Blog·News

An update to supermemory

We've discontinued the supermemory company brain and Nova. Everyone who was charged has been refunded, our MCP and plugins continue to run, and we're going all in on the memory engine.

By Dhravya Shah·4 min read

Supermemory banner reading "Frontier memory for agents" over a blurred landscape at dusk
TL;DR
The supermemory company brain and Nova are discontinued as of 9th September. Everyone who was charged has been refunded. Our MCP and plugins keep working, and we're going all in on the memory API.

Just over a month ago, we launched the supermemory company brain. Months of our time, effort and energy went into this, and a lot of money too.

The launch got 500k+ views. Users loved it. We had hundreds of companies actively using it in their Slack.

Despite that, we have decided to discontinue the supermemory company brain and Nova, our personal knowledge management platform. We stopped the service yesterday, on 9th September, and everyone who was charged was refunded.

Our MCP and our plugins with Claude Code and others will continue to operate. They have been moved to the developer platform and can still be used for personal use.

What this means for you

If you're a company brain user, you should already have been refunded, and the Slack bot will stop working. You will not be able to access the company brain dashboard. Reach out to us at support@supermemory.com for any questions.

If you use Nova, you can get the same functionality using our MCPs, and have unified knowledge across all your apps. Only the surface of the app is being discontinued. The functionality is being moved to our console.

Why would we do this

This was a very hard decision for me, but it had to be done, for three reasons.

Clarity and focus

When we launched last year, supermemory set out to do one thing: build the best memory system for agents. And we did. It's still a hard, unsolved problem, but today hundreds of thousands of companies build on top of supermemory, and many more use it with their openclaw, Claude Code and personal agents too.

Adding one more product to the stack kind of made sense, but the answer to the question "what is supermemory?" got harder and harder to answer as we added more things that we do.

Honestly, as a founder, at some point I never zoomed out and asked whether that's the right direction for us. I built it, basically because we could.

Direction of the company

There are many people trying to build the "company brain" vision. I had to ask myself, what would this look like in 5 or 10 years? It's abundantly clear that multiplayer agents will be the future, and someone will make them work and make them good. But are we the best positioned to build this company brain future?

As of now, probably not. I want to continue pushing on the frontier of what we can do with agents, and enable others to build in these awesome directions.

We want to be the default, and the best way to do something. If we can't be, we will forever be stuck in this messy middle with no clarity of thought.

Conflict of interest

We have many, many developers, startups and enterprises who already use our memory engine in production. While this was not an explicit issue, I think our current and future customers would not be very happy with us building a direct competitor, even if it is not intended to be.

We also want to be working with the Notions and Cognitions of the world, and do great work and research with them for their memory issues. Companies that are also kind of doing company brain and general agent work.

Discontinuing and focusing will now enable us to directly work with anyone, and also help us focus and keep building the best memory system.

Shipping is important, unshipping is more important

We want to make sure that everything we do, we're the best at doing.

Using some other company brain products and agent harnesses made me realize that putting 100% of your time in something can lead to great results, and since we were not able to do that, our product was average. Not out of the ordinary.

On the other hand, we are even more excited for our main product, the API, and the roadmap we have for it. We truly believe that we are, and will continue to be, the frontier system for memory in agents.

So, what is supermemory?

Supermemory is the frontier memory system for agents. It's the best way to add memory to your own agents, for products you're building and your personal agents as well.

While it's bittersweet that we have to stop serving one of our products, it's also exciting to see what's ahead for us. The team is excited to be building something that we think will be a fundamental piece of the puzzle to make really useful agents, and important for AGI.

  1. SMFS: making agentic retrieval 55% cheaper AND more accurateWe launched SMFS.ai (Supermemory Filesystem) a few weeks ago, with a simple bet: We can redesign the filesystem specifically for agents, with special files, structures, and commands that it can use for it's tasks. Today, SMFS is used by hundreds of companies to power their agents.Engineering
  2. Introducing Dynamic Dreaming: supermemory now connects the dots, for you.Dreaming is magical. TLDR: We're launching Dynamic Dreaming in supermemory today, which automatically works if you're using supermemory in any way - API, OpenClaw, Hermes agent, etc.Engineering
  3. Dear reader, we just made supermemory insanely cheap... the Context CloudWhen I first started building supermemory, I had one goal: To build the best memory system for AI. I would talk to customers, and find out that memory was not the only thing they needed - They were all setting up 7-8 different vendors at the same time.Engineering
  4. Introducing @supermemory/tools v2.0.0Today we're releasing v2.0.0. This release unifies the API across all agents sdk integrations from AI SDK to Mastra, makes conversation identity a first-class concept, and ships with memory saving on by default.Engineering
  5. supermemory will make your Hermes-agent crazy powerfulToday, we are launching supermemory support to your Hermes agent TLDR: you can use supermemory now in your Hermes agent, it totally free to get started - https://supermemory.ai/docs/integrations/hermes In case you missed it: Hermes Agent is a self-improving AI agent from Nous Research.Engineering
  6. Solving the Precision-Recall Tradeoff: Search Result AggregationWhen you're building memory for AI, search is your foundational layer. The way search generally works is straightforward: the user defines a query, and then sets a limit (top-K) on how many search results they want returned. Usually, this is set to 10 or 20.Engineering
  7. Infinitely running stateful coding agentsWe built a plugin for Claude Code and OpenCode that gives your coding agent persistent memory. It remembers your preferences, learns your codebase, and never loses context mid-conversation. The result is an agent you can run for months without starting over.Engineering
  8. Why everyone is complaining about OpenClaw's memory (it sucks) - and why supermemory fixes it.TLDR: Today, we are releasing a new version of our openclaw plugin - https://github.com/supermemoryai/openclaw-supermemory. This post is going to be a bit technical, so bear with me (or bookmark for later!) In this post, I will talk about what we do about OpenClaw memory, and how we fix it.Engineering
  9. We added supermemory to Claude Code. It's INSANELY powerful now...Today, we are launching the Supermemory plugin for Claude Code! TLDR: You can use supermemory in claude code now. - https://github.com/supermemoryai/claude-supermemory Claude code has genuinely changed how I work. But there's this one thing that drives me crazy...Engineering
  10. Clawd / Molt bot's memory SUCKS. We gave it supermemory.I'm the founder of supermemory. Clawd/Molt bot is blowing up right now, with many, many use cases. I set it up, too, and have been using it through telegram. TLDR: just go to https://supermemory.ai/docs/integrations/clawdbot to set up supermemory for your clawd bot.Engineering
  11. Catch up with our UNFORGETTABLE Launch WeekOver the last year, one belief has guided almost everything we’ve built at Supermemory AI becomes meaningfully useful only when it remembers. Memory shouldn’t be something developers rebuild from scratch. It shouldn’t be fragile, expensive, or trapped inside a single tool.News
  12. Empowering the Next Generation of Founders: Supermemory Startup ProgramIf there’s one thing we’ve learned while building Supermemory, it’s that most startups don’t fail because they didn't build features; they fail when infrastructure slows them down, or they built too slow.News
  13. Building code-chunk: AST Aware Code ChunkingAt Supermemory, we're building context engineering infrastructure for AI. A huge part of that is dealing with code: ingesting repos, understanding structure, and making it searchable. The problem is that most code chunking solutions are terrible. We built code-chunk to fix this.Engineering
  14. Supermemory raises $3 million with the best memory engine for LLMsToday, I am excited to announce our first funding round to accelerate our mission of building an interoperable, scalable and reliable memory for LLMs and agents. Memory is one of the hardest challenges in AI right now.News
  15. Unified Memory That Works Where You Work: Your Second Brain With SupermemoryHi everyone, I’m Dhravya, the founder of Supermemory. I want to start with a little story behind why this product means so much to me. You can also skip straight to what it is and how it works below.Engineering
  16. Supermemory just got faster on PlanetScaleWhat is Supermemory? Supermemory completes the missing part of the LLM puzzle: memory. Just as memory is crucial for human intelligence, it's essential for truly intelligent AI systems.Engineering
  17. Faster, smarter, reliable infinite chat: Supermemory IS context engineering.People are obsessed with prompts and prompt engineering. Sure, what you say is important, but what the model knows when you say it is the difference between a stateless text generator and an intelligent AI system. In short, context is the most crucial component.News
  18. We solved AI API interoperabilityOne API to rule them all, One spec to find them, One library to bring them all and in the TypeScript, bind them. When we were building the the Infinite Chat API, initially, we only supported the OpenAI format. This was fine, until a lot of our customers started asking, asking for more.Engineering
  19. The UX and technicalities of awesome MCPsLast month, we launched the Supermemory MCP, mostly to test our own infrastructure and get some initial traction. It blew up. To my absolute surprise, the initial launch itself got half a million impressions (!!!). Then, we launched and got #2 on ProductHunt too.Engineering
  20. Architecting a memory engine inspired by the human brainLanguage is at the heart of intelligence, but what truly powers meaningful interaction is memory — the ability to accumulate, recall, and contextualize information over time. Large Language Models (LLMs) have mastered language, but memory remains their Achilles’ heel.Engineering