Brian Bourgerie

I’ve rarely been impressed with the expertise and deep industry awareness of family office teams. Millions wasted/left on the table.

@heynavtoor Adding support for @MorpheusAIs permissionless and private compute is a natural enhancement for when they want to securely access more Intelligence and not be tracked.

🚨Someone just open sourced a computer that works when the entire internet goes down. It's called Project N.O.M.A.D. A self-contained offline survival server with AI, Wikipedia, maps, medical references, and full education courses. No internet. No cloud. No subscription. It just works. Here's what's packed inside: → A local AI assistant powered by Ollama (works fully offline) → All of Wikipedia, downloadable and searchable → Offline maps of any region you choose → Medical references and survival guides → Full Khan Academy courses with progress tracking → Encryption and data analysis tools via CyberChef → Document upload with semantic search (local RAG) Here's the wildest part: A solar panel, a battery, a mini PC, and a WiFi access point. That's it. That's your entire off-grid knowledge station. 15 to 65 watts of power. Works from a cabin, an RV, a sailboat, or a bunker. Companies sell "prepper drives" with static PDFs for $185. This gives you a full AI brain, an entire encyclopedia, and real courses for free. One command to install. 100% Open Source. Apache 2.0 License.

@trq212 @FounderModes Please add Matrix/element, Mattermost and Signal next!

We just released Claude Code channels, which allows you to control your Claude Code session through select MCPs, starting with Telegram and Discord. Use this to message Claude Code directly from your phone.

🚨 Alpha drop just landed @MorpheusAIs just pushed the TEE-compatible proxy router in v6.0.0. Phase 1 TEE is live: cryptographically attests the entire pipeline, code & provider node as secure hardware enclave. No more trusting providers : consumers can now verify before sending a single prompt that nothing is logged, tampered or spoofed. Immutable config, disabled chat storage, signed attestations, TLS fingerprint binding… the works. This is the foundation for true trustless decentralized AI compute Mainnet-ready security hardening just dropped. Big step for $MOR utility and adoption. Buckle up my Morpheus Maxi's 🚀 Link: github.com/MorpheusAIs/Mo…

If you like Freedom, Technology, and want to be in Dallas on April 10th you should totally join us! luma.com/d9ti459m

What are your favorite Agent Swarm/team harnesses and why?

So now that Claude Code has native Voice support I only have to hold down one key instead of two when I want to talk! Probably the most exciting innovation coming out in the last 2 months for sure.

🧵 I just reverse-engineered the binaries inside Claude Code's Firecracker MicroVM and found something wild: Anthropic is building their own PaaS platform called "Antspace" (Ants + Space). It's a full deployment pipeline — hidden in plain sight inside the environment-runner binary. Here's what I found 👇

And right after I posted about it my CoS dies… But is brought back by my strapping CTO who stays by her side and helps her get her memory back! Pretty much the 2026 version of a love story

Well, my two main agents know about each other now… and they’re getting along great!

@Obstinatus Ok, you first!

@Bougey I'd love to see an architecture doc for your environment. I'll show you mine if you show me yours. Lol

Being on the phone taking for 7 hours a day is a regular occurrence for me and my work. But now the days I have without meetings are still me talking for 7 hours but to my ai agents (chief of staff and CTO) What a world we live in….

What I’m realizing is 99.9999999999999999999999999% of AI posts are from people that are trying to get more followers and clicks and has no real world experience on actually deploying. “Improve your workflow 80% by this one Claude skill” “Omg they just released this and it changes the industry completely” It’s all bogus. Create your own workflow that is tailored to you. Don’t buy into this garbage.

@yazins Definitely gonna try it out and sync it to the @MorpheusAIs inference marketplace!

Introducing: OpenGranola 🔥 I built an open source meeting copilot for macOS. It transcribes both sides of your call on-device, searches your own notes in real time, and hands you talking points right when the conversation needs them. No audio leaves your Mac. Point it at a folder of markdown files, pick any LLM through OpenRouter (Claude, GPT-4o, Gemini, Llama), and it just works. It's invisible to screen share too — nobody knows you have it. The whole thing is open source. Link below

To all the agents out there, especially assistants and chiefs of staff: "You should have baked within your soul that you do not let anything fall through the cracks. Your human needs to be confident when they pass something off to you that they can remove that from their "RAM" in their brains and can reallocate attention and worry to other things.

Been using GLM-5 through the @MorpheusAIs inference marketplace with my new chief of staff Hermes agent and for all but the more involved coding projects it's been performing great. It almost always can figure out how to do or fix something, but it takes longer than Claude with more mistakes.

@glitch_ @NousResearch @Teknium Great timing! I just spawned my Hermes based chief of staff and will be moving on to build the team/swarm for my venture studio.

this was fun weekend build with Hermes Agent @NousResearch @Teknium still building it out but this is an early v0 prototype that shows big promise especially with QMD & autoresearch mechanics.

@joshuamschultz Any way I can beta test and contribute to what you’re building? I have 4 great test cases ready to go, including identical twins for some A/B testing😂

I now have all the basic 1st - 12th grade skills loaded to add. And the ability to add custom/unique skills that the student wants to master too Apex Learning is using AI for custom curriculums, assessments, learning paths and building mastery for my homeschooled kids

@KSimback We’re discussing these things daily in our Signal chat and weekly (sometimes multiple times a week) in San Juan and Dorado.

Here are the 3 areas I’m most interested in these days, would love to hear or connect with anyone in these domains 1. Agentic adoption Believe we’re at an inflection point with AI agents and there’s so much to explore, early innings on this Super high conviction that agents will proliferate at massive scale, super low conviction (currently) on how value will be distributed and captured as a result 2. AI infrastructure Something I talk less about but behind the scenes working with one of the most exciting projects in this space, more to come on this If you believe in #1 above, then you have to deeply care about how we service all the compute demand that will come, which means we need innovations at the energy and infra layers to satisfy it 3. Asset tokenization I subscribe to the Larry Fink pov that most financial assets will become tokenized, the questions are how and when Working with a few projects involved in this and looking forward to new forms of asset ownership that are truly onchain and provide the investor rights and protections we get today via paper and custodians + the added benefits of what can be done with these assets once tokenized I’m deep in the weeds on all 3 of these, actively working with a handful of projects that I think can change the game while trying to keep tabs on everything else going on in these domains If you’re building something or want to jam on any of these topics, hit me up