Blog·News

Catch up with our UNFORGETTABLE Launch Week

By Shardul Mane·3 min read

Launch Week banner with bold text "Unforgettable supermemory" over a faint calendar background

Over 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.

So during Unforgettable Launch Week, we focused on one goal -

Make memory simpler, faster, more accessible and available wherever AI lives.

And instead of announcing ideas, we shipped things you can use today.

Below is a recap of what went live, and why it matters.

memorybench - a standard way to evaluate AI memory

We kept building internal benchmarking rigs. So did our users.
Everyone was duplicating effort, and still comparing incompatible results.

memorybench changes that.

GitHub: github.com/supermemoryai/memorybench

New connectors: GitHub, S3, and Web Crawler

Your context doesn’t live in one place. Neither does Supermemory.

These sit alongside Notion, Google Drive, and OneDrive, which many of you already rely on.

Context shouldn’t be siloed. Now it isn’t.

Docs: supermemory.ai/docs/connectors/overview Access in console:console.supermemory.ai/login

Conversations endpoint - cheaper, smarter conversations

Most LLM providers bill you for every token processed, even when nothing new is happening.

Our conversations endpoint now processes only the new tokens while keeping full context.

That means:

  • lower cost
  • more consistent conversations
  • fewer “I forgot” moments

Docs: supermemory.ai/docs

Hybrid Search - where memory meets retrieval

Memory alone isn’t always enough. Retrieval alone isn’t either.

Hybrid Search blends the two, improving context quality by 10–15 percent with a single toggle. No migrations or rewrites required, just better answers.

Learn more: supermemory.ai/docs/search/examples/mem…

Stateful coding agents (opencode plugin)

Traditional coding agents degrade over time. As threads grow, they forget earlier context and repeat themselves.

The Supermemory opencode plugin makes agents stateful. They learn in real time, maintain project awareness, and adapt across sessions.

For our own team, this changed the way we build software.

GitHub: github.com/supermemoryai/opencode-super…

Embeddable Memory Graph

People like seeing how their knowledge connects.

We made the Supermemory graph embeddable so developers can include that same interactive visualization inside their own products. One component, fully customizable, integrated directly into the user experience.

Docs: supermemory.ai/docs/memory-graph/overvi…

code-chunk - chunking built for code

Most text splitters weren’t designed for code. They break logic, functions, and structure — which leads to poor recall.

code-chunk is AST-aware and splits at the right boundaries. In our evaluation, that improved recall by 28 points.

Docs: supermemory.ai/blog/building-code-chunk… GitHub: github.com/supermemoryai/code-chunk

MCP 4 - memory that travels with you

We believe users should control their memory, not platforms.

MCP 4 allows Supermemory context to work across tools like ChatGPT, Claude, Windsurf, and others, using an open Model Context Protocol server.

No lock-in. Memory that moves with you.

The Supermemory Startup Program

We’ve benefited from communities and programs that supported us early. Now we want to extend that same support to the next wave of builders.

The Supermemory Startup Program offers:

  • $1,000 in credits
  • dedicated guidance from our team
  • simple setup
  • six months to build and iterate

We’ve already seen founders move from idea to working product dramatically faster once memory stops being the bottleneck.

Apply: binary.so/eQvzzEk Read our blog: supermemory.ai/blog/empowering-the-next…

Nova - our consumer app returns

We are bringing our VIRAL consumer app back! Say hello to NOVA.

A personal memory companion designed to help individuals organize, recall, and make sense of their knowledge across tools.

Join the waitlist: supermemory.ai/consumer

Where we’re headed

Every launch in Unforgettable Launch Week was built around these principle

Memory should be reliable.
It should be accessible.
And it should exist everywhere AI operates.

Whether you’re experimenting, scaling, or building something entirely new, our goal is to give you memory infrastructure that stays out of the way - while quietly powering everything beneath it.

Thanks for being part of this journey. There is a lot more coming.

  1. An update to supermemoryWe'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.News
  2. 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
  3. 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
  4. 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
  5. 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
  6. 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
  7. 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
  8. 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
  9. 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
  10. 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
  11. 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
  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