Context-Engineering VS opencode

I haven't read through this fully yet, but there's an in-depth "course" here https://github.com/davidkimai/Context-Engineering prepared featuring content that as far as I can tell is based on this paper.

Problems w auth / security in MCP skeeve me out. For that reason, I really don't want to invest in workflows that depend on MCP and have steered clear. If there's a new "context setup" protocol, I wonder if it'll leverage ideas from this paper / project regarding "cognitive tools": https://github.com/davidkimai/Context-Engineering

here^1 -- seems like the way forward, at least to this casual observer.

1. https://github.com/davidkimai/Context-Engineering/blob/main/...

(the repo is a WIP book, I've only scratched the surface but it seems pretty brilliant to me)

You can use Claude Code against Kimi K2, DeepSeek, Qwen, etc. The 20$ a month plan gets you access to a token amount of sonnet for coding, but that wouldn't be indicative of how people are using it.

https://gist.github.com/WolframRavenwolf/0ee85a65b10e1a442e4...

We gave Gemini CLI a spin, it is kinda unhinged, I am impressed you were able to get your results. After reading through the Gemini CLI codebase, it appears to be a shallow photocopy knockoff of Claude Code, but it has no built in feedback loops or development guides other than, "you are an excellent senior programmer ..." the built in prompts are embarrassingly naive.

Qwen has it's own agent which I haven't used https://github.com/QwenLM/qwen-code

Another is https://github.com/sst/opencode

sst/opencode has plans to build a mobile app.

https://github.com/sst/opencode/issues/176

I recall watching a stream where the authors imagined instructing the agent to do a piece of work and then getting notified on your phone when it is done or being able to ask it to iterate on your phone.

There's also opencode which is a fork(?) of Claude Code that runs on any model: https://github.com/sst/opencode

And of course, not the same, but Aider still exists and is still a great tool for AI dev.

It's interesting how everyone is suddenly OK with vendor lock-in, quite a change from years past!

I wonder if this can work with OpenCode (Claude Code fork which allows for other model providers: https://github.com/sst/opencode)?

I really don't like being tied to a particular provider or model, switching models has been really helpful to get past blocks and save money (especially with Deepseek!).

And, of course, I need to use Github Copilot's Open AI-compatile API at work...

Opencode https://github.com/sst/opencode provides a CC like interface for copilot. It's a slightly worse tool, but since copilot with Claude 4 is super cheap, I ended up preferring it over CC. Almost no limits, cheaper, you can use all the Copilot models, GH is not training on your data.

Yes, this is that company. This is the "original":

https://github.com/sst/opencode

I tried recently Aider and it seemed a bit behind. It's not getting as much development as the others either: https://github.com/Aider-AI/aider/pulse/monthly

Compare with https://github.com/sst/opencode/pulse/monthly

> The recent Kimi-K2 supposedly works great.

My own experience is that it is below sonnet and opus 4.0 on capability - but better than gemini 2.5 pro on tool calling. It's really worth trying if you don't want to spend the $100 or $200 per month on Claude Max. I love how succinct the model is.

> you can use CC with any model via

Anthropic should just open source Claude Code - they're in a position to become the VS Code of cli coding agents.

Shout out to opencode:

https://github.com/sst/opencode

which supports all the models natively and attempts to do what CC does

Thanks for the link. I'm not an emacs user and I'm more in the search of something like opencode [1], but I think it's not polished enough yet. I actually want to contribute to open source, so maybe I should create my own thing, heh.

[1]: https://github.com/sst/opencode