[Blog](https://supermemory.ai/blog) · [News](https://supermemory.ai/blog/tag/news)

# Faster, smarter, reliable infinite chat: Supermemory IS context engineering.

By Dhravya Shah July 9, 2025 · 3 min read 

![Supermemory header reading "Infinite Chat brings context into the conversation" — Overlapping conversation cards bring an earlier message into the current exchange](https://supermemory.ai/_astro/cover.Bpe-exyo_1fuUGp.webp)

People are obsessed with prompts and prompt engineering. Sure, what you say is important, but _what the model know_s 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. Karpathy’s viral tweet called it out:

X content is paused until you allow embedded content.

[Open on X ↗](https://twitter.com/karpathy/status/1937902205765607626?ref%5Fsrc=twsrc%5Etfw)

> <https://twitter.com/karpathy/status/1937902205765607626>

We thought to ourselves: our current infinite chat _is_ context engineering! However, it had its fair share of issues. It didn’t work with all AI providers like Gemini and Anthropic, couldn’t support multi-modal memory, didn’t have tool call support, and more.

So, we fixed it.

With today’s release, our **Infinite Chat** becomes a full-blown context engineering engine.

The TL;DR is: it’s faster, smarter, and more reliable.

Here’s everything that’s new:

* Multi-modal memory support (images, audio, structured data, etc.)
* Works with all LLMs like Gemini and Anthropic, not just OpenAI.
* Tool calls awareness and memory
* Higher context limits
* Long-context RAG
* Implicit few-shot learning
* Smarter summarization and pruning to avoid context pollution
* A new architecture for better reliability and response quality

![Venn diagram: Context Engineering enclosing RAG, Prompt Engineering, State/History, Memory, and Structured Outputs](https://supermemory.ai/_astro/image-1.To4TL5X__22PYyG.webp)

Source

## Multi-step agent support

Agents are a bit messy. Sometimes, they stop mid-task and need to pick up where they left off, without getting confused or forgetting everything.

Say you're building a coding co-pilot. You tell it: “Edit 100 files and add 1 new feature.”

It gets through 50, then the call times out or the model hits a limit. Now what? All 50 interactions would be polluting the context.

Our new infrastructure solves it.

If you provide the conversation-id, Infinite Chat removes the unnecessary context and automatically backfills it, making the network requests much faster, even on extremely long contexts:

```
// if you provide conversation ID, You do not need to send all the messages every single time. Supermemory automatically backfills it. 
const client = new OpenAI({
    baseURL:
"https://api.supermemory.ai/v3/https://api.openai.com/v1",
    defaultHeaders: {
        "x-supermemory-api-key":
            "",
        "x-sm-user-id": `dhravya`,
        "x-sm-conversation-id": "conversation-id"
    },
})

const messages = [
{"role" : "user", "text": "SOme long thing"},
// .... 50 other messages
{"role" : "user", "text": "new message"},
]

const client.generateText(messages)

// Next time, you dont need to send more.
const messages2 = [{"role" : "user", "text": "What did we talk about in this conversation, and the one we did last year?"}]

const client.generateText(messages2)
```

That includes:

* A summary of what was done. For instance, “50 files were changed to add feature XYZ.”
* A diff of what’s pending: “These 12 are still left.”
* And even implicit few-shot grounding from earlier turns: “Here’s how you’ve answered similar requests before.”

It’s also cheaper, cleaner, and easier to reason about than long chat dumps.

## Works with all LLM providers

Initially, Infinite Chat only supported the OpenAI API format. But, our customers asked for more - Gemini, Anthropic, Langchain, AI SDK, etc.

It was a pain in the ass to implement a system with multiple different providers, each provider having different ways to do multi-modal, tool call chains, calculating token counts, etc. for all their different models.

So, [we built llm-bridge](https://supermemory.ai/blog/we-solved-ai-api-interoperability/), an open-source package, to solve this issue, and used it in Infinite Chat. This makes adoption seamless: all you have to do as a developer is prepend your provider's base URL with our API's URL, add your Supermemory API key, and we take care of the rest. That is, there is no change to the client interface. You can keep using your SDK of choice no matter what!

```
const client = new OpenAI({
    baseURL:
"https://api.supermemory.ai/v3/https://api.openai.com/v1",
    defaultHeaders: {
        "x-supermemory-api-key":
            "",
        "x-sm-user-id": `dhravya`,
    },
})
/// or new Anthropic() or new GoogleGenAI()
```

Read about it in more detail [here.](https://supermemory.ai/blog/we-solved-ai-api-interoperability/)

## Smarter Memory Management

Beyond simple message history, the new Infinite Chat lets your models remember more than just words and do more with them.

This includes:

* **Multimodal memory:** Images, audio, structured data, etc. Anything your agent sees can now persist across calls. A screenshot sent two messages ago? Still in context. A chart from last week? Still referenced.
* **Tool call tracking:** We store tool invocations and outputs as first-class context objects. The model knows what tools it has used, what the results were, and doesn’t blindly repeat actions.
* **Long-context RAG:** Instead of stuffing 10 retrieved passages into every prompt, Supermemory now decides what’s already been seen, summarizes it when needed, and surfaces _only_ new or relevant chunks.

In essence, we’ve taken Karpathy’s point seriously:

_"Context engineering is the delicate art and science of filling the context window with just the right information for the next step."_

What you really want is:

* Just enough memory to make the next decision smart
* Just enough pruning to keep token usage efficient
* Just enough scaffolding to avoid re-teaching the model what it already knows

That’s what the new Infinite Chat does.

[Take it out for a spin today!](https://supermemory.ai/docs/model-enhancement/context-extender)

## Other posts.

1. [We're open sourcing the company brain. Here's how we designed the multiplayer harness 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. NewsSep 25, 2026 ](https://supermemory.ai/blog/open-sourcing-company-brain)
2. [Jev changes a lot in memory & context engineering. Here's exactly how. 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. EngineeringSep 24, 2026 ](https://supermemory.ai/blog/jev-memory-context-engineering)
3. [I reverse-engineered Instinct's memory. Here's exactly how it works 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. EngineeringSep 20, 2026 ](https://supermemory.ai/blog/reverse-engineering-instinct-memory)
4. [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. NewsSep 10, 2026 ](https://supermemory.ai/blog/an-update-to-supermemory)
5. [Scaling Conversations: How Adapta Grew Usage Without Losing Context Adapta added Supermemory as a persistent memory layer so every conversation keeps its context — letting the team scale usage without losing the thread. Case StudyJun 12, 2026 ](https://supermemory.ai/blog/adapta-scaling-conversations)
6. [How Chatarmin Ditched RAG and Went Memory-Only with Supermemory Chatarmin replaced a heavy RAG pipeline with Supermemory's memory layer — cutting average AI response time from 40s to 12s and token usage by 40–50%. Case StudyJun 10, 2026 ](https://supermemory.ai/blog/chatarmin-memory-only)
7. [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. EngineeringMay 28, 2026 ](https://supermemory.ai/blog/smfs-making-agentic-retrieval-55-cheaper-and-more-accurate)
8. [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. EngineeringMay 25, 2026 ](https://supermemory.ai/blog/introducing-dynamic-dreaming-supermemory-now-connects-the-dots-for-you)
9. [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. EngineeringMay 18, 2026 ](https://supermemory.ai/blog/dear-reader-we-just-made-supermemory-insanely-cheap-the-context-cloud)
10. [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. EngineeringApr 27, 2026 ](https://supermemory.ai/blog/introducing-supermemory-tools-v2-0-0)
11. [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. EngineeringApr 5, 2026 ](https://supermemory.ai/blog/solving-the-precision-recall-tradeoff-search-result-aggregation)
12. [OpenClaw Memory Problems: Why It Forgets and How to Fix It (2026) 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. EngineeringFeb 19, 2026 ](https://supermemory.ai/blog/why-everyone-is-complaining-about-openclaws-memory-it-sucks-and-why-supermemory-fixes-it)
13. [Stateful Coding Agents with Memory: Build Long-Running Agents (2026) 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. EngineeringFeb 18, 2026 ](https://supermemory.ai/blog/infinitely-running-stateful-coding-agents)
14. [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. EngineeringJan 28, 2026 ](https://supermemory.ai/blog/clawd-molt-bots-memory-sucks-we-gave-it-supermemory)
15. [Catch up with our UNFORGETTABLE Launch Week 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. NewsJan 4, 2026 ](https://supermemory.ai/blog/catch-up-with-our-unforgettable-launch-week)
16. [Empowering the Next Generation of Founders: Supermemory Startup Program If 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. NewsDec 31, 2025 ](https://supermemory.ai/blog/empowering-the-next-generation-of-founders-supermemory-startup-program)
17. [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. EngineeringDec 29, 2025 ](https://supermemory.ai/blog/building-code-chunk-ast-aware-code-chunking)
18. [Supermemory raises $3 million with the best memory engine for LLMs 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. NewsOct 6, 2025 ](https://supermemory.ai/blog/supermemory-raises-3-million-and-building-the-best-memory-engine-for-llms)
19. [Mem0 vs Supermemory: Why Scira Switched 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. Case StudyOct 2, 2025 ](https://supermemory.ai/blog/why-scira-ai-switched)
20. [Never Record Again: How Montra Uses Supermemory to Rethink Video Creation 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. Case StudyAug 21, 2025 ](https://supermemory.ai/blog/never-record-again-how-montra-uses-supermemory-to-rethink-video-creation)
21. [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. EngineeringJul 25, 2025 ](https://supermemory.ai/blog/unified-memory-that-works-where-you-work-your-second-brain-with-supermemory)
22. [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. EngineeringJul 18, 2025 ](https://supermemory.ai/blog/supermemory-just-got-faster-on-planetscale)
23. [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 Infinite Chat API, initially, we only supported the OpenAI format. This was fine, until a lot of our customers started asking for more. EngineeringJul 7, 2025 ](https://supermemory.ai/blog/we-solved-ai-api-interoperability)
24. [The Wow Factor of Memory - How Flow Used Supermemory To Build Smarter, Stickier Products 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. Case StudyJun 14, 2025 ](https://supermemory.ai/blog/the-wow-factor-of-memory-how-flow-used-supermemory-to-build-smarter-stickier-products)
25. [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. EngineeringJun 8, 2025 ](https://supermemory.ai/blog/the-ux-and-technicalities-of-awesome-mcps)
26. [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. EngineeringJun 5, 2025 ](https://supermemory.ai/blog/memory-engine)

## Start building with supermemory.

Memory and continual learning for any model, any harness. Available through our API, plugins, and MCP.

[Build with supermemory ](https://console.supermemory.ai/)