All articles
TAG

Engineering

Engineering deep-dives from the Supermemory team: how we build memory infrastructure for AI agents — retrieval, embeddings, the memory graph, and performance.

17 posts

Banner with white serif text "smfs. | eval" over a painted classical landscape of Greek temples and columns
Engineering ·

SMFS: making agentic retrieval 55% cheaper AND more accurate

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's tasks. Today, SMFS is used by hundreds of companies to power their agents. TLDR: You can rea

Dhravya Shah 4 min read
Blue pixel-art illustration of a classical bust with an exposed brain beside an open book under the Supermemory logo
Engineering ·

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. We (humans) dream to condense and reflect on our thoughts, not only things that happened today, but a weird blend o

Dhravya Shah 4 min read
Banner titled "Context infrastructure for your agents" with four cards: Memory, SuperRAG, Search and Traversal, Operations
Engineering ·

Dear reader, we just made supermemory insanely cheap... the Context Cloud

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. Memory, Retrieval, Profiles, reranking, embedd

Dhravya Shah 3 min read
Blog cover banner reading "Introducing @supermemory/tools v2.0.0" beside an open box bursting with code and gear icons
Engineering ·

Introducing @supermemory/tools v2.0.0

Today 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. What's new in v2.0.0: * Unified config-object API * customId: required conversation

Mahesh Sanikommu 5 min read
Banner on black with "supermemory x HERMES-AGENT" and the tagline "give your agents Memory it deserves"
Engineering ·

supermemory will make your Hermes-agent crazy powerful

Today, 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. It meets yo

Mahesh Sanikommu 6 min read
Supermemory banner with "reranking" struck through above "aggregation," beside a blue robotic arm and chip
Engineering ·

Solving the Precision-Recall Tradeoff: Search Result Aggregation

When 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. Once the request hits the server, a resp

Soham Daga 3 min read
Supermemory banner reading "#1 in agent memory. Broke the frontier. Introducing ASMR" with two near-equal score bars
Engineering ·

We broke the frontier in agent memory: To prove a point.

Read the follow up here! https://x.com/DhravyaShah/status/2036243995500966260?s=20 TLDR: This was a big social experiment that we did to create a new standard for reporting memory system’s quality. It was a parody. A few months ago, we published our first research report showing Supermemory achi

Dhravya Shah 5 min read
Blue banner reading "supermemory x opencode" above many small arrows converging upward into a dense formation
Engineering ·

Infinitely running stateful coding agents

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. Here's how it works, in the order you'll

Shoubhit 5 min read
Dark red banner reading "We built better memory for OpenClaw" with bars showing Supermemory 85.87% vs OpenClaw 58.33% on LongMemEval
Engineering ·

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. BENCH

Dhravya Shah 4 min read
Orange banner pairing the Claude Code and Supermemory logos with the caption "stateful coding agents"
Engineering ·

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... Every day, I have to explain the

Dhravya Shah 4 min read
Banner with the white Supermemory logo, an x, and a red cartoon lobster on a dark blue gradient
Engineering ·

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. However, me and some other fri

Dhravya Shah 2 min read
Supermemory blog banner reading "building the best way to chunk code" beside stacked blue glass token cards
Engineering ·

Building code-chunk: AST Aware Code Chunking

At 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. It's now the best A

Shoubhit 8 min read
Supermemory banner reading "Unified Memory That Works Wherever You Work" with a laptop and phone linked to a hub device
Engineering ·

Unified Memory That Works Where You Work: Your Second Brain With Supermemory

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.  Anyways, when I started Supermemory one year ago, we were a consumer app that acted like a second

Dhravya Shah 5 min read
Banner reading "Supermemory Is Now Faster With PlanetScale" with a lightning bolt and PlanetScale logos
Engineering ·

Supermemory just got faster on PlanetScale

What 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. We've built a portable memory engine that works seamlessly across different LLMs through multiple interfaces, inc

Dhravya Shah 2 min read
Blog banner reading "We Solved LLM Proxies" with a blue 3D human head bust on a pedestal and Supermemory logo
Engineering ·

We solved AI API interoperability

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 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. Skip to

Alex Foster 7 min read
Supermemory blog banner reading "The UX And Tech of Memory MCP" with a rising row of blue 3D cubes
Engineering ·

The UX and technicalities of awesome MCPs

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. Seems like people absolutely loved

Dhravya Shah 8 min read
Supermemory banner reading "Architecting A Memory Engine" with a glossy blue brain icon between the words
Engineering ·

Architecting a memory engine inspired by the human brain

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. Every leap in context window s

Dhravya Shah 5 min read