I use opencode with locally-hosted llama.cpp - usually with qwen3.6-35b-a3b.

I tried opencode go for a couple month, and its definitely nice to have an lln runner with more gram and more GPUs, but I prefer to have all my stuff local whenever it's possible. Also, I'd use up my token allotments fairly quickly on opencode go.

I also tried opentouter and it, too, was great - many more models. But I exhausted by credits even quicker than opencode go, and its also not local.

Claude cli almost exclusively. So far mostly opus, but I need to start using less expensive models more frequently.

I have Codex installed, but I mostly use it to interface with Obsidian, which is where I track all of my tasks and organization stuff. Unfortunately, codex doesn't play cleanly with Claude, so it's hard to use it for coding at all, but I do have it review documentation and identify gaps or discrepancies, because it's far cheaper than having Claude do it.

I've tried lmstudio for local AI with some ~30b models. It works fairly well and fast, but only for tiny context sizes. One I pass a few thousand tokens the speed falls off pretty quickly.

Nothing. I threw them all out. After is forgot how to write good code and how to design good software.

That his how cerebral atrophy must feel like.

Nothing. Fuck AI.

I've been using oh-my-pi agent harness with a mixture of Claude for planning and either Gemma4 or Qwen3.6 for execution.

FYI, I think opencode go is kind of a subscription model, not a direct credits-to-tokens model. In terms of value it's nowhere near as good as Claude's subscriptions, but it seems way more valuable that paying for tokens directly. However they only offer a few models - decent ones, but not many and a little behind the times.

I only use openwebui with an openai key that my employer pays for. No agentic stuff, haven't found the need for that yet.

At work Cursor with Sonnet or Composer and very very few times Opus.

At home I can't afford any of that so I use opencode and try to use super cheap models in openrouter and very few times to save money, I just delegate simple straightforward, tedious tasks to gemini flash or deepseek

I haven't found anything that isn't a shell backdoor that you let an llm run commands in, so strictly via chat interfaces.

In work we use cursor. I generally use their composer model. Before that it was vscode with claude.

Personally i have not done any personal dev work in a long time, its mainly server maintenance and i can do that myself. When i get the itch to do more dev stuff ill probably use vscode with copilot. My personal machine isnt great for local models.

A mix of gpt-5.5 and claude opus 4.7, wrapped in my own mobile web UI that doubles as planning software and document editor.

The reason for the mobile focus is I've been trying to detach from my home office as much as possible, meaning I do a lot of up-front planning via ADRs and task/story writing, then I spawn agents to actually work on coding tasks. The only part that really requires sitting at a desk is code review, manual testing, and deeper human-in-the-loop coding or debugging sessions.

If you are able to max out the $100/mo plans from either OpenAI or Anthropic, then that is already a very cost-effective option.

I don't like the term "AI coding", but recently I have been playing with opencode with it's hosted models and ollama for light local models. It's good as a rubber ducky, an assistant, or co-programmer.

OpenCode Go/Zen have deepseek models that have the best cost-benefit out there. Then OpenRouter with selected providers if I want to try something else.

I don't spend more than $20/month on personal projects and still manage to have a lot more functionality than I could have without AI.

I use Zed with either Sonnet or Gemini. I do plan to swap to using Qwen locally since my hardware has no issues running it.

At work claude code, at home zed+deepseek. I loaded up a few dollars in deepseek's API and they are lasting a long long time (many months). I also tried qwen locally but it's too slow for me (it runs on the CPU...). I use AI though only for repetitive and boring implementation tasks, or throwaway one-time scripts that I don't feel like coding by hand. The point of coding at home for me is to have fun, and having the AI solve all interesting problems for me defeats entirely the purpose of why I'm coding. At work we are unfortunately being pushed to use AI a lot more, and the amount of slop code is increasing :(

Simple: I'm not a moron, so I don't use AI at all.

opencode with nanogpt (12$/month subscription or prepaid pay as you go) using GLM 5.1

let me know if you need a referral code for a 5% discount

Claude Code, mostly, but I'm with Scipitie that the tool matters less than the process around it. What's helped most is writing the project's rules and conventions into files the agent reads each session, then putting the non-negotiable ones behind a linter or a test so it can't quietly skip them. Treated that way it behaves a lot like the junior who's read all the books and understood half of them. Left to its own judgement it drifts, which is the part the guardrails are there to catch.

I'm experimenting a lot with goose, recently return on by the AI arm is the Linux foundation. It's not yet mature enough to recommend it as a daily driver for non fanatics though for agentic stuff.

Trying it as a daily driver by now :D

It's less about the tool though in my opinion but about the process. If you want to be a programmer then you need something integrated into your dev environment in my opinion.

My focus is seeing how far I come with focussing in being a software architect who only has really weird junior devs who read a lot of books but lack any understanding.

Which is ... quite close to real life ;)

I'm splitting by now my projects: agentic ones and "my" dev ones, treating trm differently helped me tremendously: different focus and I need a different skillset.

Opencode with local inference (via ollama) Have tried gpt-oss-20b, qwen3.6-30somethingB and gemma4-e4b. Qwen is too slow for my hardware and gemma4 does not follow instructions that well. Haven't spend much time (yet) but gpt-oss seems like a good balance.

For work I also use opencode but with either claude-opus or deepseek-v4-pro. Obviously opus is stronger, but deepseek is still surprisingly capable and I have more control (can't figure out how to show opus reasoning traces) so I prefer it.

That said, I still write code myself 90% of the time. I just use llm for questions, codereview, etc.