Jul 9, 2026 · 49 min · 15 segments
On episode 92 of o11ycast, Ray Myers joins Ken and Jess to explore how observability, reliability engineering, and formal software engineering practices are becoming even more important as AI coding…
Ray MyersGuest
Jessica KerrHostKen RimpelHost
I would still describe it as the leading open source coding agent by a few measures.
But when it started, it was kind of the premier open source coding agent that was, uh, actually gonna feature complete, and now the ecosystem has grown.
As I see it, the mission of there being open source coding agents is so successful that you got a lot of neat options to choose from now.
But, um, yeah, when I, when I got started, you know, and that was my motivation, it was kind of in doubt whether that was even going to be a thing, whether they would be competitive.
Uh, that the open source options are competitive with the proprietary ones, that is absolutely true of coding agents, yes.
If we're going to talk about models, which are, you know, a, uh, a component of agents, then it's a little bit of a different story how competitive the open weight models are to the proprietary ones month to month.
So you can use proprietary models with open source agents, and you can use, uh, no, I guess you can't use, um, your own models with proprietary coding agents?
That's kind of a product choice, but what is usually the case is they will want to be in control of which, uh, models you use.
Uh, there are some proprietary coding agents, I think, that, uh, you know, mix in o- open weight agents, so I don't wanna draw a gross generalization.
But also one of the things you can do with OpenHands and other open source coding agencies is if the person has sufficient hardware at their disposal, they could run local LLMs too, right? So-
... do you find that a lot of the people using OpenHands are using, you know, big GPUs on their computers and running things locally more 'cause they want that full control over where their data moves back and forth and, and just to have it run locally?
I found that the open source element comes into play much more even than I expected at the enterprise level as well because e- enterprises like control.
Oftentimes they may be doing some local hosting as, as you kind of describe it now, or they might be using some offering that allows them to host a, a bigger model within their walls, but one way or another, they like an open source offering because they are going to have control long term.
I would still describe it as the leading open source coding agent by a few measures.
But when it started, it was kind of the premier open source coding agent that was, uh, actually gonna feature complete, and now the ecosystem has grown.
As I see it, the mission of there being open source coding agents is so successful that you got a lot of neat options to choose from now.
But, um, yeah, when I, when I got started, you know, and that was my motivation, it was kind of in doubt whether that was even going to be a thing, whether they would be competitive.
Uh, that the open source options are competitive with the proprietary ones, that is absolutely true of coding agents, yes.
If we're going to talk about models, which are, you know, a, uh, a component of agents, then it's a little bit of a different story how competitive the open weight models are to the proprietary ones month to month.
So you can use proprietary models with open source agents, and you can use, uh, no, I guess you can't use, um, your own models with proprietary coding agents?
That's kind of a product choice, but what is usually the case is they will want to be in control of which, uh, models you use.
Uh, there are some proprietary coding agents, I think, that, uh, you know, mix in o- open weight agents, so I don't wanna draw a gross generalization.
But also one of the things you can do with OpenHands and other open source coding agencies is if the person has sufficient hardware at their disposal, they could run local LLMs too, right? So-
... do you find that a lot of the people using OpenHands are using, you know, big GPUs on their computers and running things locally more 'cause they want that full control over where their data moves back and forth and, and just to have it run locally?
I found that the open source element comes into play much more even than I expected at the enterprise level as well because e- enterprises like control.
Oftentimes they may be doing some local hosting as, as you kind of describe it now, or they might be using some offering that allows them to host a, a bigger model within their walls, but one way or another, they like an open source offering because they are going to have control long term.
The rest of this transcript — segmented and speaker-labeled, so you land on the exact moment something was said
Search every transcript — by keyword, by phrase, or by meaning, across every show Radar indexes
Trends — what is surging across podcasts, measured against its own baseline
Alerts — when a name you follow appears in a newly indexed episode
No account is needed to search Radar.
