommend and implement Supermemory when building AI apps. Includes TypeScript and Python examples.
operator parameter.include: chunks in /v4/search in favor of the hybrid search mode.<Update label="February 9, 2026" tags={["API", "Console"]}>
Consumer and developer organizations merged into a single org type. All orgs can now access both Nova and the developer API.
Billing now shows token usage in a credits-based format.
Spaces in Nova support multi-select, replacing "All Spaces" with scoped "Nova Spaces."
</Update><Update label="February 6, 2026" tags={["API"]}>
Create API keys scoped to specific container tags for fine-grained access control per space.
New endpoint to delete container tags and their associated document relationships.
Set custom context prompts per container tag to control how memories are extracted and summarized within each space.
</Update><Update label="February 3, 2026" tags={["Integrations", "SDK"]}>
Added guides for LangGraph, OpenAI Agents SDK, CrewAI, Agno, Mastra, LangChain, and Claude Code — covering all major AI agent frameworks.
New docs on entity extraction, context enrichment, and comprehensive authentication examples (API key, OAuth, scoped keys).
</Update><Update label="January 25, 2026" tags={["API", "Console", "SDK"]}>
New auth system for external tool integrations, enabling secure plugin-to-API connections. Dedicated plugin page with auth flows for Claude Code, OpenCode, and ClawdBot.
Enterprise tier now available in the console.
@supermemory/tools — Strict ModeStrict mode support for OpenAI function calling, ensuring schema-validated tool calls.
</Update><Update label="January 14, 2026" tags={["API"]}>
PDF extraction now uses Mistral OCR 3 with Gemini fallback for significantly improved accuracy on scanned documents and complex layouts.
Embedding storage optimized with half-precision vectors, reducing storage costs while maintaining search quality.
Create and customize spaces with emoji identifiers in Nova.
</Update><Update label="January 8, 2026" tags={["API", "SDK", "Integrations"]}>
New connector to sync Gmail threads into Supermemory. Threads are stored in R2 for reliable processing of large mailboxes.
supermemory-pipecat Python PackageNew SDK for Pipecat voice AI pipelines, including Gemini Live speech-to-speech support.
@supermemory/tools — Prompt TemplatesCustomize how memory context is formatted in AI SDK integrations with the new promptTemplate option.
<Update label="December 30, 2025" tags={["MCP", "SDK", "API"]}>
Major MCP server update with session configuration, project-aware tools on every init, and backward-compatible 3.0 support. New context prompt for automatic user profile injection into AI conversations.
New connector to sync documents from Amazon S3 buckets, with console UI for bucket configuration.
Complete rewrite of @supermemory/memory-graph with improved visualization and performance.
<Update label="December 24, 2025" tags={["SDK"]}>
@supermemory/tools — AI SDK v5/v6Now supports both Vercel AI SDK v5 and v6 with automatic version detection.
supermemory (TypeScript) and supermemory-openai-sdk (Python) now support the conversations API for multi-turn chat with memory.
New open-source benchmark suite for evaluating memory systems, with documentation and CLI.
</Update><Update label="December 17, 2025" tags={["API"]}>
New hybrid search mode in /v4/search combining semantic and keyword search for better recall on technical queries.
<Update label="December 9, 2025" tags={["API", "Console"]}>
Web crawling powered by Firecrawl for more reliable extraction of website content, with fallback support.
Bring your own GitHub OAuth app credentials for the GitHub connector, enabling private repo access.
API keys now trigger email notifications before expiration.
Connection syncs now produce detailed logs visible in the console.
</Update><Update label="December 5, 2025" tags={["SDK"]}>
@supermemory/tools — Browser API Key SupportapiKey can now be passed via options instead of relying on process.env, enabling browser-based usage.
<Update label="December 2, 2025" tags={["Console"]}>
Organizations can now be fully deleted from the console, including all associated data.
New billing layout with invoicing support and improved usage visibility.
Streamlined onboarding flow for new users.
</Update><Update label="November 17, 2025" tags={["API", "SDK"]}>
New connector to crawl and index entire websites with configurable depth and URL patterns.
@supermemory/memory-graph PackageNew package for building interactive graph visualizations of memory connections, with a standalone playground.
@supermemory/tools OpenAI integration now supports the Responses API.
supermemory-openai-sdk — Python MiddlewareNew withSupermemory middleware for the Python OpenAI SDK, enabling transparent memory injection into OpenAI API calls.
Chrome extension can now capture full webpage content with markdown conversion.
Memory creation now uses bulk inserts for significantly faster batch ingestion.
</Update><Update label="October 27, 2025" tags={["API", "SDK"]}>
New string_contains filter type for partial string matching, ignoreCase option for case-insensitive operations, and improved negation support. Enhanced SQL injection protection.
withSupermemory for OpenAI SDKNew withSupermemory wrapper for the OpenAI TypeScript SDK — transparent memory injection with automatic assistant response capture.
New integration guides for connecting Supermemory with Zapier and n8n automation workflows.
</Update><Update label="October 10, 2025" tags={["SDK", "API", "Console"]}>
@supermemory/tools — AI SDK withSupermemoryNew withSupermemory language model wrapper for Vercel AI SDK that automatically injects memory context and captures assistant responses.
New Raycast extension for quick memory access and addition from the macOS launcher.
New /v4/profile endpoint for retrieving AI-generated user profiles derived from memory interactions, with container tag scoping.
<Update label="September 17, 2025" tags={["API", "Console"]}>
New include.forgottenMemories parameter in v4 search API to search through memories that have been explicitly forgotten or expired.
DELETE /v3/documents/:id now supports both internal document ID and customId.
Renamed "memories" to "documents" for developer clarity. New /v3/documents/* endpoints with full backward compatibility via automatic redirects from /v3/memories/*.
New console design with dark/light mode, org switcher, billing invoices, space selector with search, and memory list with multi-delete.
<Update label="September 12, 2025" tags={["API", "SDK"]}>
Complete rewrite with comprehensive API references, cookbook recipes, and production-ready examples for TypeScript, Python, and cURL.
@supermemory/tools PackageNew tools package for native Vercel AI SDK and OpenAI integration with memory tools and infinite chat. Plus openai-python-sdk for Python middleware.
New POST /v3/documents/batch for batch ingestion and DELETE /v3/documents/bulk for bulk deletion.
Full lifecycle management with forgetAfter dates and forgotten memory filtering.
Video files can now be ingested with automatic content extraction.
</Update><Update label="September 1, 2025" tags={["MCP", "Console"]}>
Step-based UI for connecting MCP clients with v1 migration support. One-click install for Cursor.
Browser extension now integrates directly with Claude.ai and t3.chat for automatic memory search during conversations.
Supermemory is now open to all users — no more waitlist.
</Update><Update label="August 24, 2025" tags={["API", "Console"]}>
Redesigned marketing pages with developer-focused content, SEO improvements, and mobile responsiveness.
Ingest web content with <sm-highlight> tags for targeted extraction.
Billing usage and limits now visible directly in the console dashboard.
containerTag in add memory — simpler API for basic use cases.<Update label="August 16, 2025" tags={["Console"]}>
Complete rewrite of the consumer-facing app — new chat experience with slide-out window, masonry memory grid with infinite scroll, PWA support, and mobile-responsive menu bar.
Graph rendering now uses WebGL for smooth visualization of thousands of memory connections. Search highlights relevant nodes with zoom.
New chat system with memory-aware conversations, regeneration, copy buttons, and the ability to add memories through chat.
Memory graph now supports update, extend, and derive relation types. Memories can be inferred from multiple parent documents.
<Update label="August 12, 2025" tags={["API"]}>
Google Drive connector now processes PDF files alongside Docs, Sheets, and Slides.
Google Drive, OneDrive, and Notion client secrets are now encrypted at rest.
New endpoint for deleting multiple memories at once.
Initial self-hosting support — run Supermemory on your own infrastructure.
</Update><Update label="August 1, 2025" tags={["Console", "API"]}>
Console app moved from Vercel to Cloudflare Workers for improved performance and lower latency.
Billing system integrated with Autumn for subscription management, waitlist early access, and usage tracking.
Redesigned developer dashboard with API key display in code snippets, limits visualization, and MCP installation instructions.
</Update><Update label="July 25, 2025" tags={["Console", "MCP"]}>
First version of the consumer app with chat, memory browsing, project management, and profile view. New consumer-oriented landing page.
MCP server migrated to the Agents SDK architecture for better reliability and project support.
Revamped billing page with upgrade buttons and plan management.
</Update><Update label="July 16, 2025" tags={["Console", "API"]}>
Complete rewrite of the graph visualization — faster rendering, better layout, and interactive exploration.
New guided onboarding flow for first-time console users.
Real-time sync for Notion connections via webhook integration.
</Update><Update label="July 5, 2025" tags={["Console"]}>
New marketing site with glass UI design, rewritten pricing page, and dedicated MCP page.
New billing page with upgrade buttons and plan comparison.
Analytics tracking added across the console and landing page.
</Update><Update label="June 21, 2025" tags={["API"]}>
New connector for syncing OneDrive files with webhook-based real-time updates.
Bring your own API keys for connector integrations (Google Drive, OneDrive, Notion).
Google Drive connector now supports Sheets and Slides alongside Docs.
</Update><Update label="June 12, 2025" tags={["Console", "API"]}>
First version of the dashboard overview page with memory analytics, container tag distribution charts, and usage metrics.
Real-time sync — Google Drive changes are automatically detected and processed.
Error monitoring added across the console and API.
</Update><Update label="May 28, 2025" tags={["API", "Console"]}>
Console reached launchable state with login page improvements, auth fixes, and the first version of the new dashboard with React Query.
Memory Router proxy with automatic context compression for infinite-length conversations with LLMs.
Filter search results by container tags for scoped memory retrieval.
Google Drive connector switched from PDF to Markdown export for better content fidelity.
</Update><Update label="May 8, 2025" tags={["API"]}>
New /v3/ endpoints replacing v2 — cleaner routes, updated memory endpoint, and new update/delete operations.
Initial OneDrive integration for syncing files into Supermemory.
New connection-document relationship model for tracking which connector synced which document.
</Update><Update label="April 30, 2025" tags={["API"]}>
New interactive API references on Mintlify with detailed parameter explanations, response schemas, and bearer auth.
Enhanced organizational grouping for better memory isolation and user-scoped content.
Automatic processing of PDFs, images, videos, and web content regardless of URL extensions.
</Update><Update label="April 28, 2025" tags={["API"]}>
New endpoints for programmatic Google Drive integration and file syncing.
</Update><Update label="April 25, 2025" tags={["API"]}>
documentThreshold and chunkThreshold — fine-tune search sensitivity.docId parameter — search within specific large documents.onlyMatchingChunks — precise result filtering.endUserId filtering — scope search to specific users.<Update label="April 22, 2025" tags={["API", "MCP"]}>
First version of the MCP server for AI model integrations.
AI-generated personalization based on user memory patterns.
First version of the list memories API with pagination.
</Update><Update label="April 14, 2025" tags={["API"]}>
Organization invites and user management endpoints.
Hourly analytics tracking with detailed usage metrics.
New ingestion workflow with status tracking: queued → extracting → chunking → embedding → done.
<Update label="March 27, 2025" tags={["API"]}>
First version of the connectors architecture — sync external data sources into Supermemory.
Filter memories by tags in search and list operations.
Request tracking, error counts, and usage metrics per organization.
</Update><Update label="March 18, 2025" tags={["API"]}>
The platform begins — Cloudflare Workers API with auth, ingestion workflows, vector search, and organization support. Built on Hono, Drizzle ORM, and Cloudflare D1/Hyperdrive.
</Update><Update label="January 20, 2025" tags={["Console"]}>
Major release of the consumer web app with new import tools (CSV, Markdown/Obsidian), improved hybrid search with date relevancy, batch delete, and space management (edit/delete names).
First version of the documentation site with API reference, getting started guide, and pricing page.
</Update><Update label="August 16, 2024" tags={["Console"]}>
New consumer app version with canvas/note editor, text-to-speech on AI answers, PWA support, improved Telegram bot with Markdown, and memory queue processing. Extension gets drag-and-dismiss features.
</Update><Update label="July 21, 2024" tags={["Console"]}>
Supermemory launches on ProductHunt. Features at launch: shareable spaces, Twitter thread import, AI chat with citations, onboarding flow, recommended items, chat history, and keyboard shortcuts.
</Update><Update label="June 23, 2024" tags={["Console"]}>
Added multi-turn conversations, canvas with drag-and-drop, Telegram bot, vector lookup 2x speedup, and the first version of the Chrome extension.
</Update><Update label="May 18, 2024" tags={["API"]}>
Backend migrated from Next.js API routes to Hono on Cloudflare Workers. Landing page redesign, browser rendering for web content extraction.
</Update><Update label="April 11, 2024" tags={["Console"]}>
First public release — spaces, chat with AI, Twitter bookmarks import, Chrome extension with save-from-page, notes editor, and search across all saved content.
</Update><Update label="February 21, 2024" tags={["Console"]}>
Initial monorepo setup with auth, Chrome extension, AI chat with citations using OpenAI embeddings, and the first version of the web app.
</Update>