OpenCode: The Model-Agnostic AI Coding CLI I’ve Relied On for a Year

I have been using AI coding assistants for a while now. They all do roughly the same thing: help you write and understand code faster. But the one I keep coming back to is OpenCode. It fits like a glove.

Built for the terminal

OpenCode follows what good CLI tools do: lightweight, minimal interface, but gives you exactly what you need to see what is going on. The output is colour-coded, well laid out, and easy to read at a glance. When it explains what it is doing, I can see the plan clearly before it executes. When it writes code, I can review the diff before applying it.

OpenCode CLI interface showing structured AI response about WordPress wp-login.php

Desktop-based applications often either focus on the wrong things, or there is too much going on to keep the important functionalities in mind. OpenCode feels like a tool designed for people who live in the terminal.

Open.. everything

The OpenCode CLI is open source but also open, full stop. It does not try to lock you into anything. It tries to support as many different platforms, subscriptions etc. I want the flexibility to switch AI provider when there is a deal, a new model or to walk away from something I no longer like. Open source also means the community can contribute, audit, and improve it.

The OpenCode Go subscription

This is not needed to use OpenCode if you already have a subscription. If you don’t and/or you’ve been sitting on the fence for quite some time, maybe waiting for the perfect entry point into AI, I suggest you give it a try.

OpenCode Go costs then $10 per month ($5 for the first month). For this $10 you get $60 worth of usage. This is because usage is measured in dollar value rather than raw request counts.

The limits run in rolling windows to avoid overloading the platform. You get a 5-hour rolling limit of $12, a weekly limit of $30, and a monthly limit of $60. The actual number of requests you can make depends on which model you use — cheaper models get you many more requests, advanced ones fewer.

For example, with DeepSeek V4 Flash I get over 30,000 requests per 5-hour window. That is plenty for daily use. More advanced models like GLM cost more per request, so the same window buys fewer of them — I save those for when I need stronger reasoning.

If I need more usage, I can top up credit or let it fall back to my Zen balance. And once I hit the paid limits, the free models included with OpenCode still work.

There is also OpenCode Zen if you want the flexibility of a wider range of models and providers. But for most of what I do, Go covers it.

Models I actually use

I have settled on a few that cover most of my needs:

DeepSeek V4 Flash — my everyday driver. Fast, great value on credits, good for probably 80% of my interactions.

MiMo V2.5 — when I need vision capabilities. Looking at screenshots, debugging UI issues. Similar value to DeepSeek Flash.

GLM 5.x — for infrastructure work and complex multi-step reasoning. Excellent at planning, but I use it selectively because it consumes credits faster.

The ability to pick the right model for the task rather than being locked into one is exactly what I want. Some providers try to keep you inside their ecosystem. OpenCode lets you choose.

Actively maintained

The tool is actively developed. New models are added regularly, the CLI keeps improving, and the community around it is engaged.

Give it a try

If you live in the terminal and want an AI coding assistant that respects that, OpenCode is worth a try. It has become an indispensable part of my daily workflow.

If you want to give it a shot, you can sign up at opencode.ai (full disclosure: that is my referral link, which will give BOTH OF US $5 of extra credits).

Andrea

AI Hasn’t Torched Junior Dev Jobs — It Has Changed What The Job Looks Like

From programmer to agent manager

A post doing the rounds this week looks at employment data and concludes that AI has torched the market for junior programmers. The headline numbers are striking — youth employment in software down, entry-level postings shrinking — and I am sure the data is real.

But I read the article and came away with a different take. Because the same data also shows that overall developer employment is growing, GitHub is adding accounts faster than ever, and the roles that are expanding are the ones where judgment matters more than typing.

The original article is worth reading. Here is my take on what is really happening.

AI raises everyone’s ceiling

The narrative that AI replaces junior developers implies that senior developers are somehow immune. I don’t believe that. A developer with fifteen years of experience who knows what good code looks like can use AI to produce better code faster. But so can a junior who is curious, willing to learn, and not afraid to challenge the AI’s output.

The difference is not seniority. It is the ability to evaluate what the AI produces. Can you tell when the generated code is wrong? Do you know when to accept it and when to rewrite it entirely? Can you spot a security issue in something the AI wrote confidently but incorrectly?

Those skills come from experience and from caring about the quality of your work. They are not automatically granted by a job title.

From programmer to agent manager

What I see happening around me is a shift in what the job looks like. The traditional technical person — call them a developer, an engineer, a sysadmin — is becoming a manager of agents. You describe what you need, review what comes back, iterate, correct, and integrate. The hands-on keyboard work shifts from writing every line to directing, reviewing, and orchestrating.

This is not a downgrade. It is an upgrade. You are moving up the stack, not out of the industry.

But here is the catch: if you do not have the underlying knowledge — security, architecture, long-term maintainability, the trade-offs between different technologies — you cannot effectively drive the AI. Your results will be spotty, and you will not know why. AI amplifies good judgment and bad judgment equally.

The people who embrace it will transition, not disappear

I think the junior programmer job title as we knew it is probably going away. The idea of spending your first two years fixing typos and writing unit tests while you slowly absorb how the system works feels outdated when an AI can generate the tests and spot the typos for you.

But the people who would have filled those roles are not going to be left behind. They will transition into something else — something closer to what the data scientists and systems analysts are already doing. They will work at a higher level of abstraction, sooner, because the AI handles the lower levels.

The ones who embrace the change, stay curious, and build their technical judgment will be fine. The ones who expect the old career path to stay intact will struggle — but that was always true, with or without AI.

Not a conclusion, just a thought

I do not have a tidy answer here. The data is real, and it is affecting real people’s careers. But I think framing this as “AI killed junior dev jobs” misses the point. The job is evolving, and the people who evolve with it will end up in a better position, not a worse one.

What do you think?

Related Articles