grok @bot got lot more personalised now my ∗ grok bot (for work) ∗ hermes (for personal) ∗ cursor, cc, codex (for coding) can stay in sync on what's going on 24/7 in my life built quick grok bot template with @supermemory, give a try 👇 🔗

AI memory is more than embed and search, doing retrieval well means solving a lot of hard problems stacked underneath. that's how @supermemory's architechture is built: a single engine with vector, keyword and graph search, plus a model that figures out what to keep and what to drop. full breakdown ↓

For everyone asking, > computer: @orgo > sandbox: @vercel > cards: @agentcardhq > email: @agentmail > imessage: @PhotonHQ > memory: @supermemory > connectors: @composio With one MCP you can give your agents access to all of the above... free for some time Enjoy

Why doesn't a bigger context window just solve memory? @sohamdaga22 explains why that intuition breaks: the problem was never storing everything, it's knowing what to store and what to forget. watch the full clip →

im looking to partner with youtubers in the ai space for @supermemory if you make videos on agents, dev tools or educational stuff, i'd genuinely love to work with you. and if there's an ai creator you admire, tag them here, i'd be glad to reach out

Hermes agent is pretty cool when it comes to AI memory. @supermemory can be used with the @NousResearch Hermes agent and store your agentic sessions, facts, preferences and other memories. Check it out:

so far i think our claude code plugin sucked. now it is magical it was not very clear when it was being helpful it felt like it's kinda ruining the context It's highly loved and recepted, we have thousands of people using the claude code plugin every day, with many stars on Github. Really wanted to make it good. I sat on it for an entire day and tried to figure out every single way to deliver the value with our plugins. and I think we finally have an answer now: 1. Showing the value, somehow... Because we can't control the UI in claude code, we figured out many different ways to show when supermemory is being useful in the session. Now, supermemory will show it's value, in: - User prompt submit - Statusline - Inline, with the ◪ icon. So when you see ◪, you know supermemory is doing it's magic. It also shows the number of tokens injected, so you can be confident about pollution. 2. Great memories Coding memories are different, and honestly, the learnings that the older version was doing were not being helpful. It would remember very arbitary stuff like "The user used git push" (yeah that's terrible. 🤮). We have updated both the engine and more harness level changes to make sure that the learnings are great for coding as well. Now, we try to infer the source of truth for some things, so if something is obvious in the code (this is a typescript project), there doesn't need to be any memories for it. The memories should be your behaviours, preferences and other things. We do this through profile buckets and entityContext in supermemory. 3. Experience and observability Ok. So the memories are good. But how do you bring it back into the harness? We have both hooks and tools, and the tools are now served via a local MCP, that the agent uses pretty decently often now. This is to gather additional context. how do we show it to people? Now, the claude code plugin (and other plugin) transcripts and learnings show up in the supermemory app in the agents tab. Here, you can see the full graph of what is learnt, inferred, and how supermemory is learning over time. in a beautiful way, so you can observe and make sure that supermemory is doing it's job right! 4. Failures and when things go wrong. This is one more thing that I really really care about. While testing the plugin, I happened to be in an airplane with really slow internet. Seeing that supermemory was making the agent feel slow as well (since it's a network call before it starts answering), the plugin now guarantee takes less than 500ms (or else it is skipped) and all errors are failed open. This means that even if supermemory fails your work will not be affected. One more thing that was concerning me was honestly the token count. How many tokens is supermemory injecting? is it polluting the context? Now we clearly show the token count so you can be sure it's doing good. More often than not, it will always be less than 100 tokens. 5. Feeling the difference As I was showing this to my friends after feeling the magic myself, a common question was "How is it different from claude code's default memory?". Yes, the memories work cross-harness. That's one plus. But that's not it. If you open the "Auto-memories" folder in claude, you'll notice that it barely learns anything. Things are only learnt if you are visibly angry or direct about "Don't do this". Then, it creates a file with "When doing this, do XYZ" or "Avoid XYZ" There's barely 10 files in my repo, which I've been working on for more than 2 years now and using claude code since last 8 months. There are also a lot of outdated ones that are no longer even necessary. In order to use these memories, claude has to load the whole files automatically, which it never does... Supermemory learns and captures even the small implicit details about how you would want the agent to behave, and they are always fresh, since forgetfulness is built in. It is also used and picked up by the agent, automatically. you should REALLY try our new claude code plugin. Really proud of the entire team's work in making this amazing. these changes are coming to other plugins soon

I genuinely think every agent should use @supermemory It's dead cheap and will probably decrease your total cost You can configure it for personalization, self improvement, both. whatever you wanna do You can self host it

When using @supermemory with any agent, it really feels like I'm training the model to do certain things better in real time. eg: the series in which i want it to run tool calls. literally feels so cool

we're finally launching the @supermemory ambassador program! we're bringing on 3-4 ambassadors, who we want: ~ you make technical content and ship projects ~ you know your way around social media comment or dm me your proof of work: a project you've shipped, your best technical post, and your x & github.

We just shipped the supermemory showcase. Coding agents, voice assistants, sales tools, games, research bots, personal apps, all built on supermemory, all in one place. Made something on @supermemory? drop your project and we'll feature it ↓