Comment by jedberg
12 hours ago
There is a lot of competition in this space, both commercial companies and open source. It seems like the biggest advantage for using one of these and not Claude or Codex is that you can use multiple models. Otherwise, those two have all the same features, or probably will in the next week.
Are you able to use multiple models? Or I guess the first question is, what model(s) are you using? At this point, many enterprises care so that should be front and center, especially if you're using models hosted in China, because a lot of non-Chinese companies care about that.
You mention some things about unique ways to store memory. Do you have any data or use cases on how that improves performance? If you do, you should get those on your website too.
I'm not sure you have a very strong answer to "Why not just run Claude or Codex on my laptop?" Sure, you provide compute, but so do they, and most enterprises and even regular people are getting desktops/droplets to run their agents now because of this problem. This is kind of solved already.
Also there is a small nit with your website. The graphic next to "Proactively gets things done for you" gets bigger and smaller, so if you're trying to read anything below that, it keeps jumping up and down.
Currently we don't allow for multiple model selection, but it is on the roadmap. We do have a cli, which allows you to use the wiki layer and the tools in whatever harness you prefer. Further, we want to allow users to also bring their own keys/subscription.
We do not have formal benchmarks to measure improvement in performance. A big reason is that most benchmarks are very "atomic facts memory" focused. They'd give a huge passage, conversations, and see which memory system could surface those facts. How we're different is agents could be simply given the markdown files, and they can pretty much get the perfect context themselves. Second, we are banking more on the fact that having this layer enables new capabilities of the models
> Currently we don't allow for multiple model selection, but it is on the roadmap.
Cool! What model does it use now? Enterprises will definitely want to know.
And the other big question: Why not just use Claude or Codex (via CLI on a desktop or droplet)?
Its GPT-5.6-terra under the hood. Also we want to control the harness. Features like proactivity/long tasks are not possible the way Claude/Codex work today. We do plan on releasing our desktop app, which would have these things inbuilt.