We are a sandbox provider company and we have a manus like agent deployed to "showcase" our capabilities. You can build one too -- maybe we will open-source it. For now, you can try it for free at https://showcase.instavm.io/

> I have since fallen off the productivity wagon unfortunately

If you don't mind sharing, what was the reason? I'm asking coz these things and also note taking isn't sustainable for me at all.

Not OP but I used to be totally into productivity hacks and being on top of things, goal setting, habit tracking, everything.

I stopped when I realized I could just... Not, and still thrive in my life. Simplify my systems.

I set myself a goal to workout every morning. Sometimes I miss it because my infant daughter decides to wake up at 4am instead of 5am. I give myself grace.

We eat largely the same meals every day. Some cooked protein, some cooked veggies, and a grain (rice or pasta).

And I just have a regular routine at work where I work on work and also do explorative education for myself during breaks. Look into different frameworks, patterns, etc.

I didn't need to meticulously plan out every second of my day, month, year. I just needed systems that made things predictable. Sometimes I drop the ball and it's fine. I get back on the horse when I can.

I made a comment about this, if you are on macOS - Coderunner (https://github.com/instavm/coderunner)

If you don't want to depend on cloud, have a mac, then you can run a sandbox locally on you mac. I have built an apple container (not docker) based sandbox to run arbitrary code - coderunner[1]. It is quite fast. And apple container provides one vm per container unlike docker on macos which shares the vm across all containers. Coderunner is good for processing sensitive docs locally in a secure sandbox.

1. coderunner - https://github.com/instavm/coderunner

In the coderunner read me it talks about reading files without sending them to the cloud. Does that mean there is something agentic going on? That’s more than I expect from something called a sandbox.

Also if it is agentic, why is it less cloud based than eg Claude code? Are there LLMs running locally?

Regarding files, they are volume mapped (local <--> sandbox) as with docker.

It's not agentic - agents can use it to execute code. Those agents can be powered by any LLM including local.

I’m still not sure why sending files to the cloud is supposed to be a disadvantage of other approaches but not this one. Whether you run your LLM’s commands in this sandbox or not, content is going to the cloud if the LLM is in the cloud, and not going to the cloud if the LLM is local. It looks like the amount of data in the cloud is entirely orthogonal to whether you use coderunner.

If you run your LLMs locally then nothing goes to the cloud. If you use cloud offerings then of course nothing is going to help you.

I think their point is more that that architecture of this CodeRunner program isn't very clear.

It's unclear if it is a container manager, or comes with a LLM Agent built in. These are two separate concerns and the README makes it very unclear how to use one without the other.

I could say the same about any AI architecture. By definition cloud = cloud, local = not cloud. So when coderunner advertises ~ “more privacy because less cloud” I’m not sure what it is about coderunner that helps me get less cloud than anything else.

You can achieve what Skills achieve via function calling somewhat.

I've this mental map:

Frontmatter <---> Name and arguments of the function

Text part of Skill md <---> description field of the function

Code part of the Skill <---> body of the function

But the function wouldn't look as organised as the .md, also, Skill can have multiple function definitions.

Yes. Infact you can serve each Skill as a tool exposed via MCP if you want. I did the same to make Skills work with Gemini CLI (or any other tool that supports MCP) while creating open-skills.

1. Open-Skills: https://github.com/BandarLabs/open-skills

Interesting. Skills on MCP makes a lot of sense in some contexts.

Have you tried Claude Code in the second tab instead, that would be a fair comparison.

Claude Code isn't as surgical as Codex at reviews

If anyone wants to use Skills in Gemini CLI or any other llm tool - check out something I have created, open-skills https://github.com/BandarLabs/open-skills

It does code execution in an apple container if your Skill requires any code execution.

It also proves the point that Skills are basically repackaged MCPs (if you look into my code).

Will Skills and Code Execution replace MCPs eventually?

I doubt that. MCPs are broader. You can serve a Skill via a MCP but the reverse may not be always true.

For example, you can't have a directory named "Stripe-Skills" which will give you a breakdown of last week's revenue (unless you write in the skills how to connect to stripe and get that information). So, most of the remote, existing services are better used as MCPs (essentially APIs).

Anthropic via Azure has sent me an invoice of around $8000 for 3-5 days of Opus 4.1 usage and there is no way to track how many tokens during those days and how many cached etc. (And I thought its part of the azure sponsorship but that's another story)

> If anything, I think we'll see (another) splintering in the market. Companies with strong internal technical ability vs those that don't.

A tangent, I feel, again, unfortunately, the AI is going to divide society into people who can use the most powerful tools of AI vs those who will be only be using chatGPT at most (if at all).

I don't know why I keep worrying about these things. Is it pointless?

I do feel this divide, but from what I've read, and ehat I've observed, it's more a divide between people who understand the limited use-cases where machine learning is useful, and people who believe it should be used wherever possible.

For software engineering, it is useless unless you're writing snippets that already exist in the LLMs corpus.

> For software engineering, it is useless unless you're writing snippets that already exist in the LLMs corpus.

If I give something like Sonnet the docs for my JS framework, it can write code "in it" just fine. It makes the occasional mistake, but if I provide proper context and planning up front, it can knock out some fairly impressive stuff (e.g., helping me to wire up a shipping/logistics dashboard for a new ecom business).

That said, this requires me policing the chat (preferred) vs. letting an agent loose. I think the latter is just opening your wallet to model providers but shrug.

If you need a shipping dashboard, then yeah, that's a very common, very simple use-case. Just hook up an API to a UI. Even then I don't think you'll make a very maintainable app that way, especially if you have multiple views (because the LLMs are not consistent in how they use features, they're always generating from scratch and matching whatever's closest).

What I'm saying is that whenever you need to actually do some software design, i.e. tackle a novel problem, they are useless.