<?xml version="1.0" encoding="UTF-8"?><rss version="2.0"><channel><title>supermemory blog</title><description>Engineering notes, technical reports, and announcements from the supermemory team.</description><link>https://supermemory.ai/</link><item><title>How we built insanely good memory for grok bot (by making it a teammate instead)</title><link>https://supermemory.ai/blog/grok-bot-memory/</link><guid isPermaLink="true">https://supermemory.ai/blog/grok-bot-memory/</guid><description>Grok Bot is built around Bots working together. So for Grok Bot, we built Supermemory as a Bot. It sits in the conversation like any other teammate.</description><pubDate>Tue, 03 Nov 2026 00:00:00 GMT</pubDate><category>News</category><category>Engineering</category><author>Muskan Jain</author></item><item><title>We dug into Claude Code&apos;s memory. Here&apos;s exactly how it works</title><link>https://supermemory.ai/blog/claude-code-auto-memory/</link><guid isPermaLink="true">https://supermemory.ai/blog/claude-code-auto-memory/</guid><description>Last month, our founder Dhravya Shah broke down how Instinct&apos;s memory works. We wanted to do the same for Claude, since that&apos;s where we spend most of our day.</description><pubDate>Wed, 28 Oct 2026 00:00:00 GMT</pubDate><category>Engineering</category><author>Muskan Jain</author></item><item><title>How AI memory actually works. A beginner&apos;s guide</title><link>https://supermemory.ai/blog/how-ai-memory-works/</link><guid isPermaLink="true">https://supermemory.ai/blog/how-ai-memory-works/</guid><description>How AI apps remember things between chats, why a bigger context window doesn&apos;t solve it, and the parts every memory system shares.</description><pubDate>Fri, 09 Oct 2026 00:00:00 GMT</pubDate><category>Engineering</category><author>Muskan Jain</author></item><item><title>We&apos;re open sourcing the company brain. Here&apos;s how we designed the multiplayer harness</title><link>https://supermemory.ai/blog/open-sourcing-company-brain/</link><guid isPermaLink="true">https://supermemory.ai/blog/open-sourcing-company-brain/</guid><description>Company Brain is now open source. A walkthrough of the multiplayer harness behind its Slack experience, from proactivity and memory boundaries to approvals and recovery.</description><pubDate>Fri, 25 Sep 2026 00:00:00 GMT</pubDate><category>News</category><author>Dhravya Shah</author></item><item><title>Jev changes a lot in memory &amp; context engineering. Here&apos;s exactly how.</title><link>https://supermemory.ai/blog/jev-memory-context-engineering/</link><guid isPermaLink="true">https://supermemory.ai/blog/jev-memory-context-engineering/</guid><description>We tested Jev across reranking, chunking, observation, and harness decisions. Here is where fast decision models help memory systems, where they cost more, and where they still fall short.</description><pubDate>Thu, 24 Sep 2026 00:00:00 GMT</pubDate><category>Engineering</category><author>Dhravya Shah</author></item><item><title>I reverse-engineered Instinct&apos;s memory. Here&apos;s exactly how it works</title><link>https://supermemory.ai/blog/reverse-engineering-instinct-memory/</link><guid isPermaLink="true">https://supermemory.ai/blog/reverse-engineering-instinct-memory/</guid><description>Instinct keeps its memory as git-tracked markdown files, found with grep rather than vectors. Here is the whole system as far as black-box probing can reconstruct it, and how to rebuild it on supermemory in about 60 lines.</description><pubDate>Sun, 20 Sep 2026 00:00:00 GMT</pubDate><category>Engineering</category><author>Dhravya Shah</author></item><item><title>An update to supermemory</title><link>https://supermemory.ai/blog/an-update-to-supermemory/</link><guid isPermaLink="true">https://supermemory.ai/blog/an-update-to-supermemory/</guid><description>We&apos;ve discontinued the supermemory company brain and Nova. Everyone who was charged has been refunded, our MCP and plugins continue to run, and we&apos;re going all in on the memory engine.</description><pubDate>Thu, 10 Sep 2026 00:00:00 GMT</pubDate><category>News</category><author>Dhravya Shah</author></item><item><title>Scaling Conversations: How Adapta Grew Usage Without Losing Context</title><link>https://supermemory.ai/blog/adapta-scaling-conversations/</link><guid isPermaLink="true">https://supermemory.ai/blog/adapta-scaling-conversations/</guid><description>Adapta added Supermemory as a persistent memory layer so every conversation keeps its context — letting the team scale usage without losing the thread.</description><pubDate>Fri, 12 Jun 2026 12:00:00 GMT</pubDate><category>Case Study</category><author>Dhravya Shah</author></item><item><title>How Chatarmin Ditched RAG and Went Memory-Only with Supermemory</title><link>https://supermemory.ai/blog/chatarmin-memory-only/</link><guid isPermaLink="true">https://supermemory.ai/blog/chatarmin-memory-only/</guid><description>Chatarmin replaced a heavy RAG pipeline with Supermemory&apos;s memory layer — cutting average AI response time from 40s to 12s and token usage by 40–50%.</description><pubDate>Wed, 10 Jun 2026 12:00:00 GMT</pubDate><category>Case Study</category><author>Dhravya Shah</author></item><item><title>SMFS: making agentic retrieval 55% cheaper AND more accurate</title><link>https://supermemory.ai/blog/smfs-making-agentic-retrieval-55-cheaper-and-more-accurate/</link><guid isPermaLink="true">https://supermemory.ai/blog/smfs-making-agentic-retrieval-55-cheaper-and-more-accurate/</guid><description>We 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&apos;s tasks. Today, SMFS is used by hundreds of companies to power their agents.</description><pubDate>Thu, 28 May 2026 23:10:49 GMT</pubDate><category>Engineering</category><author>Dhravya Shah</author></item><item><title>Introducing Dynamic Dreaming: supermemory now connects the dots, for you.</title><link>https://supermemory.ai/blog/introducing-dynamic-dreaming-supermemory-now-connects-the-dots-for-you/</link><guid isPermaLink="true">https://supermemory.ai/blog/introducing-dynamic-dreaming-supermemory-now-connects-the-dots-for-you/</guid><description>Dreaming is magical. TLDR: We&apos;re launching Dynamic Dreaming in supermemory today, which automatically works if you&apos;re using supermemory in any way - API, OpenClaw, Hermes agent, etc.</description><pubDate>Mon, 25 May 2026 23:05:00 GMT</pubDate><category>Engineering</category><author>Dhravya Shah</author></item><item><title>Dear reader, we just made supermemory insanely cheap... the Context Cloud</title><link>https://supermemory.ai/blog/dear-reader-we-just-made-supermemory-insanely-cheap-the-context-cloud/</link><guid isPermaLink="true">https://supermemory.ai/blog/dear-reader-we-just-made-supermemory-insanely-cheap-the-context-cloud/</guid><description>When 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.</description><pubDate>Mon, 18 May 2026 23:16:00 GMT</pubDate><category>Engineering</category><author>Dhravya Shah</author></item><item><title>Introducing @supermemory/tools v2.0.0</title><link>https://supermemory.ai/blog/introducing-supermemory-tools-v2-0-0/</link><guid isPermaLink="true">https://supermemory.ai/blog/introducing-supermemory-tools-v2-0-0/</guid><description>Today we&apos;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.</description><pubDate>Mon, 27 Apr 2026 18:34:44 GMT</pubDate><category>Engineering</category><author>Mahesh Sanikommu</author></item><item><title>Solving the Precision-Recall Tradeoff: Search Result Aggregation</title><link>https://supermemory.ai/blog/solving-the-precision-recall-tradeoff-search-result-aggregation/</link><guid isPermaLink="true">https://supermemory.ai/blog/solving-the-precision-recall-tradeoff-search-result-aggregation/</guid><description>When you&apos;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.</description><pubDate>Sun, 05 Apr 2026 18:44:55 GMT</pubDate><category>Engineering</category><author>Soham Daga</author></item><item><title>OpenClaw Memory Problems: Why It Forgets and How to Fix It (2026)</title><link>https://supermemory.ai/blog/why-everyone-is-complaining-about-openclaws-memory-it-sucks-and-why-supermemory-fixes-it/</link><guid isPermaLink="true">https://supermemory.ai/blog/why-everyone-is-complaining-about-openclaws-memory-it-sucks-and-why-supermemory-fixes-it/</guid><description>OpenClaw remembers by writing Markdown files in its workspace, so it forgets anything the agent didn&apos;t save. Why that breaks down, how the supermemory plugin recalls and saves on every turn instead, and how to install it, free on every plan.</description><pubDate>Thu, 19 Feb 2026 05:02:16 GMT</pubDate><category>Engineering</category><author>Dhravya Shah</author></item><item><title>Stateful Coding Agents with Memory: Build Long-Running Agents (2026)</title><link>https://supermemory.ai/blog/infinitely-running-stateful-coding-agents/</link><guid isPermaLink="true">https://supermemory.ai/blog/infinitely-running-stateful-coding-agents/</guid><description>We 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.</description><pubDate>Wed, 18 Feb 2026 05:03:14 GMT</pubDate><category>Engineering</category><author>Shoubhit</author></item><item><title>Clawd / Molt bot&apos;s memory SUCKS. We gave it supermemory.</title><link>https://supermemory.ai/blog/clawd-molt-bots-memory-sucks-we-gave-it-supermemory/</link><guid isPermaLink="true">https://supermemory.ai/blog/clawd-molt-bots-memory-sucks-we-gave-it-supermemory/</guid><description>I&apos;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.</description><pubDate>Wed, 28 Jan 2026 00:53:10 GMT</pubDate><category>Engineering</category><author>Dhravya Shah</author></item><item><title>Catch up with our UNFORGETTABLE Launch Week</title><link>https://supermemory.ai/blog/catch-up-with-our-unforgettable-launch-week/</link><guid isPermaLink="true">https://supermemory.ai/blog/catch-up-with-our-unforgettable-launch-week/</guid><description>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.</description><pubDate>Sun, 04 Jan 2026 00:17:07 GMT</pubDate><category>News</category><author>Shardul Mane</author></item><item><title>Empowering the Next Generation of Founders: Supermemory Startup Program</title><link>https://supermemory.ai/blog/empowering-the-next-generation-of-founders-supermemory-startup-program/</link><guid isPermaLink="true">https://supermemory.ai/blog/empowering-the-next-generation-of-founders-supermemory-startup-program/</guid><description>If there’s one thing we’ve learned while building Supermemory, it’s that most startups don’t fail because they didn&apos;t build features; they fail when infrastructure slows them down, or they built too slow.</description><pubDate>Wed, 31 Dec 2025 08:44:26 GMT</pubDate><category>News</category><author>Shardul Mane</author></item><item><title>Building code-chunk: AST Aware Code Chunking</title><link>https://supermemory.ai/blog/building-code-chunk-ast-aware-code-chunking/</link><guid isPermaLink="true">https://supermemory.ai/blog/building-code-chunk-ast-aware-code-chunking/</guid><description>At Supermemory, we&apos;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.</description><pubDate>Mon, 29 Dec 2025 20:45:44 GMT</pubDate><category>Engineering</category><author>Shoubhit</author></item><item><title>Supermemory raises $3 million with the best memory engine for LLMs</title><link>https://supermemory.ai/blog/supermemory-raises-3-million-and-building-the-best-memory-engine-for-llms/</link><guid isPermaLink="true">https://supermemory.ai/blog/supermemory-raises-3-million-and-building-the-best-memory-engine-for-llms/</guid><description>Today, 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.</description><pubDate>Mon, 06 Oct 2025 16:35:17 GMT</pubDate><category>News</category><author>Dhravya Shah</author></item><item><title>Mem0 vs Supermemory: Why Scira Switched</title><link>https://supermemory.ai/blog/why-scira-ai-switched/</link><guid isPermaLink="true">https://supermemory.ai/blog/why-scira-ai-switched/</guid><description>Scira AI moved its production memory layer from Mem0 to Supermemory. This is what failed, what improved, and how the team evaluated the two systems.</description><pubDate>Thu, 02 Oct 2025 04:02:38 GMT</pubDate><category>Case Study</category><author>Dhravya Shah</author></item><item><title>Never Record Again: How Montra Uses Supermemory to Rethink Video Creation</title><link>https://supermemory.ai/blog/never-record-again-how-montra-uses-supermemory-to-rethink-video-creation/</link><guid isPermaLink="true">https://supermemory.ai/blog/never-record-again-how-montra-uses-supermemory-to-rethink-video-creation/</guid><description>Campbell Baron, the founder of Montra, has been making videos since he was twelve. By thirteen, he was already doing brand work. Today, he’s betting on a very different future for creators: a world where recording is the exception, and most videos are generated from scratch.</description><pubDate>Thu, 21 Aug 2025 15:38:25 GMT</pubDate><category>Case Study</category><author>Naman Bansal</author></item><item><title>Unified Memory That Works Where You Work: Your Second Brain With Supermemory</title><link>https://supermemory.ai/blog/unified-memory-that-works-where-you-work-your-second-brain-with-supermemory/</link><guid isPermaLink="true">https://supermemory.ai/blog/unified-memory-that-works-where-you-work-your-second-brain-with-supermemory/</guid><description>Hi 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.</description><pubDate>Fri, 25 Jul 2025 17:16:18 GMT</pubDate><category>Engineering</category><author>Dhravya Shah</author></item><item><title>Supermemory just got faster on PlanetScale</title><link>https://supermemory.ai/blog/supermemory-just-got-faster-on-planetscale/</link><guid isPermaLink="true">https://supermemory.ai/blog/supermemory-just-got-faster-on-planetscale/</guid><description>What is Supermemory? Supermemory completes the missing part of the LLM puzzle: memory. Just as memory is crucial for human intelligence, it&apos;s essential for truly intelligent AI systems.</description><pubDate>Fri, 18 Jul 2025 18:38:14 GMT</pubDate><category>Engineering</category><author>Dhravya Shah</author></item><item><title>Faster, smarter, reliable infinite chat: Supermemory IS context engineering.</title><link>https://supermemory.ai/blog/faster-smarter-reliable-infinite-chat-supermemory-is-context-engineering/</link><guid isPermaLink="true">https://supermemory.ai/blog/faster-smarter-reliable-infinite-chat-supermemory-is-context-engineering/</guid><description>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.</description><pubDate>Wed, 09 Jul 2025 07:13:42 GMT</pubDate><category>News</category><author>Dhravya Shah</author></item><item><title>We solved AI API interoperability</title><link>https://supermemory.ai/blog/we-solved-ai-api-interoperability/</link><guid isPermaLink="true">https://supermemory.ai/blog/we-solved-ai-api-interoperability/</guid><description>One 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 Infinite Chat API, initially, we only supported the OpenAI format. This was fine, until a lot of our customers started asking for more.</description><pubDate>Mon, 07 Jul 2025 02:35:52 GMT</pubDate><category>Engineering</category><author>Alex Foster</author></item><item><title>The Wow Factor of Memory - How Flow Used Supermemory To Build Smarter, Stickier Products</title><link>https://supermemory.ai/blog/the-wow-factor-of-memory-how-flow-used-supermemory-to-build-smarter-stickier-products/</link><guid isPermaLink="true">https://supermemory.ai/blog/the-wow-factor-of-memory-how-flow-used-supermemory-to-build-smarter-stickier-products/</guid><description>Overview: Flow is a note-taking app built around a bold vision: to create a more personal, context-aware writing experience powered by AI. At the heart of this mission is memory.</description><pubDate>Sat, 14 Jun 2025 20:50:54 GMT</pubDate><category>Case Study</category><author>Dhravya Shah</author></item><item><title>The UX and technicalities of awesome MCPs</title><link>https://supermemory.ai/blog/the-ux-and-technicalities-of-awesome-mcps/</link><guid isPermaLink="true">https://supermemory.ai/blog/the-ux-and-technicalities-of-awesome-mcps/</guid><description>Last 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.</description><pubDate>Sun, 08 Jun 2025 05:13:09 GMT</pubDate><category>Engineering</category><author>Dhravya Shah</author></item><item><title>Architecting a memory engine inspired by the human brain</title><link>https://supermemory.ai/blog/memory-engine/</link><guid isPermaLink="true">https://supermemory.ai/blog/memory-engine/</guid><description>Language 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.</description><pubDate>Thu, 05 Jun 2025 19:20:31 GMT</pubDate><category>Engineering</category><author>Dhravya Shah</author></item></channel></rss>