davidvgilmore

For those that have capable enough hardware, it's effectively free to run subtasks on-device. (just the marginal cost of additional electricity).

With Google's most recent 12b param Gemma model, even Mac users with just 16gb of unified memory can offload some tasks on-device.

Many of them are produced by Chinese labs. Some, like Neomotron, are U.S. made. And we support inference providers in both the U.S. and overseas.

If geography is important, we can restrict which geos inference takes place in. And if you don't want to use Chinese-trained models, you can use others like Mistral, Neomotron, Google's, or OpenAI's.

Four ways: (1) We are built specifically for Claude Code model routing. (2) We route at a subagent/subtask level. (3) We support on-device routing. (4) We have a built-in ML router trained specifically to route Claude Code subagent tasks. Its use is optional.

Yes - in short, open models like Deepseek, Mimo, Kimi, and GLM tend to complete tasks with less tokens and cost less per token than both Sonnet and Haiku. So those models are more cost efficient, and we often think of that as them having higher "capability-per-dollar" than Sonnet or Haiku.

Much of Claude Code's internal model routing ends up delegating tasks to Sonnet or Haiku, so by intercepting those calls and using open models instead, we often see better performance at a better price.

Your comment is fair. I don't love vibe coding as a category name. And somehow using vibe coding to describe something whose namesake, the Memex, had such virtuous ambitions feels cheap. But I ALSO want people to understand what our product does.

I want to make something that truly empowers people. Many of our users are tech savvy, but not coders. We decided to make a GUI because it allowed them to one-click install.

And we are closed source freemium right now because we're trying to find a revenue model that we can sustain ourselves with without being wholly dependent on VCs. We plan to open source components of Memex so it's more extensible in the future and to give back.

We were never going to have something that is worthy of the name memex on the first release. But our ambition is that with time and hard work, we have a chance.

Memex makes it easy to ideate, research, and build projects without writing a line of code. It's a fully chat based interface (not an IDE). Its GUI allows you to visualize data inline, perform deep research-esque queries, and create + run programs. It supports any programming language / tech stack that LLMs "know". It also comes with pre-built templates that allow you go from 0-60 on your project quickly.

HN Community: We had this clause in our Terms and Conditions: "you will not (and will not enable others to) use the AI Features: (e) for the development of any service or other offering that competes with or replicates the Services.”

That clause was boilerplate our lawyers included, and it doesn't reflect how we operate or what we intend to enforce. I should have caught it, but I missed it.

The terms and conditions are now updated to not include a anti-competition clause.

HN Community:

We had this clause in our Terms and Conditions: "you will not (and will not enable others to) use the AI Features: (e) for the development of any service or other offering that competes with or replicates the Services.”

That clause was boilerplate our lawyers included, and it doesn't reflect how we operate or what we intend to enforce. I should have caught it, but I missed it.

The terms and conditions are now updated to not include a anti-competition clause.

thanks!

Fair

That's fair. We do plan to open source components of Memex to allow for extensibility while also having a strong enough revenue model to build without being fully dependent on VCs

That's a good feature idea and something we've considered but not gotten around to yet.

We do have a secrets mgmt feature that uses keyring, so you can store secrets through the app in your system keychain, which then requires your approval before Memex uses it.

We're hoping to make that feature easier to use with MCP

I suppose you copy and paste this for each startup launch you see?

Hi @thro1 - this is my first post to the HN community. Memex is something I and my cofounders have worked hard on. While I expected some trolling, your comment is just baffling.

To anyone reading this exchange: I wrote the Show HN attempting to be as clear and to the point as possible according to the "Show HN" guidelines. And everything I wrote is factual. It's available for free for you to try yourself on our website.

in this context, not opionionated == you can use it to build with Rails, FastAPI, Firebase, python + modal ... whatever tech stack you want to use. Some will work better than others just due to the nature of the LLMs.

We've heard loud and clear from the HN community that bringing your own key is important, and we're going to fix that.

Regarding multiple models -- that's next up in the roadmap. We're a small team - we were three and just had two more join recently. So we decided to add checkpoints / shadow git repo before adding multiple model support.

(p.s. sorry this comment got buried!)

Honestly I hear you on this one. But the market has really taken up "vibe coding", so it's been the easiest way to clearly communicate to people what Memex does.

thanks - yeah, we've heard this feedback loud and clear from the HN community.

We're cooking

thanks - yeah, we've heard this feedback loud and clear from the HN community.

We're cooking

In general, we can't see what users are doing. But we can see some things like that they upgrade to new releases. We only site users @ logos that are using it on a consistent basis

we can't see their activity other than that they have accounts and have used it.

In the case of Google, we've had folks from both PM & engineering. We've talked with our PM user who has been using for prototyping.

thanks for calling this out

To be 100% clear: we do not prevent anyone from using Memex to build a Memex competitor. That clause was boilerplate our lawyers included, and it doesn't reflect how we operate or what we intend to enforce. I should have caught it and we'll fix it.

On the Usage Data side, your code is never stored anywhere other than your machine when you use Memex. And you can enable "Privacy mode" to not have your prompts stored either.

thanks - great feedback

on (1) re: multi tasking ... that's a known UX limitation. You can "command+click" the logo in the top left to open a new window, then just keep the convos open. That's the way to multi-task with it today. We definitely want to clean this up in a future version.

(2) noted - yeah, a global git diff is a good feature request

on (3) in the settings (wrench icon) there's a toggle for "Manual" code execution. To be clear - you also want to be able to approve file edits, not just command execution?

(4) doh - that's a good point

(5) we actually run a shadow git repo that commits on every turn the agent takes. It's aware of your .gitignore too. We only expose checkpoints on user messages right now, but we're planning on doing more on this front.

Our namesake is Vannevar Bush's "Memex": https://www.theatlantic.com/magazine/archive/1945/07/as-we-m...

We like the ethos of peaceful scientific progress.

And we're most passionate about advancing technological progress, which is what the original Memex aimed to do by increasing scientists' productivity.

Our Memex is a small contribution to technological progress, but it's one I am at least proud to make

We have users at Google that use Memex

You can use it for paid apps, open source apps. Whatever you want. Everything you create with Memex is 100% yours.

That clause is only meant to keep people from reselling our app, Memex, itself. But I agree it's super confusingly written and we're going to fix that.

The main difference is that Memex isn't an IDE. It's a chat-based, full agentic coding experience. You can see the code it creates, but you can't edit it (yet).

It's not for everyone, but as agentic coding gets better we expect it will become a more common usage pattern.

Thank you! Yes - there are definitely limitations. We are bullish on models getting better and we're hoping to add features that make it easier for folks to do more.

Looking forward to your feedback!

well, maybe not a full clone (yet). But it can one-shot Tauri apps pretty well :)

That's probably fair. My only defense is that we are on a shoestring budget and I'm not a designer ...

I admit our branding isn't great. But heck - we pivoted twice in 18 months on just a pre-seed and still have half our cash left.

Hopefully we'll be able to grow and afford a better logo later :)

helpful context.

yeah - we want to get the BYOK support to be self-service but we just prioritized other things based on user feedback.

thanks again for the context.