There's so much happening in this space, but I still haven't seen what would be the killer feature for me: dual-mode operation in IDE and CLI.
In a project where I already have a lot of linting brought into the editor, I want to be able to reuse that linting in a headless mode: start something at the CLI, then hop into the IDE when it says it's done or needs help. I'd be able to see the conversation up to that point and the agent would be able to see my linting errors before I start using it in the IDE. For a large, existing codebase that will require a lot of guardrails for an agent to be successful, it's disheartening to imagine splitting customization efforts between separate CLI and IDE tools.
For me so far, cursor's still the state of the art. But it's hard to go all-in on it if I'll also have to go all-in on a CLI system in parallel. Do any of the tools that are coming out have the kind of dual-mode operation I'm interested in? There's so many it's hard to even evaluate them all.
I posted this the other day, but didn't get a response:
Does anyone think this model of "tool" + "curated model aggregator" + "open source" would be useful for other, non-developer fields? For instance, would an AI art tool with sculpting and drawing benefit from being open source?
I've talked with VCs that love open source developer tools, but they seem to hate on the idea of "open creative tools" for designers, illustrators, filmmakers, and other creatives. They say these folks don't benefit from open source. I don't quite get it, because Blender and Krita have millions of users. (ComfyUI is already kind of in that space, it's just not very user-friendly.)
Why do investors seem to want non-developer things to be closed source? Are they right?
I think it’s mostly a value capture thing. More money to be made hooking devs in then broke creatives and failing studios (no offense, it just seems like creatives are getting crushed right now). In one case you’re building for the tech ecosystem, in the other for the arts. VC will favor tech, higher multiples. Closed source is more protected from theft etc in many cases.
But as you point out there are great solutions so it’s clearly not a dead end path.
In a project where I already have a lot of linting brought into the editor, I want to be able to reuse that linting in a headless mode: start something at the CLI, then hop into the IDE when it says it's done or needs help. I'd be able to see the conversation up to that point and the agent would be able to see my linting errors before I start using it in the IDE. For a large, existing codebase that will require a lot of guardrails for an agent to be successful, it's disheartening to imagine splitting customization efforts between separate CLI and IDE tools.
For me so far, cursor's still the state of the art. But it's hard to go all-in on it if I'll also have to go all-in on a CLI system in parallel. Do any of the tools that are coming out have the kind of dual-mode operation I'm interested in? There's so many it's hard to even evaluate them all.