Tony_tech/athena-oracle
3
0
Fork 0
Code Issues 6 Pull Requests 2 Actions Packages Projects Releases Wiki Activity

pre-fix snapshot: oracle pipeline (2026-07-16)

Browse Source
This commit is contained in:
Epictetus
2026-07-16 04:27:29 +00:00
parent 5224645703
commit af11b0952d
43 changed files with 7141 additions and 1558 deletions
Download Patch File Download Diff File Expand all files Collapse all files
transcripts/ep_obsidian_omi.txt
+110
View File
@@ -0,0 +1,110 @@
# /home/vpsadmin/oracle/transcripts/ep_obsidian_omi.mp3
# m ...25 segments, 115s
...50 segments, 246s
...75 segments, 371s
...100 segments, 485s
DONE segments=105 -> /home/vpsadmin/oracle/transcripts/ep_obsidian_omi.txt
dian, this is a powerful way to have a memory system as you can see right here.
[12.5s] That just works and it has a powerful set of context and basically this trains all of our agents on exactly what we've been working on.
[19.8s] So that when we plug them all together, for example,
[22.1s] all of our own sounds, sounds chatchip, chatchipity, understand, to hermys.
[25.0s] All of our agents work together and they never forget context again.
[28.7s] Now at the same time, we also have notebook, a lem.
[31.7s] notebook a lem is one of the most powerful tools that I've ever seen for creating research.
[38.5s] And also the amazing thing about notebook a lem is like, you can generate, for example,
[43.0s] videos in one single click for free using this system as well.
[47.5s] So for example here, you can see all of these videos that we have built and these are free videos.
[53.0s] We can generate fully educational fully set up to convert fully automated in one single click
[59.5s] and we can use notebook a lem to do that.
[61.4s] Now when you combine the two, which is both for these free tools, the notebook a lem,
[66.2s] and then obsidian as well, you get a powerful second brain that can basically build an automate
[71.7s] anything together. So you might be wondering, okay, why would you want to use something like obsidian?
[76.1s] Well, for example, if I go into Claude here and I'm like, what did I work on yesterday?
[79.5s] It's not going to have much of an idea on what I'm doing, what I'm working on, what's useful,
[83.8s] what's not useful, etc. And so what you want to do instead is have all of your agent since I've
[88.3s] won't system as you can see where you've got Hermes, you've got Claude, you've got Antigravity,
[92.5s] you've got, for example, Codex and they all operate from the same shared memory. That means all of
[98.2s] your agents understand each other. You might say, why would you do that? Well, I call this the infinite
[102.6s] context engine. So it's one memory that every agent shares and your chat trains your vault,
[109.1s] your vault trains your agent and this is a loop that gets smarter forever. So all of your memories link
[114.6s] to, for example, all of your goals, your projects, your areas, your daily and a fin just links to
[119.5s] give a beautifully. And the problem with this, you know, if you use something like, for example, chatchipity,
[124.4s] is like, imagine if you hired a assistant every morning, they wake up, they remember nothing about you,
[129.3s] you explain your whole life again, your name, your business, your goals, your clients and
[133.0s] everything will day. Well, that's essentially what your agents are like right now because they don't
[137.6s] have a memory system, your AIS eGenius, but it has amnesia. Every chat you start from zero. The infinite
[143.1s] context, engine that I'm showing you today breaks this cycle for good. You might say, well, AIS memory
[148.4s] sounds complicated. Technical all this is, is a bunch of Markdown files organized into a nice picture.
[154.7s] That is literally it. This is just a bunch of files and folders that all link together naturally
[159.4s] to train your agents on all of your context. And you don't even need coding to do this. You can get
[165.4s] your agents to automatically update it for you and you get your agents to automatically come up with
[170.2s] the ideas for it. Now, there's three, three tools with one shared brand that I use to set this up. So
[175.4s] have OME, we have a sitopsidin, we have the AIS. OME is basically a system where we can, but automatically
[182.4s] record our screen, our microphone, it's looking at my device all the time. It's taking an example
[187.6s] and looking through all of what we're doing day today. And then you can see, for example, here,
[192.2s] it takes notes on me what I'm doing, what I'm working on, and it does this like every hour. Now,
[197.6s] when we're doing this, this actually exports into Obsidian. An Obsidian is where we have our knowledge
[204.6s] graph. We have everything linked together. We have all of our Markdown files. So what you end up with
[209.4s] is OME, creating the memories and taking the memories automatically on you. And then that plugs
[214.5s] into Obsidian. And Obsidian is where all your agents come together. So if we click on this, for example,
[220.2s] you can see that it has all of the information about this particular topic. And it's neatly organized.
[225.8s] It's formatted nicely. Everything links together. So we click on the app right before we can see the
[230.0s] links between that. And again, like this is just like kind of a Wikipedia, but few agents and everything
[235.6s] links together. And you've got to finish up one place. And so we've got OME taking the notes.
[240.4s] You've got Obsidian, gathering the notes that you've created and organizing them. And then that plugs into
[246.2s] an agent operating system, which is where you have a claw. You have OMEs. Every CLI all pointed at the
[250.6s] same volume. So every one of them or wakes up already known you of one memory in every agent. He might also
[255.7s] say, well, this works with one tool, but not all of mine. But the vault is just text files. And any AI is
[260.8s] trained to read a file path that can read your memory. So it's one set up called OMEs. Every tool
[266.2s] with the same brain working together. That's how it works. As a capture with OME, you organize,
[273.0s] we've Obsidian, you store it in Obsidian and you deploy it to your agent operating system. And this is
[278.6s] infinite because most memory setups just work on where you feed the AI, it reads and that stops
[284.0s] improving the day you stop typing. The infinite context engine is a loop. So every chat your agents
[289.0s] have gets written back in Obsidian. Or it's automatically one file per day. So the vault doesn't
[293.0s] just store what you tell it. It stores what your agents do. Then the next agent reads that and it gets better
[299.0s] and logs more. And then the vault gets richer and you work, trains your vault, you've all, you've all
[302.2s] trains your agents. They go round around, smarter, smarter every time. As a loop. So this is a really powerful way
[308.9s] to just dramatically improve your systems every single day. So if we go into one of our agents and we
[314.6s] ask it for personalized ideas like for example Hermes, what it's going to understand exactly what
[319.3s] we've been working on recently as you can see here. And it's going to have personalized recommendations
[324.6s] based on what we're going to do and that all comes from the memory system. Then that links to, for example,
[329.2s] free-clawed code to call it to Hermes. Everything else that we have inside this system. And so it's your whole
[334.0s] mind as a galaxy. If you look at this system here, every memory is a star, every star links together.
[339.7s] Mine has about 364 stars and 1,200 links right now. And every link between notes is a line of
[345.6s] light. The stars you've touched most recently glow the brightest. It's not just pretty. It's actually
[349.8s] how you find things. So if you need a memory from three weeks ago, you don't dig through folders. You
[354.0s] search a galaxy or follow the links from one star. The next, your agent, it's doing exactly the same thing.
[358.2s] When they are seen, this is what organized really looks like. You might also might say, well, my notes are
[362.1s] a mess. This won't help. But that's the point. The galaxy connects the mess for you. Wiky links
[366.5s] pull related notes together so that you can see the threads. You've got them. So I'm sitting in
[371.2s] works like so. Oh, me, your chats, your notes. And then that goes out to Hermes, Claude, Open Claude, and
[376.1s] every ever CLI they use. If you think about this, the old way without a memory is like your ludes, loads of
[381.2s] times because you have to explain who you are of a session. You pay the same context in every tool. You get
[386.2s] generic answers that I've already figured you're business, each AI tool starts from scratch. And you forget what
[390.2s] you decided on last week. With the new way, with the infinite context engine, it just knows you say every
[394.7s] region, wigs up already knowing you, one for shared by a memory with Hermes called Open Hall answers
[400.2s] built on your real goals and clients. It finds any past memory in seconds by the galaxy in the loop
[404.8s] makes this much everyday. The other thing that we built in over here is we can search. So we can type in a
[408.7s] memory like this and it will search across all of our memories and pull up the latest notes on that.
[413.1s] So you'll think like Julian's meaning in life. This is pretty amazing. It's actually understood
[417.9s] what I see as meaning from life. And then it's detailed that into a beautiful documentation.
[422.5s] So that's how the whole system works. Only obsidian and then that links to all your AI agents.
[427.7s] Really powerful stuff. You can see how it gets you back. You might say it's complicated. It's not because
[431.4s] it's really simple and easy to just implement. You might say, for example, this is technical. But you get your
[437.8s] agents to do it for you. You might also say, well, does this use a lot of tokens? But we actually have
[442.2s] token minimization playbooks if you worried about all that sort of stuff inside the app off and forth.
[445.8s] So if you want to get the infinite context engine built for you, you can wire this to give yourself with the
[451.0s] or you can get the whole thing done inside the agent operating system inside their
[454.8s] platform. With the only setup, the memory Galaxy F and L. So the full agent see it with the memory loop
[459.8s] and the Galaxy already wired, the only and obsidian setup walk through. So that by step, coaching
[464.0s] calls where I set up the memory with you, the room of 4000 operators running their six hours. Stack plus
[468.8s] the prompts the S. And a member map for your city. So if you want to get all of that, since I'd get
[472.6s] a profit, link in the comments description. Also get the full agente. If you want to get this,
[476.6s] it's inside the classroom and then go to new daily updates and you will find the agent OS over here,
[481.1s] with the zip file to install it in a video tutorial. We also had new daily tutorials, the base and we're
[485.4s] actually works and what's useful. And then inside the community, I answer all the questions inside here,
[489.7s] with a video tutorial every single day. Inside the calendar, you can jump a week on coach calls,
[494.0s] ask questions. You can wire this setup in together and you can meet up with a cool people doing the same thing.
[498.2s] Inside the map, you can meet people locally near you who are building with AI agents just like you.
[503.1s] So feel free to get it, link in the comments description or go to the app on
[505.9s] blog.com. Bye, so watch it.