I've used Cursor for work for a few years, but I'm really not a fan of giving all of my data to Musk. Also I think I want to spend less time writing code by hand.
I tried Antigravity but it's utter garbage.
I heard some good things about Opencode+open models/ollama cloud, but opencode seems slightly buggy when running it over ssh.
I'm really reluctant to give my money to the 2 leaders in the field, I don't think I want to contribute to them making more money, but I could be convinced if there was no doubt they're the best, which I'm not totally sure of.
I'm also on a limited budget and don't want to get a 200$ subscription unless there is zero doubt it's worth it.
My main focus is building MVPs around AI/agents, mobile apps, and scraping/automation.
In your opinion is there a clearly superior solution today you'd recommend? In terms of capabilities, value for money, usage limits.
Key tips that work for me are:
1. Use the AI model to create/refine your prompts. Take that enhanced prompt and start a new session with that enhanced, longer prompt
2. If you're capable, stub the project you're developing against. For example, if the frontend is React/Vue, use the scaffolding tools to stub out the project footprint and that's it! No changes other than what the scaffolding gives you. Once you have that project footprint, start your AI session in that directory
3. Encourage your model to follow strict TDD/BDD practices. Tests for the requirements are written first, they'll fail, and production code to make those tests pass comes second. By doing this, you'll incrementally move towards a cleaner, testable, and verifiable codebase
4. Write your AI-driven step-by-step (literally use those words) development plan to cap each iteration (aka step in the plan) at 100k tokens. Trust me, it works. I don't care how big the context window is - 100k is where the models start dropping things
If there's any point you take away from above it's number 1. Why are we writing prompts?! Let the thing that's good at text generation and has read the entire internet write the prompts! You can always refine what it gives you.
Addressing Claude Code vs local models: Claude Code is worth it but you don't have to pay for the Max Pro Plan. Start small and see how much you use. The local models will give mixed results and I encourage using those where applicable. Think about using a local model to take frontier-generated requirements and write integration tests against those requirements (TDD). See where that gets you? Swap the models out and try again.
I really hope this helps!
With cmux your agents can access the browser, spawn full shells, and you aren't locked-in to a specific vendor. It's really powerful but you need to update your instruction file so your coding harness knows it can use the cmux tools to test.
You can also download Handy to use voice so you can just give your feedback via voice into the CLI during the planning phase of a project.