opencode VS qwen-code

Dax, the creator of OpenCode — an open-source coding agent, of all the people one might expect to disagree — put the case for hand-coding cleanly in a recent interview about Spec-Driven Development:

Pipa is our agent for studio operations at Lunch Pail Labs. She lives in Slack, is powered by E2B sandboxes, and uses OpenCode for the harness.

One reason I liked OpenSpec more than others, such as Kiro and SpecKit, is that OpenSpec is highly portable between coding assistants, codebases and stages of development. I've plugged OpenSpec into all sorts of projects, from infrastructure to Python libraries. I also work on diverse codebases, with a variety of AI friends that OpenSpec supports: OpenCode, Codex and Claude Code.

Beyond the big names, I would also keep an eye on OpenCode and T3 Code. OpenCode is a solid open-source, terminal-first option if you want a model-agnostic agent and bring your own provider setup. T3 Code is interesting for the opposite reason: it gives you an open-source GUI on top of the agents you may already pay for, like Claude Code, Codex CLI, OpenCode, or Cursor.

Brought to you by the infamous creator of OpenCode, who will exfiltrate all your data, then feign ignorance:

https://github.com/anomalyco/opencode/issues/10416

I probably won't keep working on Pebbles. Instead, I'll focus on contributing to pi-mono and qwen-code, the projects that inspired this whole adventure. Both are doing interesting work in the AI assistant space, and I'd rather help push those forward than maintain my own thing.

I took inspiration from projects like pi-mono and qwen-code. Since these tools are open source, I can read the code and actually understand how they work. I've always loved terminal apps, so it made sense that I'd fall in love with coding agent CLIs.

I spun up Qwen3 Coder 30B A3B Instruct 4bit locally with MLX using LM Studio and several CLI options: Claude Code Router, llxprt, and Qwen Code.

Kind of glad that I missed the Cursor hype then rapid slide into enshittification, since I didn't think its goal of replacing an IDE would be a winning strategy and instead went for IDE plugins/extensions like Augment Code, GitHub Copilot and Gemini Code Assist as they work in both Rider/Intellij and VS Code.

I'm assuming I don't use AI as much as most devs as I'm still comfortably within Augment Code's 600 user messages/mo dev plan limit which IMO is great value for being able to use its Context Engine. If I ever exceeded that I'd likely temporarily switch to Qwen Coder's effectively unlimited free tier [1] until the next quota refill.

Not sure if Augment's going to increase their prices or downgrade their quotas since they're still at the whims of Claude Sonnet / GPT 5 API pricing, but if they do I'd be looking at moving to an open model solution like Open Code / Roo Code so I can easily switch to the best value coding models of the day, between Qwen3 coder, Grok Code Fast, GLM, Kimi K2, DeepSeek, etc we're spoilt for choice [2].

[1] https://github.com/QwenLM/qwen-code

[2] https://openrouter.ai/rankings#categories

Install QwenCode And let's use it with Qwen3 Coder 30B Instruct locally (I recommend having 24GB of VRAM for this one 😅)

Agentic coding is evolving rapidly, reshaping how developers interact with AI to generate code. Instead of being locked inside full-blown IDEs, many are moving back toward lightweight, flexible command-line interfaces. Since the arrival of Claude Code, we’ve seen a wave of new coding CLIs Gemini CLI, Qwen Code, and others but each has come with a major limitation: they are tied to a single model provider.