Try it out for coding (in a "Code" project) and document creation / manipulation (in a "Work" project). In Work projects we have automatic checkpointing for every change the agent makes. Would love to hear your feedback.
This is one of the better agent harnesses I've seen for inspecting reasoning chains, which is super useful for me. Sometimes reading the reasoning is better for my needs than reading the response. I appreciate how transparent that is in contrast with Claude Code/Codex/etc.
One question — I saw you mentioned negotiating ZDR with your "providers" — are you hosting the models yourselves, or is another entity hosting them? If another entity, which group?
Nowhere near ready for production
First impression: it works great. I use Codex as my main agent, and the UI looks similar enough that it's familiar and simple to get started. I just pointed it to my existing LM Studio models library, ran Qwen3.6 35B, and the results are exactly what I would hope for.
I did notice some rough edges that might be worth improving, however:
- Current working directory is not the clearest on the main page of the app. It shows the project name, but is missing the prominent working directory label like Codex has. - The model seems to load when you hit Enter, but it shows "Working" instead of of "Loading model". - There doesn't seem to be a way to pre load the model, it seems like you have to send it something to load the model. - I don't see a way to easily unload the model like the eject button in LM Studio without quitting the app - I pointed it to a directory called "GitHub & Projects" and it somehow ended up making a new folder called "GitHub & Projects". Yes, I know the name is weird but it shouldn't have done that.
i believe that for most people on the street, for most tasks, a Chat GPT 3.5 era LLM is sufficient enough. sprinkle in tool calling and other things, and that becomes enough. if you can prioritize that level of a model on-device (baking it in etc), then you can bifurcate AI users between those unwilling to pay and those who are willing to pay A LOT for frontier model performance.
Tools like Opencode demonstrate that when you box them in tightly enough they can actually be pretty competent.
That way everyone has access, even with older devices, and it's a subscription! Then Apple can tie their APIs into the ecosystem you love at a flat cost you can afford. No need to support local model integration in the first place, problem solved.
It already is.
Please don't slur us older GenX as boomers.
There is no way I’m running a python or JS agent which is probably vibe coded, it’s just too much risk from a security and supply chain standpoint.
> use the largest frontier open source models through LM Studio Secure Cloud
(I’m the founder of LM Studio)
Since most people are unaware of this fact.
I would obviously prefer an open source, open weights stack.
But I guess a paradox is that as long as there are open source options I could use, a solid agentic environment that I can use with my own open weights is something I might pay for, in a similar sort of way to paying for a Mac when I could use only Linux.
If someone wanted to make their entire income from, say, making the BBEdit of LLM harnesses, that would be a viable strategy. Sooner or later people need to make an income somewhere. My own feeling is that Apple should acquire LM Studio, but if they said "this is $X per year" I might consider it, given the attention to detail.
I don't think we need closed-source developer tools, especially ones where they might restrict access if they decide to start charging for them later.
and using a closed-source, VC-backed app that might change anything in the next update might not be best for privacy
It’s an important criteria to have in mind when you select an application.
Happy to clarify which is who and who is which.
Less unanimous and debatable, but many would say they more often do not align than the opposite.
Is that a problem for you comrad?
I agree. Incidentally, this is exactly what ollama are doing too.
I run lmstudio personally with a range of harnesses (open and closed) and can't say there is that much of a leap to getting everything talking https://lmstudio.ai/docs/integrations
To me this looks like another case of bundling things that shouldn’t be bundled (the harness with the UI) making both worse off because you can’t individually focus on each component. They’ve done this before, bundling a decent UI with decent inference for IMO no good reason, combining the downsides of each instead of letting people mix+match.
and if someone can't figure out how to write down an address it's very likely they also can't figure out how to make local models not suck for coding, and would likely switch back to codex/cc after 15 minutes anyways.