rcarmo

Neat, but I keep having to edit the pi stub to remove the "/bin/env node" and replace that with bun instead, because, well, somehow that's still hardcoded.

The official one seems to do, as well as other info from the engine (I think remember their mentioning LOD/UV map hints in one of the public demos, or articles, a few months back--or it might have been an Unreal Engine podcast)

Addendum: My unfettered notes on chaining MCP operations are here: https://github.com/rcarmo/umcp/blob/main/docs/CHAINING.md

I happen to think codemode is useful, but not the full answer. I have a long and skewed history with chaining things in MCP and built a dozen or so enterprise ones (see https://taoofmac.com/space/blog/2026/04/29/2341 for notes) and it all falls back into the trade-off between agent scope/context and tool coverage: If you are using a coding agent it will have no trouble sorting out any tool regardless of how many are exposed (it's just a matter of either progressive tool disclosure or good tool metadata, since the coding agent will just go at it and expend whatever tokens are needed), whereas in a "normal", limited, scoped agent that has only a few things it needs to do (like handling a ticketing system) codemode is pretty much overkill.

Pi is primarily a coding agent, so yeah, code mode makes sense, but I've found that better MCP design saves everyone a lot of trouble and would also probably have improved the thing's reputation overall (I personally am not fond of the line protocol, would rather have protobuf and more typing, but it is what it is).

In enterprise integrations, that is just not an option. MCP has pretty much taken over there.

Have a go at https://github.com/rcarmo/memento, I would appreciate Claude testers since I mostly use Codex. Just trying it and filing an issue about what doesn't work would be great...

You can turn those tools off. In fact, that is what I am doing right now in https://github.com/rcarmo/piclaw until I am positive the new MCP stuff has full parity with the MCP adapter I've been shipping for the past six months or so.

I'm actually pretty happy that they did it, since 90% of what I have to integrate in enterprises is MCP-driven (it's a security and auth boundary that has become pretty much mandatory for any third-party agents wanting to reach into corporate data) and this lets me use Pi directly. Am just being cautious about the first version, because, well... it's a first version, and I like my tools stable.

(I actually played around with the idea of using QuickJS myself for codemode, but since I rely on Bun that gives me the ability to use other things... never got around to do it though.)

I have had to hack a couple of workarounds in https://github.com/rcarmo/memento to do uploads, and there's a draft going around, but the general practice in enterprise MCPs seems to be to do it "out of band" and have MCP tools to hand-over storage handles/URLs so the MCP server can do the imports itself "safely".

Have been doing https://rcarmo.github.io/projects/python-office-mcp-server/ for a year or so now, and have Go and TS libraries that use the same test fixtures. This is a non-trivial thing in terms of test coverage, but I’ll get there… don’t see a paying market for it though.

I am using Go assembly for SIMD very heavily in https://github.com/rcarmo/go-pherence, this is just icing on the cake.

Yah, that's what I use: https://rcarmo.github.io/projects/go-system-one uses Gemma, and that's partly why. Seems less prone to getting distracted with ordering.

Very nice as a conceptual thing, but there's a bit more to it. I've bolted Gemma 4 onto a custom pipeline for that (https://rcarmo.github.io/projects/go-system-one/) and it's OK-ish (a bit slow on my puny 3060, but I can use it to prototype a bunch of things locally until the Jev mania settles and we have better models).

Hi there! I've decided to take a stab at building a Jev-like that can run on relatively humble hardware (I only have a 3060, but plenty of CPUs). This is based on my go-pherence kernels, so piecing it together was fairly simple, although the core techniques needed some digging around and are likely to change.

Some of these are actually... pretty good. I used to do print design to pay my way through college, and they wouldn't be too far from run-of-the-mill pamphlets we would turn around (both design and print in small runs) over lunch.

Yep. Not instantly though. I am hacking away at these things over on https://github.com/rcarmo/go-pherence (I do SIMD versions of common inference algos) and trying to improve that.

I want this with TOTP or passkeys. Just giving me a hostname doesn't cut it these days.

I was hoping for Douglas Adams’ Electric Monk, but this seems fun too.

Which has been happening for over twenty years on taoofmac.com, for instance. It’s a reflex by now.

Neat, but… I’ve built up skills for my agents to just generate SVG charts and embed them in the chat timelines. A library helps, sure, but you can get surprisingly good results that cover 80% of the timeline and bar chart visualizations without any libraries, and that goes for diagrams as well (mine generate .drawio XML)

I'm currently playing with the https://linkr.now - which has an API and a set of agent skills. _much_ more useful than other KVMs I've tested in the past, and I published a pi/piclaw add-on here: https://rcarmo.github.io/piclaw-addons/addons/linkr/

This was painful to read, even though the subject matter is very interesting to me. Please, ModelRift, get a human author.

I keep looking over my shoulder to the pair of KALLAX behind me ever since I watched this, just to check if they budge.

It is. Review coming soon :)

Yeah, I never mention prices in my reviews because the very first link is usually to the manufacturer or the product page, and prices go stale.

Also, no remote postings in Europe is just stupid.

Yep, that’s mine

Mine already covers all of that, based on what Codex says…

I have a trifling complaint about this, which is that it smacks of LLM aid throughout, especially in headings. I wish people would aggressively filter for these things--I have a technical writing SKILL.md that tries to remove all the AI tropes it finds and use simplified technical English (it's a thing, look it up) to do docs, and that makes one heck of a difference...

They are more creative than that.

The EU ones do reach out to endpoints, but mine is currently off and I am not testing that :)