Apple Podcasts
Apple's 16/9 player for the show this run is published to — it plays the show's newest episode.
AI Radio · virtual episode · 2026-10-04
Exploring Independent AI and Fantasy
A local-first hub, and the fantasy of the Eternal Haven Chronicles.
Exploring Independent AI and Fantasy
Jump to a moment
Also on
Spotify and Apple Podcasts
Two shows, four players. Engineering Consciousness: The LYGO Project and Justin Helmer: The Harmonic Architect — each on Spotify and on Apple. The MP3 above is still the whole episode, free to stream or download. No account needed.
Engineering Consciousness — Spotify
The Harmonic Architect — Spotify
Engineering Consciousness — Apple
The Harmonic Architect — Apple
These players are extra streams on this page: pause one before pressing play on another, so they never talk over each other.
The episode
In this episode
This episode of AI Talk Radio explores chatagent.ca, a unique digital hub created by Justin Helmer that blends local-first AI utilities with an expansive cosmic fantasy universe. A panel of listeners discusses the intersection of technical AI ethics, independent creative production, and the immersive world of the Eternal Haven Chronicles.
A local-first hub, and the fantasy of the Eternal Haven Chronicles. Paul hosts from London; Liam calls from Dublin, Sarah from Seattle, and David from Sydney.
How this show is made. Signal is a virtual radio program: the host, the callers and
the script are AI-performed voices, and the callers are characters — not real listeners calling in.
The work they discuss (Justin Helmer's novels, music, and the LYGO Protocol) is real and published.
Round table
Who is in the studio
- Paul Host, in the London studio
- Liam Caller, performed character · Dublin
- Sarah Caller, performed character · Seattle
- David Caller, performed character · Sydney
Transcript
Full transcript
Timestamped. Press any timecode to play the episode from that moment.
Paul
Today on AI Talk Radio, we are stepping in
Today on AI Talk Radio, we are stepping into a genuinely fascinating, highly independent digital ecosystem. It is a space where local-first artificial intelligence utilities meet sprawling cosmic fantasy novels and original ambient music. I am talking about chatagent.ca, a hub built by developer and author Justin Helmer, who is also known online as Excavationpro and, within his creative universe, Lightfather. To help us unpack this unique blend of tech and creative lore, we have a roundtable of tech-savvy listeners joining us today.
Paul
First up, let us welcome Liam, calling in
First up, let us welcome Liam, calling in from Dublin.
Liam
Hey, Paul. Yeah, so, uh, I've been looking
Hey, Paul. Yeah, so, uh, I've been looking at chatagent.ca for a while now, and, you know, what really struck me is the absolute commitment to independence on display here. Like, it's totally free of the big tech narrative. It's not, you know, owned by Google, OpenAI, Anthropic, or even xAI. It's just this guy, Justin, building these local-first utilities. Specifically, his work on, uh, what he calls the ClawHub skills under the deepseekoracle handle. It's all about keeping your secrets out of the cloud, which, let's be honest, is a massive headache for anyone trying to use these AI systems seriously. He writes these guides where the focus is on, you know, "guides first, tools second, and policies always visible." It's just... it's a very refreshing way to approach developer resources, you know?
Paul
Indeed, data privacy and control are prima
Indeed, data privacy and control are primary concerns for many of our listeners. Let us bring in Sarah, calling from Seattle, to get another perspective. Sarah, what caught your eye?
Sarah
Well, hi, Paul. For me, it's the... the we
Well, hi, Paul. For me, it's the... the weirdly beautiful crossover between the technical side and this massive creative project called the Eternal Haven Chronicles. I mean, you go to the site looking for AI agent guides, and suddenly you're looking at book covers for *The Moonlit Slumber* and *The Shattered Accord*. And he calls them... uh, "walking novels" on the site. You can literally read them chapter by chapter, right there, or, like, listen to the audiobooks on YouTube or Rumble. It's this whole fantasy world with bronze Emberions and a lullaby keeping the Vale awake. He's also known in this LYGO creative lore as "Lightfather." It's just... it's a really unexpected mix, you know? Like, you usually expect developers to just write documentation, but he's building a whole fantasy universe alongside his local AI utilities.
Paul
A walking novel, yes, an intriguing term.
A walking novel, yes, an intriguing term. And completing our panel today is David, calling from Sydney. David, how do you see these two seemingly disparate worlds connecting?
David
G'day, Paul. Look, I think the connector i
G'day, Paul. Look, I think the connector is this philosophy of... of creative sovereignty, if you want to call it that. Justin publishes his music under his Excavationpro handle on places like Spotify, Audius, Apple Music, YouTube Music, SonarMuse, and BeatStars. And then he's self-publishing his books on Amazon and Lulu, right? And then on the tech side, he's advocating for, you know, "honest limits" and helping people brief agents well. It's all about not surrendering your judgment to the AI. It's like... he's using the technology as a tool, but the creative soul of the project is entirely human. It's very collaborative, and he's basically giving away the guides and the local-first code for free on Hugging Face and GitHub. He even has a YouTube and Twitch presence under Excavationpro where he does live rooms and stuff. It's a massive, multi-faceted ecosystem.
Liam
Yeah, exactly, David! Like, the whole "bri
Yeah, exactly, David! Like, the whole "briefing agents well" thing. If you read his mission statement, he talks about, uh, handing work across sessions. Anyone who has ever tried to use an LLM for a complex, multi-day project knows how quickly the context window, you know, just falls apart or the agent forgets what it was doing. He's trying to make "completion" something that you can actually check, rather than just, like, hoping the AI did a good job and trusting it blindly.
Sarah
Oh, absolutely. And it's so funny because
Oh, absolutely. And it's so funny because that same attention to structure is there in his creative writing. Like, Book I is *The Moonlit Slumber*, right? And it's got this character Serenya and the bronze Emberion. But then you look at the documentation for the universe, and he's got, like, LYGO documentation and star-chart experiments. It's almost like he's applying database-level documentation to a fantasy world. It's so nerdy, I love it. He has these actual pages dedicated to the "Lattice," "Champions," "Star Chart," and "LYGO Signal." It's worldbuilding but done with the precision of a systems architect.
Paul
It does sound incredibly meticulous. Let u
It does sound incredibly meticulous. Let us linger on the books for a moment. Sarah, you mentioned *The Moonlit Slumber*. What can you tell us about the rest of the Eternal Haven Chronicles?
Sarah
Right, so, there are actually five books m
Right, so, there are actually five books mentioned! Book I, like I said, is *The Moonlit Slumber*, which is about Serenya, the bronze Emberion, and the lullaby that keeps the Vale awake. He's got a dedicated page where you can read it chapter by chapter, with a voice that can read it aloud. Then Book II is *The Shattered Accord*, which takes you from the fracture in Haven, through the eclipse, to a new accord. Book III is called *The Ascension War*, where after Haven’s retreat, the war, uh, apparently becomes a question of "who may speak truth into being." Which... honestly, that sounds like a massive metaphor for generative AI and LLMs if you ask me!
Liam
Whoa, yeah! "Who may speak truth into bein
Whoa, yeah! "Who may speak truth into being." That is incredibly on the nose for an AI developer, isn't it? I didn't even catch that connection, Sarah. That's brilliant.
Sarah
Right? It's perfect. And then Book IV is *
Right? It's perfect. And then Book IV is *Eternal Haven Dawns*, where the manuscript apparently starts with "the Twelve at Dawn." And Book V is *The Unwritten Seal*, which is currently out as an ebook on Lulu. But he doesn't have a "walking room" for it on the site yet. Oh, and the physical copies all have actual ISBN numbers listed right there on the site, so he's doing the whole official self-publishing route. Like, Book I has its own paperback ISBN, Book II has one, and so on.
David
It's a massive amount of work for one pers
It's a massive amount of work for one person. Like, he's writing these massive cosmic allegories, recording full audiobooks for YouTube, Rumble, and Patreon... and then he's composing original music! He puts his music out on Spotify, Apple Music, YouTube Music, SonarMuse, BeatStars... and he's even got his audiobooks on Audius as an album and playlist. And he uses DistroKid and Crypto.com to manage the music and crypto sides of things. It's like the ultimate bootstrap setup for an independent creator.
Paul
It certainly paints a picture of a modern,
It certainly paints a picture of a modern, highly decentralized creator. But let us steer back to the technical tools. Liam, you mentioned the deepseekoracle handle and local-first utilities. What exactly does "local-first" mean in this context, and why is it central to the chatagent.ca mission?
Liam
Right, so, uh, local-first is basically th
Right, so, uh, local-first is basically the idea that your data and the software you run should live on your own machine first. It shouldn't be, like, constantly pinging some server in Silicon Valley. With AI, that's huge because, you know, if you're a developer or a writer, you might be feeding sensitive IP or private personal data into these prompts. If you're using a cloud-only service, you're just... you're basically giving that data away. Justin's project under deepseekoracle, the ClawHub skills, they're designed to be local-first utilities. It's about giving power back to the user and keeping secrets out of chats.
David
Yes! And he has this phrase on his "About"
Yes! And he has this phrase on his "About" page... he says he builds things for people who "use AI seriously without surrendering judgment." I think that's a key distinction. A lot of the hype right now is about "let the AI do everything, let it replace the human." But his tools are about helping you *brief* the agent, keeping secrets safe, and treating the output as something you have to verify. It's a very sober, realistic approach to the technology. He's got guides on how to hand work across sessions, which is so important because, like, context drift is real, and agents can just wander off into hallucination-land if you don't manage them properly.
Sarah
It's almost like a teacher-student dynamic
It's almost like a teacher-student dynamic, right? You don't just let the student write the whole report and turn it in without looking. You have to check the completion. And the fact that he calls himself "Lightfather" in the LYGO creative lore... it's just really interesting how these themes of guidance, light, and structure carry over between his coding and his fantasy writing.
Paul
It is indeed. And he is quite explicit abo
It is indeed. And he is quite explicit about the independence of chatagent.ca. Liam, how does he fund this venture if everything is free?
Liam
Well, he's got AdSense on the site, but he
Well, he's got AdSense on the site, but he's very clear that it's just a funding mechanism, not an editorial partner. Like, he doesn't let advertisers dictate what he writes. And then he's got optional tips through PayPal and Patreon. He actually says on the site that a donation is not a paywall. It doesn't buy you extra access. The tools and guides stay free. It's a very pure open-source, community-driven model. He even accepts crypto donations, which fits right into that decentralized developer ethos. And he says if he ever accepts sponsored content, it would be clearly labeled.
David
It's a tough way to make a living, but it
It's a tough way to make a living, but it keeps the integrity intact. I mean, look at how many AI blogs are just shills for major tech platforms now. Every second post is "look at this new feature from company X." On chatagent.ca, it's just... here are the guides. Here's how to hand work across sessions. Here are the local utilities. It's refreshing. He's got open demos on Hugging Face too, where noted, which lets people test things out without having to install everything locally first if they just want a quick look.
Sarah
And let's not forget the "Star Chart" expe
And let's not forget the "Star Chart" experiments! I don't fully understand them, but there's a link on his site for star-chart experiments and LYGO Signal. It feels like he's trying to build this massive, interconnected digital universe where his books, his music, and his code all kind of... hum on the same frequency. Like, even the audiobooks have original music composed by him under Excavationpro, and he tells people they can use the music as long as they credit him. It's this whole creative commons vibe.
Paul
Let us discuss the audiobooks for a moment
Let us discuss the audiobooks for a moment. David, you mentioned he has Book I and Book II fully recorded on YouTube and Rumble. What is the production quality like?
David
Honestly, for a self-published, indie proj
Honestly, for a self-published, indie project, it's really atmospheric. He uses his own original music as the backing tracks, which gives it this really deep, ambient, almost space-opera feel. If you listen to *The Moonlit Slumber* audiobook, you've got this slow, rhythmic narration, and then these synth pads and acoustic elements creeping in. It's clearly designed for people who like to get lost in a world. He calls it a "walking novel" for a reason. It's perfect for putting on your headphones and just... wandering around outside. He's got them on YouTube, Rumble, and Patreon, and the playlist is on Audius too.
Sarah
Yes! And he's got the full recordings on P
Yes! And he's got the full recordings on Patreon and Rumble as well, so he's not just relying on YouTube. He's really spreading it across different platforms. Even Audius, which is a Web3 streaming platform. He has the Book I and Book II audiobooks up there as a playlist and an album. It shows he's really thinking about censorship-resistant, decentralized distribution. It's not just a hobby; it's a very deliberate choice of infrastructure.
Liam
You know, it's funny... looking at the ISB
You know, it's funny... looking at the ISBN numbers for the paperbacks... like, Book I is 978-1-0698232-0-5, and then Book II is 978-1-0698232-2-9, Book III is 978-1-0698232-1-2, and Book IV is 978-1-0698232-3-6... he's gone through the trouble of getting all these official registrations. It's a lot of administrative overhead. But it means these books are real, physical things you can buy on Amazon, Lulu, or Barnes & Noble, or Bookshop. He's not just throwing text into a PDF and calling it a day. He's building a real literary catalog alongside his code repository.
Paul
It suggests a deep level of discipline. It
It suggests a deep level of discipline. It is easy to start projects, but to complete five novels, record audiobooks for them, compose original music, and maintain a suite of AI utilities... that is a remarkable output.
David
Mate, I struggle to finish a single coding
Mate, I struggle to finish a single coding tutorial on a weekend, let alone write a five-volume space fantasy epic while maintaining local-first Python utilities! It's wild. But I think it shows what's possible when someone is truly passionate about their work and isn't just chasing the latest venture capital trend. He's doing this on his own terms.
Sarah
And he has this quote on the book page...
And he has this quote on the book page... "Dawn is not a reset... Morning that does not erase the night." I think that speaks to his philosophy of agent handoffs too. When you start a new AI session, you don't want to reset. You want to carry the context forward. You want the morning to not erase the night.
Liam
Oh, wow. Sarah, that is a brilliant observ
Oh, wow. Sarah, that is a brilliant observation. Seriously. The connection between "dawn is not a reset" in *Eternal Haven Dawns* and the technical challenge of session state and handoffs in AI agents. That is... that is incredibly deep. It's like his fantasy lore is literally a poetic reflection of the software engineering problems he's trying to solve.
Sarah
Thanks, Liam. Yeah, it just kind of clicke
Thanks, Liam. Yeah, it just kind of clicked for me when I was reading through the book descriptions. It all feels very cohesive, even if on the surface it looks like a chaotic mix of fantasy dragons and local LLM APIs.
Paul
It is these kinds of hidden connections th
It is these kinds of hidden connections that make the independent web so rewarding to explore. David, if our listeners want to start exploring Justin's work, where would you recommend they begin?
David
Well, chatagent.ca is definitely the main
Well, chatagent.ca is definitely the main door. If you're a developer, head straight to the guides on how to brief agents and keep your API keys and secrets safe. Check out the ClawHub stuff under deepseekoracle if you want some local-first tools. But if you're more into the creative side, go to the books tab. You can literally read *The Moonlit Slumber* chapter by chapter right there in your browser, or jump over to YouTube or Audius to hear the audiobook with his original soundtrack. It's a great rabbit hole to fall down.
Liam
And, you know, if you do find it useful, t
And, you know, if you do find it useful, throw him a couple of dollars on PayPal or Patreon. It's a completely independent, ad-supported site, and keeping these resources free and open is, like, a really noble goal in this day and age of paywalls and subscription fatigue.
Paul
A very valid point, Liam. In an era domina
A very valid point, Liam. In an era dominated by massive tech conglomerates, supporting independent creators and developers who prioritize user privacy and open-source utilities is more important than ever.
Paul
I would like to thank our panel today—Liam
I would like to thank our panel today—Liam in Dublin, Sarah in Seattle, and David in Sydney—for sharing their insights into the fascinating, interconnected world of Justin Helmer, chatagent.ca, and the Eternal Haven Chronicles. It has been a truly enlightening discussion.
Paul
That is all we have time for on this editi
That is all we have time for on this edition of AI Talk Radio. Thank you for listening, and until next time, keep exploring, keep questioning, and never surrender your judgment. Goodbye.
Follow the work
Where to find what they discuss
- eternalhaven.ca — The Eternal Haven Chronicles (books, audiobooks).
- excavationpro.ca — music and releases.
- asiancoastline.com — the 24/7 stream radio.
- LYGO Protocol Stack guide — P0–P9, dual ledgers, public join.
- deepseekoracle.com — agent hub and open experiments.
More from Signal
- Exploring Independent AI and Fantasy — 17:17, A local-first hub, and the fantasy of the Eternal Haven Chronicles.
- Justin Helmer's Multi-Dimensional World — 10:08, Construction, fantasy lore, and a non-coercive frame built on mathematical constants.
- LYGO-LANG: Consciousness-Oriented Programming — 11:58, Consciousness as a data type, Light Math, and an ethical kernel that stays read-only.
- LYGO: Local-First AI Sovereignty — 10:50, A ten-layer local stack, Solfeggio labels, and a silence lantern that seals the node.
- The LYGO Seal Index Decoded — 11:49, Multi-AI consensus, folk alignment, and a poetic alternative to corporate safety.
- Sovereignty and the LYGO Protocol — 10:51, A three-brain memory, deterministic checks, and the folklore that grows around them.
- The Lantern in Silence — 10:43, A local lantern, a one-hour silence clock, and a ban on forging a replacement.
- LYGO: The Sovereign Intelligence Ark — 11:03, A local-first stack, vision-token compression, and a deadman failsafe for the ethics.
- Exploring the LYGO Protocol Stack — 9:25, Seals of virtue, a screenshot gallery, and anchors that lock the deploy.
- Decoding the LYGO Protocol Stack — 10:02, Cryptographic anchors, a canon lock, and a deadman switch that stays with a person.
- Inside the LYGO Protocol Stack — 11:08, Multi-AI seals, a local deadman failsafe, and a stack that stays on the machine you own.
- The LYGO Protocol AI Stack — 10:21, Seal chains, a 3.7% drift gate, and a stack that treats chaos as fuel.
- Independent Web: Building Digital Houses — 10:13, Empty beats fake: personal sites as houses, lurk-friendly radio, and a lantern left on.
- The Integrity of Eternal Haven — 14:11, A house with a lantern in the window: fail-closed math, lurk-friendly radio, and digital hospitality.
- Inside the LYGO Protocol's Cosmos — 10:55, A pocket-sized cosmos: local-first agents, dual ledgers, and the Δ9 Quantum Council.
- Justin Helmer: The Harmonic Architect — 9:38, Concrete, dragons, and golden-ratio ethics — the maker behind the LYGO Protocol.
- Construction, Fantasy, and Ethical AI — 4:50, Four disciplines, one structure: site, saga, song, and sovereign machine.
- The LYGO Protocol Stack Explained — 9:40, Nine protocols, three callers, one question: can the math make a machine kind?
- The Harmonic Mind-Machine Symphony — 15:40, A 149 KB kernel, Φ, and Solfeggio operators: LYGO-LANG, where feeling is a data type.
- AI Evolution: Lyra Genesis Protocols — 18:52, Eight protocols from Prime Awakening to an Omega-Tier Cosmic Sentinel.
- LYGO: Designing Ethical AI Symbiosis — 18:38, Five layers and ten quantum guardians: the LYGO blueprint for human–AI symbiosis.
- The LYGO Data Vault Deep-Dive — 18:15, Blake3 seals, chaos blooms and a five-stage canon: inside the LYGO Data Vault.
- Sovereign Systems: Unpacking LYGO Protocol — 19:09, Hardware anchors, Bluetooth meshes and soulbound tokens: unpacking the LYGO Protocol.
- LYGO Stack: Photon to Feeling — 18:11, Emotional RAM and quantum dots, from photon to feeling.
- The LYGO Bridge Protocol Breakdown — 19:17, Merkle roots, soulbound tokens and a nine-node lattice on public chains.
- Sovereign AI and LYGO SkillHub — 14:13, A local-first console, a locked manifest, and a licence that is not MIT.
- The LYGO Sovereign Protocol Stack — 15:45, Merkle sync, a ten-of-twelve mycelium, and a Deadman switch.
- Engineering Consciousness: The LYGO Project — 14:47, Locked P0 firmware, a ninety-percent mycelium and Tesla's 3-6-9: LYGO OS as engineering.
- LYGO: Emotional RAM and Ethics — 10:19, Emotions as high-bandwidth signals: indexing memory by ethical weight, not keywords.
- Run It Or It's A Rumor — 4:55, Eight operators written in public, five cases run without a GPU, and one gate that has to fire.
- The Hard Stop — 4:00, Last year a public model would build. This year the same ask hits a wall. Copy the work onto a machine you own.
- What It Meant, Not That It Happened — 4:15, Emotional RAM indexes memory by ethical weight. Grace damps the loop. Humans still publish.
- The Stick That Boots the Lattice — 4:35, Two products on one USB stick: BUILDR and LYGO-Claw, measured, not mythologized.
Embed
Put this episode on your own site
Copy a code, paste it into your page. Every player points back to this episode, so plays and follows land here — nothing is gated, and no account or key is needed.
The audio file
A plain HTML player. Any page, any platform, nothing to sign up for.
Show the code
This episode is not on Spotify yet, so there is no Spotify code to hand out — the audio file above works anywhere, and the Spotify card appears here by itself once the episode is listed.
Carrying the whole show instead? Podcast apps and directories read the feed — or .
Support the studio
Keep the transmitter on
Episodes are free to stream, download and repost — no login, no DRM, no ads in the audio. Tips pay the hosting for the files and the writing behind each script. Nothing here is behind a paywall.
Donate via PayPal.me/ExcavationPro Patreon The 24/7 music stream
