AI Radio · virtual episode · 2026-09-27
Sovereign AI and LYGO SkillHub
A local-first console, a locked manifest, and a licence that is not MIT.
The episode
In this episode
The LYGO SkillHub and Console, focusing on the importance of sovereign, local-first artificial intelligence running entirely offline on personal hardware. A roundtable of tech experts discusses the project's core philosophy of transparency, security through manual consent, and its community-driven distribution model.
The SkillHub and Console in build 1.5.6 — gemma4-12b and a coder 7b running with no cloud endpoints, RAW packages held behind a consent step, and a sealed-source audit trail that caught a build the panel says would have booted with no brain.
Round table
Who is in the studio
- Paul Host, in the London studio
- Dave Caller, performed character
- Sarah Caller, performed character
- Marcus Caller, performed character
Transcript
Full transcript
Timestamped. Press any timecode to play the episode from that moment.
Paul
Cold open: sovereign, local-first AI
Welcome to AI Talk Radio. I'm Paul, broadcasting from a very quiet London studio. Tonight, as the city wind down, we are stepping into the relaxed, reflective world of sovereign, local-first artificial intelligence. Specifically, we're exploring the LYGO SkillHub and the latest releases of the LYGO LLM Console. It's a fascinating project about running deep, offline AI ecosystems on hardware you actually own. No cloud keys, no third-party tracking, just pure local compute.
Paul
Dave joins from Dublin
To talk us through this self-hosted universe, we have a wonderful roundtable of tech-savvy callers joining us. I'd like to welcome our first guest, Dave, calling in from Dublin, Ireland. Dave, welcome to the show.
Dave
Dave: a public catalog on chatagent.ca
Hey, Paul. Yeah, thanks. It's... uh, it's great to be here. I've been sitting here in the dark just, you know, watching the terminal scroll. It's a peaceful way to spend an evening. Honestly, the whole LYGO thing... it's really struck a chord with me because of that sovereign angle. It's steered by Justin Helmer, who a lot of folks in the dev community know as... well, Excavationpro or Lightfather. And, like, what he's built here with the SkillHub... it's basically this public catalog on chatagent.ca where you can pull these "deepseekoracle" skills from ClawHub, but you also have this... this gated, local download portal for these "FULL" operator packages. It's all about keeping your data on your own metal, you know?
Paul
Sarah joins from Sydney
A truly offline posture. Let's bring in Sarah, calling all the way from Sydney, Australia, to get a developer's perspective on this. Sarah, welcome.
Sarah
A brutally honest alpha: build 1.5.6
Thanks, Paul! Yeah, look, Dave is spot on. As a developer, what really, um, what really appeals to me about the LYGO project is just how brutally honest it is. We've just had this new alpha build drop... build 1.5.6. And, you know, instead of hiding the bugs under some corporate marketing speak, they literally list the known gaps right on the page. Like, they tell you straight up that three agent-gauntlet tasks are still failing. They explain it's a console mechanism gap, not the models themselves. And they even warn you that there's an intermittent GPU display-driver reset that they haven't proved is fixed yet. It's just... it's so refreshing to see that level of transparency.
Dave
The 1.5.6 RAG index write fix
Oh, absolutely. And, like, the big quality-of-life fix in this 1.5.6 alpha is actually a massive deal for anyone who's been running it heavily. In the older builds, the RAG index write... you know, Retrieval-Augmented Generation where the AI looks at your local files... it had this annoying habit of racing itself. If you had a busy console, it would just print "could not write the index" and fail. But in 1.5.6, they fixed that. They implemented... uh, they basically assigned one temp path per write, plus a write lock. So now, a busy console stops throwing those errors on a healthy day, and even a fresh install won't print it on its first boot. It just... it just works quietly in the background.
Paul
Running entirely locally?
That sounds like a much more stable foundation. And this is all running locally, correct? No external servers?
Sarah
Offline out of the box — and a USB CLAW stick
Oh, completely local, Paul. No cloud endpoints are enabled unless you manually go in and add your own API keys. Out of the box, it's 100 percent offline. And the setup options are wild. You've got these PC local setups, but they also have this thing called the "USB CLAW" stick build. It's basically a portable setup built for a USB drive. It ships with its own Python environment and its own engine, so... like, if you plug it into any Windows box, the host machine doesn't need a single thing installed. It just keeps its own save/ and models/ folders right there on the stick. It even looks for its generators inside the kit at a folder called toolssd-cpu if the host machine has no media root. It's incredibly clever.
Paul
Marcus joins from Austin
Fascinating. Now, let's complete our roundtable by introducing Marcus, who is calling us from Austin, Texas. Marcus, welcome to the discussion.
Marcus
Channel A: the public tentacle
Hey, Paul. How's it going? Yeah, I've been listening to Dave and Sarah, and, uh, you know, they're highlighting the exact reasons why I got interested in this. I've been looking closely at the differences between what they call Channel A and Channel B on the SkillHub. See, Channel A is the "public tentacle." It's what you install directly from ClawHub using npx clawhub@latest install deepseekoracle/ and then whatever skill slug you want. That's your safe, green security surface. It's great for strangers, store reviews, and all that. But then... then you have Channel B. That's the "FULL" operator portal. It's not published to ClawHub at all.
Dave
Channel B and the RAW engineer packages
Right, right. And Channel B... that's where you get the actual unlocked RAW engineer packages, isn't it, Marcus?
Marcus
Consent gates: Star Chart writes and pushes
That's it, Dave. We're talking Cyborg Kernel, Continuum, SkillSpector... the actual local GGUF agent portal. But, you see, the steward, Justin, has set up this really interesting philosophy around it. To download those FULL packages, you have to agree to some very specific, honest terms. There's this rule about consent and live writes. Like, you can pulse and verify locally all you want. But if you're doing live Star Chart writes, git pushes, or publishing to Hugging Face, the system requires explicit human consent. You have to pass an --i-consent flag. The agents aren't allowed to silently write to the live chart. It keeps the human firmly in the loop.
Sarah
17.8 GB across six files: Inno disk spanning
I love that. It's like a built-in safety valve. And, you know, the way they distribute these files is pretty unique too. Because the full packages are massive, right? They bundle the actual LLM weights. If you get the PC LOCAL FULL setup, you're looking at about 17.8 gigabytes across six files. And they have to use Inno disk spanning because, well, Windows won't load a single setup executable past about 4.2 gigabytes. So, you download this one small .exe which acts as disc one, and then five .bin files as discs two through six. You just keep them all in the same folder and run the installer. It installs without any network connection at all.
Paul
What actually runs in the console
And what kind of models are we talking about here? What's actually running inside this local console?
Sarah
gemma4-12b, a coder 7b, and local embeddings
Well, the big one is gemma4-12b. It handles text, images, and audio, and it comes with its multi-modal projector. They also ship it with qwen2.5-coder-7b as the "fast brain" for coding tasks, plus a local embeddings model. Now, gemma4-12b is a heavy lifter—it really wants about 10 gigabytes of RAM to run comfortably, though more is always better. If you're on a smaller machine, say with an 8 gigabyte GPU, you'd use the Qwen coder model for speed, and route the deeper image tasks through Gemma. But the cool thing is... the console is completely flexible. If you have a bigger GGUF model you already own, you just drop it into the models/ folder, hit "Scan drives" in the console, and it boots it up. No reinstall needed.
Dave
173.9 seconds per image on a CPU build
And don't forget the image generation, Sarah. That's one of my favorite parts. It has this built-in picture engine based on stable-diffusion.cpp. And again, they are so honest about the performance metrics. They tell you that on a CPU build with no CUDA, no graphics card, and no admin rights... it's only about a 12 megabyte add-on. If you run the standard Stable Diffusion 1.5 checkpoint, which is a 4.27 gigabyte file, it takes about 173.9 seconds—basically close to three minutes—to draw a single 512 by 512 image on a standard CPU. If you use a distilled 4-step checkpoint, it takes about 55 seconds. And if you run it on a free GPU card, it drops to 12.5 seconds. But they don't hide the CPU times behind fancy marketing. They put the 174-second figure right there in the docs so you know exactly what to expect.
Paul
Not a standard open-source licence
It seems honesty is a core theme of this entire project. Marcus, you mentioned the licensing and the terms earlier. How does that side of things work? It doesn't sound like a standard open-source license.
Marcus
Sovereign Licence 3.0, and no warranty
No, Paul, it's not. It runs under the LYGO Sovereign License version 3.0. It's free to use and free to build on, but it is explicitly not MIT. You can't use it for resale, rebranding, or white-labeling. The model weights themselves, like Gemma, keep their own Apache-2.0 licenses, of course. But the console itself belongs to the protocol. And they make it very clear: no warranty, no support promise. You run it on machines you trust, and the steward isn't liable for what you or an agent does after you install it. They even have these interesting names for the security protocols, like "TraumaCodex" for the protocol code, and the "Flame Ward" where a "burn" simply means quarantining bad data, not... you know, anything violent.
Dave
The sealed-source audit that caught 1.3.1
Yeah, it's got a very cool, slightly cyber-noir terminology to it. Like "Whisper lattice" and "Cyborg Kernel." But what I respect is how they verify the builds before publishing. They compile every single installer from a sealed, read-only payload in the canon vault. Then they clean-room restore it and run an audit scan to make sure there's no private data left in the build. In fact... uh, in one of the previous alphas, build 1.3.1, the scan actually caught a couple of pre-publish defects. It turned out the build was accidentally carrying 778 files of the steward's private transcript archive and a bench log! And the config file was still pointing to his personal vault drive instead of a generic path.
Sarah
Every download lists its SHA-256
Yeah! That would have booted with no brain on anyone else's machine. But because of their audit process, they caught it, stripped it out, rebuilt the installers, and re-ran the scan until it was completely clean. No transcripts, no private keys, nothing. That's why every single download has a SHA-256 hash listed next to it. They tell you straight up: run CertUtil -hashfile on Windows or sha256sum on Linux before you unzip or run anything. If the hash doesn't match, you delete it immediately.
Marcus
A monthly code, and a thank-you gate
It's a proper defense-in-depth mindset. And even the way they fund it is pretty unique. The downloads are free, and they don't lock the installer files behind some aggressive paywall. Instead, they have this Patreon system where they post a monthly code. You enter this code in your browser, and it unlocks the download buttons on the portal. It's more of a "thank-you gate" than a hard lock, because the plaintext code isn't even stored—your browser just remembers that you unlocked it for that month. And the actual build files are still publicly available on Hugging Face if you want to bypass the portal entirely. Plus, there's a PayPal tip jar which they describe as "optional fuel for hosting." It doesn't buy you extra rights or bypass security. It's just a tip.
Paul
A model built on technical literacy
It sounds like a community-driven model built on mutual respect and technical literacy.
Dave
1.3.2: letting a local browser reach the console
Exactly, Paul. It's for people who want to understand exactly what's running on their machines. Like, in build 1.3.2, they added a fix so a local browser could even reach the local console at all, by making the gateway answer the Private Network Access preflight request. It's these tiny, highly technical details that make you realize this is being built by engineers, for engineers. It's not trying to be a slick consumer app that hides the terminal. It embraces the terminal.
Sarah
Verify, install, fetch from a locked manifest
Yeah, and it encourages you to learn. The instructions are so simple: verify the download, run the installer, get a model using the fetcher script—which reads a locked JSON manifest to make sure nothing is pulled from a moving branch or a third-party mirror—and then just boot the console bat file. It's a self-contained sandbox. If you want to experiment with local AI without feeling like you're giving up control of your data, this is the way to do it.
Paul
A quiet local harbour
It certainly seems to offer an empowering alternative to the centralized cloud paradigms we see so much of these days. A quiet, local harbor for your own data and agents to run safely.
Paul
Thanks to Dublin, Sydney and Austin
Well, I think that is a wonderfully reflective note on which to draw our discussion to a close. I want to thank our fantastic panel tonight. Dave in Dublin, Sarah in Sydney, and Marcus in Austin—thank you all for sharing your insights into the LYGO SkillHub and Console.
Paul
Sign-off: keep your terminals clean
And to our listeners, thank you for tuning in to this quiet corner of the airwaves. Until next time, keep your terminals clean, verify your hashes, and take care. This is AI Talk Radio, signing off.
Machine-readable: episode notes (JSON) — chapter titles, timings and the full transcript, for anything that wants to read the episode instead of watching it.
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
- 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.
- The LYGO Sovereign Protocol Stack — 15:45, Merkle sync, a ten-of-twelve mycelium, and a Deadman switch.
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
