maxalbarello

Hey all!

I recently started building context-use (https://github.com/massimoalbarello/context-use) because i deeply believe each one of us has an amazing story to tell, which for the most part is never told. Unfortunately, there aren't enough Walter Isaacsons in the world.

Now, though, thanks to AI and a bit of guidance and taste from the subject, it's possible for each of us to have our own self-writing autobiography. Here is mine: https://massimo.context-use.com/p/about/intro

context-use is the child of Obsidian and Substack. It offers both a private "context vault" for me and my agents and a public "billboard" for the rest of the world to see who i am, what i did and what i care about.

I believe the current feed-like structures of social networks are too linear to express one's self. Also, there the incentives are biased towards getting the most likes, comments and all the other bullshit. There are better alternatives like Substack, but they look too editorial to me.

This is the place where you can be unfiltered.

Try hosting it yourself and lmk what you think :)

congrats guys! how does the automated testing using ChatGPT/Claude clients work?

What are you working on? Curious to hear more

interesting! how do you review each other's plans? do you just copy-paste them into chat or something else?

wondering if the problem is the teammates rubber-stamping or the tool/workflow being outdated

that definitely helps but i'm wondering if that whole process (via an agent or via a human teammate) should be performed at the plan stage instead of the review stage. this should reduce the back and forth after the pr is opened (avoiding the delays and costs of running the CI several times)

the telemetry hooks and the rest is great but i'm wondering why there isn't a service that takes care of all of this. seems to be a problem that everyone building CLI has

rust, python and typescript mostly

yeah but maybe there the stakes are not as high. although i guess it touches the military and so it might be

i find it hard to believe that there is no equivalent anywhere else in the world. there is so much talent out there and the stakes are so high that it seems like an inevitability.

whatever many secrets are involved, information wants to be free and it's hard to believe that others won't figure it out.

by the time they do catch up we better be steps ahead. what's after EUV?

and yet not even close to the complexity of the human brain

Thank you! The video you recommended definitely goes more in depth. I still like Veritasium's style more but it's just personal preference ofc

For anyone interested in the topic I highly recommend this Veritasium video: https://www.youtube.com/watch?v=MiUHjLxm3V0

What was your request about?

> No one wanted to use those or make them for other people.

but why not?

personally i find it much easier to track my food, workouts, daily diaries etc. in ChatGPT/Claude as I already use them for everything else. no need for a standalone app when the app could simply plugin into ChatGPT.

wondering if it's a UX problem or a more fundamental one like platform risks

independently of whether the app is completely LLM generated or not, my point was more regarding the incredible distribution that ChatGPT offers and why it is not being taken advantage of.

one of the biggest problems of many consumer apps is convincing people to download it and give it a try. For many consumer apps like journaling, fitness tracking, nutrition, ... it seems that letting people use them where they are already spending a lot of time (i.e. ChatGPT) could be a great distribution advantage. Yet I could barely find any purely consumer ChatGPT apps and so I'm wondering what's missing. Any ideas?

Thanks a lot for your work on oclif!

What I was looking for is something like a framework + service. Imagine the equivalent of netx.js + vercel but for CLIs instead of for full stack apps. oclif seems to be only a great framework afaik.

as usage of CLIs increases I wonder whether there will be a need for a service that provides everything that developers of CLIs need (auth, telemetry, releases, ...). Something like what Vercel is today for full stack apps. Are you aware of anything along those lines?

can you provide a bit more info?

While playing around with OpenClaw I realized that after a few days of adding skills, plugins, crons, etc. things were all over the places. Memory files spread everywhere in the workspace, plugin configs stored here and there, skills not always visible to crons, ...

I started working on a CLI to keep OpenClaw organized: https://clawtique.ai

The analogy is that of a boutique. OpenClaw goes to the boutique and is "dressed up" properly so that all the various components are organized and easy to maintain. Clawtique is organized around the concept of a "dress", basically a bundle of everything OpenClaw needs to achieve a goal (skills, plugins, memory segments, crons, ...). The CLI enables users to easily dress and undress OpenClaw so that you can try out a dress and easily remove it without leaving any dangling dependencies.

Some dresses i created are the sleeping-coach (bundles the OuraClaw plugin https://github.com/rickybloomfield/OuraClaw with skills and crons that notify you on how you slept) and the fabric-sync (bundles the fabric plugin https://github.com/onfabric/openclaw-fabric with skills and crons to maintain an accurate USER.md of you based on your interactions on the various big tech platforms).

The follow up is to have OpenClaw use the Clawtique CLI itself so that it can easily dress and undress with whatever it needs to accomplish the goal without everything becoming an unmanageable mess.

Here is the repo: https://github.com/onfabric/clawtique

Curious to know what you guys think

that's much better than having a dedicated whatsapp account for each openclaw

Would love to share some projects I've been working on but I can't because of this... any tips?

Discipline is the way

gh actions are slowing us down. any alternatives?

There has never been a better time to be a developer! Less mechanical debugging, more creative thinking.

Giulio Cesare by Alberto Angela. Unfortunately, I didn't pay much attention to my history classes in high school. Want to catch up

Also wondering how to evals agentic pipelines. For instance, I generated memories from my chatGPT conversation history, how do I know whether they are accurate or not?

I would like a single number that I would use to optimize the pipeline with but I find it hard to figure out what that number should be measuring.

Working on [context-use](https://github.com/onfabric/context-use) to turn data exports into portable AI memories.

I've been searching, posting, chatting on various platforms for more than a decade now. context-use allows me to turn all those years of data into context that I can bring to my favorite agents.