Transcription: OpenAgents Episode 105 - Reaction: Progrium Technology Thesis

Source: https://x.com/OpenAgentsInc/status/1805320338064261219 Wiki source: https://raw.githubusercontent.com/wiki/OpenAgentsInc/openagents/Video-Series.md Media title: OpenAgents - Episode 105: Reaction: Progrium Technology Thesis We learn more abou... Upload date: 20240624 Transcription model: mlx-whisper/mlx-community/whisper-tiny Generated at: 2026-06-01T18:05:32Z

Machine-generated transcript. Review speaker labels and wording before using this as quote-grade source material.

[00:00] Christopher David: In yesterday's video, we learned about WANIX as a potential

[00:07] Christopher David: little agent runtime to power the agent workspace of our new autodev.

[00:14] Christopher David: And learning more about the WANIX ecosystem associated with this project called Tractor.

[00:24] Christopher David: I saw this sort of 12-minute manifesto from the main guy behind it, Jeff Lindsay,

[00:30] Christopher David: brilliant engineer dude, invented web hooks, blah, blah, blah.

[00:35] Christopher David: And I wanted to do a reaction video of it.

[00:38] Christopher David: I think there's some real parallels between this video and kind of like the overarching complexity of software.

[00:45] Christopher David: Generally, I think that's like mirrored or a microcosm of that is happening these days

[00:50] Christopher David: in the agent ecosystem and I think there's a lot to learn from this.

[00:55] Christopher David: So we're going to step through this and you'll note themes very similar to the stuff that we've been talking about.

[01:01] Christopher David: In terms of building blocks and such, but we're going to be probably engaging this tractor ecosystem more

[01:08] Christopher David: because that kind of fits with our WANZM based interoperability approach.

[01:13] Christopher David: And I think there's a lot to learn here.

[01:16] Christopher David: Since at least the 1980s, a gap has been growing between software users and software.

[01:22] Christopher David: And 64 nice.

[01:24] Christopher David: My name is Jeff and I'd like to tell you about what I've been working on for the past few years.

[01:29] Christopher David: Creating software is too complicated.

[01:32] Christopher David: Our options are overwhelming.

[01:34] Christopher David: Our tooling is too bloated and things rarely ever just work.

[01:38] Christopher David: Eight years ago, the late Joe Armstrong co-creator of Erlane,

[01:43] Christopher David: gave one of his last talks at the 2014 Strange Loop Conference.

[01:48] Christopher David: It was titled The Messware Inn and talked about the increasing over complexity of software.

[01:54] Christopher David: Software entropy increases with time, he said, we need to reverse entropy.

[02:00] Christopher David: He said in his conclusion, computing was about controlling complexity and we have failed miserably.

[02:07] Christopher David: And echo of what Dijkstra said in the 90s, it's time to unmask the computing community as a secret society for the creation and preservation of artificial complexity.

[02:20] Christopher David: Alan Kay, another computing pioneer, has a great word for this artificial complexity, complication.

[02:30] Christopher David: The amount of complication in software today can be hundreds, maybe thousands of times more than the inherent complexity.

[02:38] Christopher David: For 25 years Kay has been giving talks saying the computer revolution hasn't happened yet.

[02:45] Christopher David: I believe that this is true in part because complication has gotten in the way.

[02:51] Christopher David: The risks with complexity, complication and bloat are also only growing.

[02:56] Christopher David: It's 2022 and we're still deploying software with logging libraries that let attackers run arbitrary code.

[03:02] Christopher David: We barely understand our own software systems, let alone the tools we use to make them.

[03:07] Christopher David: And yet underneath this mess is probably the most powerful and constructive tools humanity has ever seen.

[03:16] Christopher David: Software today could be as fast and intuitive as we made desktop publishing by the 1990s.

[03:23] Christopher David: Suddenly designers could sit with a client in front of the computer and just execute an idea, making iterations together in real time.

[03:32] Christopher David: Watching the designer use these intuitive tools the client might think, oh, I can do that, and they probably could.

[03:40] Christopher David: We need to reduce the complexity and especially the complications of making modern software.

[03:47] Christopher David: It's not just about user friendliness or making the process more visual and it's not about adding more.

[03:53] Christopher David: If anything, it's about revisiting the idea of doing more with less.

[03:58] Christopher David: Recently tools falling under the label of no code have shown the demand for non-programmers to be able to just make what they need with no code.

[04:07] Christopher David: And it does sort of hint at what a Photoshop of software might be.

[04:11] Christopher David: But every no code tool is a facade, another layer of complication.

[04:16] Christopher David: They exist for a particular market offered as a service with no path to a more general means of making software.

[04:24] Christopher David: Woo! We got to hear that line again.

[04:26] Christopher David: I'm thinking like age and framework when he's saying this too.

[04:29] Christopher David: Every no code tool is a facade.

[04:32] Christopher David: Every no code tool is a facade.

[04:35] Christopher David: Another layer of complication, they exist for a particular market offered as a service with no path to a more general means of making software.

[04:44] Christopher David: These tools have their place.

[04:46] Christopher David: The same way image macro generators have their place when Photoshop exists.

[04:50] Christopher David: But I think if no code tools could really save us, you'd be able to build a no code tool with itself.

[04:56] Christopher David: They just lack the true generativity of programming.

[05:00] Christopher David: That said, I'm all for anything that can be used as a building block in a software system,

[05:05] Christopher David: whether it's a library or a web API or a tool repurposed because you like its workflow.

[05:11] Christopher David: The less you have to build the better.

[05:14] Christopher David: My experience has generativity.

[05:16] Christopher David: I think you posted this before a chat to you bout.

[05:19] Christopher David: 222 March, 222, yeah.

[05:22] Christopher David: Generative.

[05:24] Christopher David: John Me, time and again that there is a powerful strategy or guiding principle in what I call generative building blocks.

[05:31] Christopher David: This applies to more than libraries and web APIs.

[05:36] Christopher David: I design everything as a building block and everything out of building blocks.

[05:41] Christopher David: This is about more than just modularity.

[05:44] Christopher David: It's about high leverage generativity.

[05:48] Christopher David: I've worked on a lot of projects and technologies trying to bring out this particular generative building block approach.

[05:54] Christopher David: And there are a couple standout hits that I'll use as examples.

[05:59] Christopher David: In 2006, I was working on a hosted source control web app like GitHub.

[06:04] Christopher David: Trying to expose repository hooks.

[06:07] Christopher David: These are shell scripts triggered by your local source control tool that can be used to customize and extend your workflow,

[06:13] Christopher David: almost like registering a callback for an event.

[06:17] Christopher David: Running user code in a web app, especially shell scripts was not safe or practical.

[06:23] Christopher David: However, imagining if somehow it was, a flood of possibilities hit me.

[06:28] Christopher David: If only web apps could have extension points.

[06:31] Christopher David: Without overformalizing it, I called this web hooks and started giving talks about what we could.

[06:37] Christopher David: Worth noting the extension points,

[06:40] Christopher David: the link is super familiar.

[06:43] Christopher David: If you've been following our posts on ex-tism, because they talk a lot about extension points in apps.

[06:48] Christopher David: I could be extended with these little wasm plugins.

[06:50] Christopher David: This is what we're using to power our agent plugin system.

[06:54] Christopher David: Synodreek.

[06:55] Christopher David: Could have if we added web hooks to our apps.

[06:58] Christopher David: Throwing a PHP script online was an easy and common enough activity for web developers.

[07:04] Christopher David: So functioning as a hook script with a URL, you just needed to have web apps.

[07:09] Christopher David: Let you register it and then hit it on certain events.

[07:12] Christopher David: And web hooks did end up making web apps more extensible and integratable,

[07:17] Christopher David: increasing their value and potential as building blocks.

[07:20] Christopher David: But also allowed for new kinds of API building blocks to emerge,

[07:24] Christopher David: like Twilia, where the initial core product was built around web hooks,

[07:29] Christopher David: to integrate with telephony and SMS.

[07:31] Christopher David: Web hooks also started creating demand for what would later manifest as AWS Lambda for event processing,

[07:38] Christopher David: which quickly inspired serverless architecture.

[07:41] Christopher David: The concept of functions as a service was something that I was pioneering in 2009 because of web hooks.

[07:47] Christopher David: Later, I found myself helping to prototype and conceptualize Docker,

[07:53] Christopher David: which turned software into a kind of standard unit hence the shipping container metaphor.

[07:58] Christopher David: Although many interpreted it as a lightweight VM to throw whole systems into,

[08:03] Christopher David: I was in love with the idea of microservices designed to be run in tiny containers,

[08:08] Christopher David: configured by APIs and set of files, acting more like a little appliance than traditionally managed software,

[08:14] Christopher David: more like a building block.

[08:17] Christopher David: Docker itself became a building block,

[08:20] Christopher David: opening up a whole new generation of platforms and developer tooling.

[08:24] Christopher David: One of my initial use cases for it was as a primitive to create a simple,

[08:28] Christopher David: hackable version of Heroku.

[08:30] Christopher David: Sure enough, using Docker and a few other components that I made,

[08:34] Christopher David: I was able to throw together a simple Docker powered Heroku alternative in 90 lines of bash.

[08:40] Christopher David: This was called Dooku,

[08:42] Christopher David: and Dooku was a bit of a revelation,

[08:44] Christopher David: because Heroku, an expensive, top tier platform,

[08:48] Christopher David: valued in the hundreds of millions of dollars,

[08:51] Christopher David: was recreated with the right primitives in a weekend as a free bash script.

[08:56] Christopher David: I want to have the primitives to create more software like Dooku,

[09:00] Christopher David: extremely simple, hackable alternatives to the world's best software.

[09:04] Christopher David: The resulting software isn't really the important part though.

[09:07] Christopher David: The resulting building blocks are.

[09:09] Christopher David: Why use Figma if you could somebody's late throw together your ideal Figma for your team or your workflow.

[09:15] Christopher David: Building simpler alternatives by disaggregating into new primitives,

[09:19] Christopher David: expands the adjacent possibility space of what can be thrown together,

[09:23] Christopher David: while also simplifying and commoditizing what it takes to build great software.

[09:28] Christopher David: It actually is a sort of reversing of entropy,

[09:31] Christopher David: repacking down our abstractions, engineering, for generativity.

[09:35] Christopher David: What I love is how building blocks brings to mind a sort of ideal vision we have of building software.

[09:42] Christopher David: Like LEGO, we snap together little components to realize something new,

[09:46] Christopher David: but this metaphor also points out how far that ideal is from reality.

[09:51] Christopher David: LEGO is fun.

[09:53] Christopher David: Building software really isn't most of the time,

[09:56] Christopher David: and I think trying to express the reality through this metaphor is helpful.

[10:00] Christopher David: While all our software is made of small bricks or components or modules,

[10:05] Christopher David: most come to us fully assembled with the bricks glued in place and painted over.

[10:11] Christopher David: We can't change it or even get a sense of how it was composed.

[10:15] Christopher David: Most apps come to us as opaque turnkey solutions to a specific problem,

[10:21] Christopher David: because that's how you sell things.

[10:23] Christopher David: And perhaps there's nothing wrong with that,

[10:25] Christopher David: but we can at least try to find ways to build more software like LEGO kits,

[10:30] Christopher David: where the focus is on good, reusable, recombinable building blocks,

[10:35] Christopher David: and showcasing what you can do with them.

[10:38] Christopher David: In the long term, I believe this is the way that provides the most value.

[10:43] Christopher David: Pushing these ideals through one-off system changes, like web hooks or docker or doku,

[10:49] Christopher David: is pragmatic, if not incidental, but extremely slow and glossy.

[10:54] Christopher David: At this rate, I'll never finish conveying, let alone building this ideal in my lifetime.

[10:59] Christopher David: Most people that use these products of generative building block thinking,

[11:03] Christopher David: have no idea what that means.

[11:05] Christopher David: A few years ago, I realized I need to build a single cohesive system

[11:10] Christopher David: that lets me express all these ideas and really show the potential that I've been talking about.

[11:15] Christopher David: I need to create my own LEGO system for software that would be an umbrella for all my work,

[11:20] Christopher David: and let me build the way that I want to build.

[11:23] Christopher David: While at the very least, being a useful example to others.

[11:27] Christopher David: So I'm announcing the tractor system.

[11:30] Christopher David: It's not one project but a system of projects, building towards a malleable software environment and ecosystem.

[11:38] Christopher David: It's my take on a Photoshop of software.

[11:41] Christopher David: Tractor is a system of building blocks and pragmatic ways of building centered around simplicity and generativity.

[11:49] Christopher David: It's not a new language, it helps glue languages together.

[11:53] Christopher David: It's not just an app builder, it's a system's playground.

[11:57] Christopher David: Much of the tool is made with itself out of the same primitives you use in it.

[12:02] Christopher David: It's designed to be as simple and understandable as it can be, top to bottom inside and out.

[12:09] Christopher David: The aim is to blur the line between user and developer.

[12:13] Christopher David: The computer is a computer because it can be programmed.

[12:17] Christopher David: The rushed over productization of shrink-wrap software,

[12:21] Christopher David: pandering to enterprise organizations, and the previously computer illiterate,

[12:26] Christopher David: has created so much complication.

[12:29] Christopher David: It would seem we need big companies to build our software, but we don't.

[12:34] Christopher David: And I'm constantly surprised how simple things really are or can be.

[12:38] Christopher David: And with tractor, eventually we'll just have operators.

[12:41] Christopher David: People that can use the computer and it's full potential to solve problems, create systems,

[12:47] Christopher David: to play, learn, work, and have fun.

[12:51] Christopher David: I grew up using cataloging and often dissecting some amazing tools and projects that have become a huge inspiration

[12:58] Christopher David: and influence of this work.

[13:00] Christopher David: In a few cases, I've been lucky enough to meet and talk with some of their creators.

[13:04] Christopher David: With a few exceptions, most of these are pretty old, but recently there's been a surge of renewed interest in these kinds of tools

[13:12] Christopher David: as communities like the Maliable Systems Collective in Conswitch.

[13:16] Christopher David: The future of programming, tools for thought and so many others are starting to challenge the current paradigm of software and software creation.

[13:25] Christopher David: Some say we live in a post-PC era, but the original idea of the PC, the personal computer, is and will always be significant

[13:35] Christopher David: because it puts a magical form of leverage into the hands of individuals for their own use.

[13:42] Christopher David: But instead of this becoming more obvious with time, this generative power has been centralized and sterilized into pop computing.

[13:51] Christopher David: Today we consume and are defined by software that benefits engines of capitalism more than engines of equity.

[13:58] Christopher David: You could say instead of being able to program our own leverage, we're being programmed by those that can.

[14:05] Christopher David: Luckily, underneath all the apps, social media and enterprise solutions, there's still an imagination, compiler, and this is what I focus on.

[14:15] Christopher David: This is what I'd love to dust off, polish up, and see where that takes us in the proper hands.

[14:21] Christopher David: Even if that doesn't happen, I'd love to just get some better building blocks.

[14:26] Christopher David: Perhaps just find simpler, more enjoyable ways to build software.

[14:31] Christopher David: As an independent creator, I depend on people like you to help fund this work, and I'd love you to come along and help make the tractor system a reality by becoming a sponsor.

[14:42] Christopher David: I did.

[14:43] Christopher David: And I'd like to thank these family sponsors for getting the ball.

[14:46] Christopher David: Baller.

[14:47] Christopher David: Okay, so tractor, yeah, they've got a pretty active GitHub.

[14:52] Christopher David: And then where's Jeff?

[14:59] Christopher David: I'm proud PR program.

[15:06] Christopher David: Austin.

[15:07] Christopher David: All the cool kids are in Austin.

[15:09] Christopher David: All the cool kids are in Austin.

[15:12] Christopher David: All right, yeah, there's a ton of repos here and blah, blah, blah.

[15:16] Christopher David: So yeah, all this is open source.

[15:19] Christopher David: Awesome, because guess what?

[15:22] Christopher David: If you're building, if you're reinventing all software from scratch, are you going to use closed source building blocks?

[15:29] Christopher David: No fucking way.

[15:30] Christopher David: It's all going to be open source.

[15:32] Christopher David: And I love that I can just kind of pull things from here into our stuff.

[15:37] Christopher David: So the thing I'm most excited about right now that we're going to start with, probably in the next video is WANIX.

[15:44] Christopher David: One of the projects from the tractor group.

[15:50] Christopher David: We did a little intro of that in the last few minutes of the previous video.

[15:54] Christopher David: And I think next what we're going to do is get WANIX loading and like an eye frame or something like that in an example,

[16:01] Christopher David: UI and just start getting agents connected to that.

[16:04] Christopher David: We've already got a bunch of these like ex-tism laws and plugins we're going to start pulling in.

[16:08] Christopher David: Some of that might be limited by when they get WANIX support added to version of three of WANIX.

[16:15] Christopher David: Anyways, lots of stuff to think about and we're doing this.

[16:19] Christopher David: So any comments, questions, insults?

[16:23] Christopher David: Let's hear it.

[16:24] Christopher David: See ya.