badlogic

i wrote the blog post and i also wrote pi.dev. i haven't written much code myself in the past 12 months. i'm not making coding agents out to be the problem. the entire last section keeps is basically "use a clanker for this and that".

i'm making specific usage pattersn out to be the problem, and explain why those patterns can't work due to the way agents work.

you get me

you can use subscriptions with pi.

OpenAI officially supports using your subscription with pi. Same for OpenCode and other 3rd party harnesses.

if i ever want a claw, i'd obv. go with this :)

wow, i love this! was about to build this myself, but this looks exactly what i want.

i'm not a member of openclaw. i build some oss in parallel, and added 3 or so commits to the openclaw repo. and peter is taking some of the openclaw contributors with him.

don't do this, this is ridiculous. both openclaw and pi are passion projects by two friends who are already well off.

peter's claw is a lot more than just a wrapper around my slop.

i too had plenty of offers, but so far chose not to follow through with any of them, as i like my life as is.

also, peter is a good friend and gives plenty of credit. in fact, less credit would be nice, so i don't have to endure more vibeslopped issues and PRs going forward :)

OpenCode is not written in Go. It's TS on Bun, with OpenTUI underneath which is written in Zig.

The web package has a minimal example. I'm not a frontend developer, so YMM hugely V.

FWIW, you can use subscriptions with pi. OpenAI has blessed pi allowing users to use their GPT subscriptions. Same holds for other providers, except Flicker Company.

And I'm personally very happy that Peter's project gets all the hype. The pi repo already gets enough vibesloped PRs from openclaw users as is, and its still only 1/100th of what the openclaw repository has to suffer through.

It's not an API drop in replacement, if that's what you mean. But the pi-ai package serves the same purpose as Vercel's AI SDK. https://github.com/badlogic/pi-mono/tree/main/packages/ai

There are lots of ways of doing subagents. It mostly depends on your workflow. That's why pi doesn't ship with anything built in. It's pretty simple to write an extension to do that.

Or you use any of the packages people provide, like this one: https://github.com/nicobailon/pi-subagents

libGDX, now that's a name I haven't heard in a while.

differential rendering

Now where have I seen that before.

It is very 2026, that this exists for the product by a company that goes all in on vibe coding. Kudos for the creative solution.

Neat. Any reason why the MCP server doesn't expose a JavaScript/eval tool? Current models excel at writing JS to drive and inspect the DOM. They aren't great at driving browsers via screenshots.

Create a markdown file, for each SKILL.md of the skills you want to use, put the frontmatter in that single markdown file along with the fulk path to the SKILL.md file. On session start, tell Gemini to read that file. If you put it in your AGENTS.md, you don't have to instruct Gemini. And if you have your skills in a known folder, let Gemini write a small scripts that generates that markdown file for you.

Loved the fun write up. Now that we know that LLM-based vision is lossy, here's a different challenge:

Give the LLM access to the site's DOM and let it recreate the site with modern CSS. LLMs are much better with source code, aka text, right? :)

I can talk for the gov. site in my European home country: they too are buying GPUs for chat ...

Oh, I didn't intend this to come across as MCP being useless. I've written this from the perspective of someone who uses LLMs mostly for coding/computer tasks, where I found MCP to be less than ideal for my use cases.

I actually think MCP can be a multiplier for non-technical users, where it not for some nits like being a bit too technical and the various security footguns many MCP servers hand you.

Also not disagreeing with your argument. Just want to point out that you can achieve the same by putting minimal info about your CLI tools in your global or project specific CLAUDE.md.

The only downside here is that it's more work than `claude mcp add x -- npx x@latest`. But you get composability in return, as well as the intermediate tool outputs not having to pass through the model's context.

Yes, the only reason they are building a browser is to gobble up more data.

https://x.com/badlogicgames/status/1980698199649317287

I run a few production RAG systems, some as old as end of 2023 and arrived at the same conclusions.

Query expansions and non-naive chunking give the biggest bang for the bug, with chunking being the most resource intensive task, if the input data is chunk (pun intended).

I love this! Not just because I also grew up in the 90ies and like your music choice :)

As we drown in media and slop, I think it's super important to teach kids how to be selective, develop taste. And I too found that physical connection does help with that.

Great project and execution. It would be great if you could also introduce a social aspect, i.e. kids sharing/swapping cards.

(Did something similar for our then 3yo, since it's one of a kind, the social aspect is kinda not there. Yet! https://mariozechner.at/posts/2025-04-20-boxie/)

Chrome dev console has Gemini integrated as well. Otherwise pick any coding agent (Claude Code, Codex, opencode, ...) give it the Playwright MCP and ask away.

Genuinely love this. I've sort of done this by hand before the advent of good coding agents [1]. But now, it is even more enjoyavle, as development time is even less an issue.

I'd love to see more people realize this and use that new power to build things that don't necessarily scale on their own, but might trigger changes for sizeable groups, either socially, or politically.

[1] https://mariozechner.at/posts/2024-07-15-two-years-in-review...

Can you share which model you are using?

The todo and porting "programs" are unrelated. The blog post shows the full porting pipeline.