This 100% automatic AI Agent can do anything, just watch

แชร์
ฝัง
  • เผยแพร่เมื่อ 10 ก.พ. 2025
  • Work 30% faster with Vectal: www.vectal.ai
    Learn how to make $$ with AI - www.skool.com/...
    I'M HIRING! Do you want to join my team? Apply here: forms.gle/2iz4...
    Agent Zero GitHub: github.com/frd... (give it a star!)
    Jan's Demo: • Agent Zero 🤖 first dem...
    My Docker Video: • Build AI Agents with D...
    Follow me on Instagram - / thedavit
    Follow me on Twitter - x.com/DavidOnd...
    Please Subscribe.
    Credits: ‪@AgentZeroFW‬
    David Ondrej Podcast - Episode 15

ความคิดเห็น • 196

  • @DavidOndrej
    @DavidOndrej  6 หลายเดือนก่อน +5

    🔥 Learn how to make $$ with AI Agents - www.skool.com/new-society

    • @flyingcheesecake3725
      @flyingcheesecake3725 5 หลายเดือนก่อน

      david, can someone with little to no knowledge in programming get value from your course? i watched the video halfway and got interested in it (i joined, giving it a try at least)

    • @eismccc
      @eismccc 5 หลายเดือนก่อน

      Are you still trying to hire someone?

  • @emmanuelarthur8377
    @emmanuelarthur8377 6 หลายเดือนก่อน +57

    The fact that it can feed errors in the terminal back into itself and resolve them is amazing!

    • @Keytotransition
      @Keytotransition 6 หลายเดือนก่อน +2

      YES. open interpreter does a similar thing and while the OS mode is great the limitations are too many.

  • @MyStoryCrafters-co
    @MyStoryCrafters-co 6 หลายเดือนก่อน +29

    I’ve been working on making almost the exact same thing. User intervention is genius and I don’t think I would have ever thought of it. Great work here.

  • @ScottLahteine
    @ScottLahteine 3 หลายเดือนก่อน +3

    I love the way this is architected, and the general concept of an AI that is able to self-assemble its own library of information and code that it used in past tasks is really powerful. We also recently got releases of OpenAI Swarm and a project called “01” that builds voice input and agents on top of Open Interpreter. It’s really been exploding in the last 4 months, especially. As a longtime coder, every educational video on this topic fills me with excitement realizing all the implications of this new way of automating tasks. And as the maintainer of a popular open source project, I have tasks! I can’t wait to see how agents can help me to tackle them.

  • @MrJoe1199
    @MrJoe1199 6 หลายเดือนก่อน +3

    Very well thought out way to "do" agents, and complete with excellent pragmatic features for controlling agents and helping agents to recover from errors. The best feature IMHO is that all the behaviors are in external files and not in the code.

  • @justinduveen3815
    @justinduveen3815 6 หลายเดือนก่อน +1

    David, thank you so much for helping us learn how to harness the power of AI agents.
    I’ve been a big fan for a long time and have found your content to be super helpful for AI automation builders.
    Jan, your new tool-creating, AI agent framework is really smart! Thank you so much for sharing!

  • @KCM25NJL
    @KCM25NJL 6 หลายเดือนก่อน +35

    I like the idea of generating function call code dynamically, especially for generic purposes such as 'File Open,' 'File Save,' or specific algorithms like 'Sort Algorithm X.' To optimize efficiency and promote reusability, I strongly recommend cloudifying these functions, either in a private or public manner. Publicly available functions could be curated to ensure quality and security. This approach can potentially reduce the number of LLM calls required, saving time and money.

    • @TheAlastairBrown
      @TheAlastairBrown 6 หลายเดือนก่อน +11

      Billions of agents hammering away writing functions to pull down the current time and date 🤣. I think the first thing I'll ask Agent Zero to do is come up with a list of 50 functions and build a library of general purpose capabilities.

    • @KCM25NJL
      @KCM25NJL 6 หลายเดือนก่อน +3

      @@TheAlastairBrown Yep, I can well imagine running AZ on Groq to rapidly build a heavy duty RAG vector DB or Knowledge Graph of reusable function calls. I'd probably go with the KG just for the sake of storing clusters of relatable functions based on use case. Frankly with all the big brains out there, I can see no reason why this hasn't been done yet.

    • @DaleIsWigging
      @DaleIsWigging 6 หลายเดือนก่อน

      With ai search engines getting better maybe this will exist in the future with "currently working" github repositories

  • @StuartJ
    @StuartJ 6 หลายเดือนก่อน +43

    I was waiting for something like this. Agents that you have to define yourself, seemed counterintuitive to me. AI should be able to figure it out for itself.

    • @LVE-xr5or
      @LVE-xr5or 6 หลายเดือนก่อน +2

      @@Tom_Neverwinterthat’s what I was thinking too

    • @MungeParty
      @MungeParty 6 หลายเดือนก่อน +1

      Yeah I don't think this is doing anything new relative to AutoGPT.

    • @roygatz
      @roygatz 6 หลายเดือนก่อน +3

      @@MungeParty popular framework are taking a top down approach and there are many things that render the frameworks too complicated to use. I think what agent0 is trying to do is to take a bottom up approach and define a set path to at least do something productive or hopefully userful. Though nothing production worthy, a good starting point.

    • @orthodox_gentleman
      @orthodox_gentleman 6 หลายเดือนก่อน

      I have thought the same exact thing dude

  • @SouhailEntertainment
    @SouhailEntertainment 6 หลายเดือนก่อน +33

    Introduction to Agent Zero and Interview - 00:00:00
    Overview and Key Features of Agent Zero - 00:00:29
    Demonstration: Current Time in Different Locations - 00:01:28
    Error Handling and Agent Self-Correction - 00:02:00
    Choosing Language Models and Cost Efficiency - 00:08:01
    Compatibility with Various Models and Frameworks - 00:09:44
    Setup and Configuration of Agent Zero - 00:11:01
    The Role of Docker in Agent Zero - 00:24:22
    Advanced Features: Subordinate Agents and Task Delegation - 00:20:52
    Interactive Agent Management and Error Recovery - 00:46:41
    Memory and Knowledge Tool Usage - 00:32:56
    Combining Agent Zero with Other Frameworks - 00:38:28
    Building and Improving Agent Zero - 00:58:39
    Future Development and Open Source Collaboration - 01:09:44
    Final Thoughts and Closing Remarks - 01:18:45

  • @Keytotransition
    @Keytotransition 6 หลายเดือนก่อน +33

    “agent one has no idea that his user is actually another agent and he doesn't need to know” - bro that’s it we’re just one of the many sub agents and we’ve just made our sub agents .

    • @JarkkoHautakorpi
      @JarkkoHautakorpi 6 หลายเดือนก่อน +6

      We are in simulation using agent-zero but we don need to know it

    • @AeroMagic_Official
      @AeroMagic_Official 5 หลายเดือนก่อน +1

      bro u just broke my brainnnnnn....

    • @solank7620
      @solank7620 5 หลายเดือนก่อน +2

      @@JarkkoHautakorpiMatrixception.

  • @karlbarker2912
    @karlbarker2912 6 หลายเดือนก่อน +6

    I’ve used open interpreter and now Claude engineer, but this looks amazing, can’t wait to try it

    • @Keytotransition
      @Keytotransition 6 หลายเดือนก่อน +2

      Yeah I’ve been using open interpreter for a while now and it helps a lot but troubleshooting is so annoying because it either sucks in many other modes or it won’t stop looping on OS mode . But this, this is something pretty much next level.

  • @BadreddineOtky
    @BadreddineOtky 6 หลายเดือนก่อน +1

    I have been testing lots of AI frameworks, tools and platforms. This is the BEST ONE I have seen! Great project!!! Thank you so much for sharing.
    This will help me so much in my everyday work

    • @nanolaxyz8490
      @nanolaxyz8490 6 หลายเดือนก่อน

      better than Aider?

    • @BadreddineOtky
      @BadreddineOtky 6 หลายเดือนก่อน

      @@nanolaxyz8490 yes definitely better. the auto-sanbox and auto-correct features are awesome

    • @AeroMagic_Official
      @AeroMagic_Official 5 หลายเดือนก่อน

      @@nanolaxyz8490 what dat

  • @JcMz072
    @JcMz072 5 หลายเดือนก่อน +1

    Yooo this project is so legit! I’m trying it out myself and it’s by far exceeded anything else I’ve tried

  • @lifeonearth9261
    @lifeonearth9261 6 หลายเดือนก่อน

    Super cool project. Had an issue with the database but found a workaround in Issues that fixed it. Thanks for this great project!

  • @kniiz
    @kniiz 6 หลายเดือนก่อน

    no wonder strawberry got so hype, its because of this. im in love. nice agent! Thank you both for an nice interview.

  • @CaptGhost-u3u
    @CaptGhost-u3u 5 หลายเดือนก่อน

    that is so amazing, I'm a student and I'm thinking, with all this LLMs that can run locally if i can build a bot like this, and now its here. truly amazing

  • @GrahamSmart
    @GrahamSmart 5 หลายเดือนก่อน +1

    Absolutely amazing work.

  • @ysy69
    @ysy69 4 หลายเดือนก่อน +1

    Jan talks about helping the agent when it runs intro some issues and not able to move forward. I wonder if Agent Zero is able to learn and remember every help it gets over the course of all engagement so that it doesn't run into the same problems

  • @CreativeEngineering_
    @CreativeEngineering_ 5 หลายเดือนก่อน

    The whole name thing is easy, with explaining how to use the memory you would add something like 'If a user's request or statement contradicts a previously made statement or request then ask the user to explain the reason for the contradiction. Something along those lines, I'm sure it could be refined more, but that's the gist of it.

  • @DataJuggler
    @DataJuggler 6 หลายเดือนก่อน

    Congrats on the 100K subscribers. Ask Jan in his spare time to write a C# version of Agent Zero.

  • @16bitbrawler
    @16bitbrawler 6 หลายเดือนก่อน

    This is really amazing. Thank you so much for sharing!

  • @stonedoubt
    @stonedoubt 6 หลายเดือนก่อน +5

    Open Interpreter does something like this. It can write code, execute it, debug if there is a problem, etc.

    • @utawmuddy5940
      @utawmuddy5940 4 หลายเดือนก่อน

      Suppose to be a-lot better for alit if other stuff, i live it!

  • @CharlesZerner
    @CharlesZerner 6 หลายเดือนก่อน +2

    Awesome! Can’t wait to try it.

  • @whizadree
    @whizadree 6 หลายเดือนก่อน +1

    Think a web gui using flask would be nice addition , that can setup the llms add api keys , and enter your request and get either the final output or see the entire output

  • @shivachaturvedhi8840
    @shivachaturvedhi8840 6 หลายเดือนก่อน +1

    Interesting...
    another video on
    1. creating custom tools
    2. custom .md files
    3. generating and running code in other languages (other than python)
    4. ability to develop some design pattern using some tool etc
    could be er useful

  • @AD4K8
    @AD4K8 6 หลายเดือนก่อน

    This is incredible brothers!

  • @SIRENSCINEMATIC-SCOTLAND
    @SIRENSCINEMATIC-SCOTLAND 6 หลายเดือนก่อน

    So much to take in here incredible that this is the free stuff 😂
    I'm a paid member and recommend

  • @evynt9512
    @evynt9512 6 หลายเดือนก่อน

    Agent technology will define nature.

  • @maxxflyer
    @maxxflyer 6 หลายเดือนก่อน

    amazed, I work on a similar project but the docker shit is amazing.

  • @GRAYBOOSH-420
    @GRAYBOOSH-420 6 หลายเดือนก่อน

    I've been waiting for something like this... I'm excited

  • @r3dsign
    @r3dsign 5 หลายเดือนก่อน

    I watched 3 minutes of the video and Im sure that this is the idea that wil make AIG possible.

  • @thomasthelen7874
    @thomasthelen7874 6 หลายเดือนก่อน

    How f*** awesome!!! Kudos to Jan!!!

  • @christopher-george
    @christopher-george 5 หลายเดือนก่อน

    Truly amazing !

  • @jamesspalding1210
    @jamesspalding1210 6 หลายเดือนก่อน

    This is such an excellent video, amazing framework and can’t ait to test it out

  • @timmcgirl5588
    @timmcgirl5588 6 หลายเดือนก่อน +7

    Honestly, this can achieved using Open Interpreter, by simply giving it a prompt to integrate with any open source tool for free.

    • @MiguelCayazaya
      @MiguelCayazaya 6 หลายเดือนก่อน +1

      open interpreter will take you into more loops than GPT 3.5 - I trusted the bastard snif ... but I like the idea of challenging all ideas so the last one stands

    • @timmcgirl5588
      @timmcgirl5588 6 หลายเดือนก่อน

      @@MiguelCayazaya i use Claude 3.5 Sonnet, it never loops when i use it do to proper prompt engineering.

    • @timmcgirl5588
      @timmcgirl5588 6 หลายเดือนก่อน +1

      @user-qp1jq3eh3e it never loops when I use it, I use Claude 3.5 Sonnet with Open Interpreter, can use Groq inference with Llama 3.1 also. Not sure we're on the same page, proper prompt engineering is also key.

    • @karlbarker2912
      @karlbarker2912 6 หลายเดือนก่อน +1

      Open interpreter does not have persistent memory

    • @timmcgirl5588
      @timmcgirl5588 6 หลายเดือนก่อน +1

      @@karlbarker2912 By integrating Open Interpreter with Gorilla AI and n8n, you can create a system that maintains persistent memory across sessions. This approach leverages n8n’s automation capabilities to ensure that user interactions are contextually aware and persistent, enhancing the overall user experience. The Gorilla AI API platform offers various utilities and capabilities that enhance the functionality and application of AI models.

  • @MeinDeutschkurs
    @MeinDeutschkurs 6 หลายเดือนก่อน

    I hope that perplexicA will get an API soon.

  • @stanTrX
    @stanTrX 6 หลายเดือนก่อน +2

    looks good. do i have to let this framework to "find a way to tell the time" each time i reopen this program? or it remembers and saves required stuff like this to it's knowledge base?

  • @baTonkaTruck
    @baTonkaTruck 6 หลายเดือนก่อน +1

    The problem with tools like this: Most people don’t know enough to use them, and the ones that do don’t need them.

  • @cbau0809
    @cbau0809 6 หลายเดือนก่อน +4

    This agentic approach is amazing. My only recommendation is to use pydantic to instruct the llm into a structure response rather than using a parse json function.

    • @jeffsteyn7174
      @jeffsteyn7174 6 หลายเดือนก่อน

      Json is structured

    • @MungeParty
      @MungeParty 6 หลายเดือนก่อน +3

      They address this in the video, it doesn't use structured output specifically to retain compatibility with models that don't support it.

  • @florianstephan5745
    @florianstephan5745 6 หลายเดือนก่อน +1

    wow, an AI finally telling me the time...AGI is near ;-)

    • @TJ-hs1qm
      @TJ-hs1qm 6 หลายเดือนก่อน

      TZ=Asia/Tokyo date 😂

  • @Derick99
    @Derick99 6 หลายเดือนก่อน

    This worked the first time now anytime you use it, it tells me its just a language model and cant do anything but it originally worked and would do research etc

  • @thomasnook118
    @thomasnook118 6 หลายเดือนก่อน

    Title should’ve been “Agent can tell you the current time in Berlin VIA your terminal… just watch” LOL but all jokes aside, these ai/agents are still just toys

    • @JakobN-zg1st
      @JakobN-zg1st 6 หลายเดือนก่อน

      Why do you believe ai/agents are toys?

    • @thomasnook118
      @thomasnook118 6 หลายเดือนก่อน

      @@JakobN-zg1st no real world applications yet (meaningful applications) . I think one day they COULD be but for now they aren’t very useful.

  • @tier1recon836
    @tier1recon836 6 หลายเดือนก่อน +2

    Any tutorials using it with ollama?

  • @Derick99
    @Derick99 6 หลายเดือนก่อน +5

    Whats the time stamp for training 3.1 llama finetuning with your data

  • @johnmarkston4883
    @johnmarkston4883 6 หลายเดือนก่อน +1

    any discount codes for the skool ? i was part of your skool about a year ago but didnt have enough time to dedicate to it, $197 is a weeks pay for me and i couldnt afford it while also paying for all the api fees to build an agent

  • @janalgos
    @janalgos 6 หลายเดือนก่อน +1

    now just need to incorporate mixture of models to improve quality from the small models

    • @TheAlastairBrown
      @TheAlastairBrown 6 หลายเดือนก่อน

      Ask it to improve itself ?

  • @CarolinaFarming
    @CarolinaFarming 6 หลายเดือนก่อน +3

    Why don't you have a prompt that Agent 0 checks that lists the best libraries to use for certain tasks? So it will use the correct library from the beginning to download youtube videos.

  • @joesmoo9254
    @joesmoo9254 6 หลายเดือนก่อน

    Great framework. Is there a way to feed context to the system. Fi a directive or architecture directory where you put bussiness rules and standards

  • @reinerheiner1148
    @reinerheiner1148 6 หลายเดือนก่อน +9

    The price will double in 5 days!!! This marketing trick instantly made me suspicious and dropped my motivation to keep watching this video down to zero. But hey, I am sure you will get enough people who fall for this.

    • @orthodox_gentleman
      @orthodox_gentleman 6 หลายเดือนก่อน +2

      I thought the same thing

    • @iGhostr
      @iGhostr 6 หลายเดือนก่อน +1

      Same

    • @riegaldutoit5792
      @riegaldutoit5792 6 หลายเดือนก่อน +2

      thought the same.. raising the price on new information has become his thing lately.

    • @remain___
      @remain___ 6 หลายเดือนก่อน

      🤨 why? You think discounts are cause for suspicion?

    • @Hyp3rSon1X
      @Hyp3rSon1X 6 หลายเดือนก่อน +2

      The best way to make money is selling people a guide on how to make money.
      The guide doesn't need to work and in most cases it won't. But as the creator of the guide you can then simply blame it on the incompetence of the user.
      Adding the factor of "fear of missing out" only adds in sales of the guide.
      So yes, I absolutely agree with this!

  • @KOSMIKFEADRECORDS
    @KOSMIKFEADRECORDS 6 หลายเดือนก่อน +1

    Promising will be following closely. If i had the bucks id be in your discord.

    • @idkwhy4939
      @idkwhy4939 6 หลายเดือนก่อน

      Facts

  • @MeinDeutschkurs
    @MeinDeutschkurs 6 หลายเดือนก่อน

    Intriguing!

  • @FriscoFatseas
    @FriscoFatseas 6 หลายเดือนก่อน +22

    Excited for when its simple enough for me to care

    • @anwhelan
      @anwhelan 3 หลายเดือนก่อน

      Mate it doesn’t get much simpler: step1: input prompt step2: wait a sec step3:read whatever it writes under the green bit.

  •  6 หลายเดือนก่อน +2

    40:04 - Instalation / setup

  • @anwhelan
    @anwhelan 3 หลายเดือนก่อน

    Interrupt agent with any key is killer. This vid couldn’t not come at a better time. I’d just spun up an instance to build something almost exactly like this so from the bottom of my repetitive strain injuries, thank you very much 🙏🐇🫶😂

  • @HistorIAsImposibles776AC
    @HistorIAsImposibles776AC 5 หลายเดือนก่อน

    Wow amazing, let's get it working !!! Is it possible to Collaborate with the project ?

  • @supernaturalself3577
    @supernaturalself3577 6 หลายเดือนก่อน +5

    how would on go about using agent zero in a persistent way? For example if you didn't want to lose the libraries everytime docker instance shutdown. I would imagine I would want to keep the environment intact so that one doesn't have to waste time reinstalling something every time one fires up docker.

    • @JarkkoHautakorpi
      @JarkkoHautakorpi 6 หลายเดือนก่อน

      You can persist your running docker instance. Stop it and resume it where u left it.

  • @supernaturalself3577
    @supernaturalself3577 6 หลายเดือนก่อน +1

    can I get agent zero to change itself to use claud instead of perplexity?

  • @resresres1
    @resresres1 5 หลายเดือนก่อน

    This is a nice proof of concept, but LLM's at the moment can only handle fairly basic coding. Perhaps when LLM's can do much more complicated projects, complete on their own, then this concept of having it fix it's own code will be absolutely necessary.

  • @emmanuelkolawole6720
    @emmanuelkolawole6720 6 หลายเดือนก่อน +1

    When will agent zero support automatic docker container restart in cases where the container created on startup is corrupted by llm mistake. I don't want to restart the whole application again and again. The agent should just launch a new docker container

  • @DreadFox_official
    @DreadFox_official 6 หลายเดือนก่อน

    Well dang, I wanted to build an agent like this for my cybersecurity framework but you already made it. I'm excited to experiment with this. Thank you so much for spending time to build this.

    • @DreadFox_official
      @DreadFox_official 6 หลายเดือนก่อน

      @@Tom_Neverwinter This project is pretty big, I can see how it took multiple minds to come together.

  • @jimg8296
    @jimg8296 6 หลายเดือนก่อน

    Very cool project

  • @MercLeague
    @MercLeague 3 หลายเดือนก่อน +1

    i dont understand how to use it. downloaded it and clicked evey possibl eoptin. nothing happens. pretty hard to be user friendly if its not usable.

  • @RhumpleOriginal
    @RhumpleOriginal 6 หลายเดือนก่อน +1

    If this guy did this, imagine what governments have going on behind closed doors...

    • @DavidOndrej
      @DavidOndrej  6 หลายเดือนก่อน +2

      true

    • @mircorichter1375
      @mircorichter1375 6 หลายเดือนก่อน +1

      Follow Mike Benz Cyber on X... He put it all out

  • @RowanSheridan
    @RowanSheridan 6 หลายเดือนก่อน

    Good overview, would be helpful to have timestamps

  • @igorbetternower7800
    @igorbetternower7800 6 หลายเดือนก่อน

    Sounds like the future of AI, impressing, but too high for me. I guess I'm one of the first to be substituted by AI 🙂

  • @mountshasta2002
    @mountshasta2002 6 หลายเดือนก่อน

    This is pretty cool. Currently trying to have it utilize crewai and other than using the wrong pip command we're cruising. If I want to provide context or a codebase can I just put it into the work_dir? Like if I wanted to provide docs. EDIT: adding docs to the work dir causes token limits to max and timeouts.

  • @Dmytro-fr9nd
    @Dmytro-fr9nd 6 หลายเดือนก่อน +5

    What kind of hardware it requires to run?

    • @jean-philippes5826
      @jean-philippes5826 5 หลายเดือนก่อน

      random pc no need graphic card like big local llm

  • @LVE-xr5or
    @LVE-xr5or 6 หลายเดือนก่อน +9

    39:00 where it gettes good

    • @KOSMIKFEADRECORDS
      @KOSMIKFEADRECORDS 6 หลายเดือนก่อน

      what the self promo? LOL sneaky.

  • @pizzaiq
    @pizzaiq 6 หลายเดือนก่อน +1

    I've built a broader version of something like this 8 months ago. More evolved since then. The bots are not smart enough to be actually functionally usable yet but the principle is simple and good. My framework allows the bot to create, use and query databases and build a code base of functions that perform various tasks. The idea is that you give the bot access to read, write and execute and give it behavioral parameters. Them evolve the process. I even have it write a clone of it's own code base clone and test it, the back itself up and run a self update. I got bored writing it after a while...

  • @kellymaxwell8468
    @kellymaxwell8468 6 หลายเดือนก่อน +1

    But can it program and script and do games bring back old closed down games, remake old games, and make more of games that have gone

  • @rots.866
    @rots.866 6 หลายเดือนก่อน

    can i use this to complex project with server and client side?

  • @felipeblin8616
    @felipeblin8616 6 หลายเดือนก่อน

    Amazing

  • @peterbellheim720
    @peterbellheim720 6 หลายเดือนก่อน

    Thank you David ... I am big fan about your Workflow...👌👍🤝

  • @analysisjitsu
    @analysisjitsu 5 หลายเดือนก่อน

    Wow!

  • @leomaxwell972
    @leomaxwell972 6 หลายเดือนก่อน

    Interesting thought... I can see, and I've had, AI forget/mix-up my or other's names, but, when it comes to their own name or company, they have no problem remembering exact details... obviously this is a (un)holy grail of bias, that they would be super hard coded... but... how limited is this "hardcoded" space? surely it could fit the user's name for their model/iteration/shard/etc. of their AI conversation partner, no? or maybe it really is that limited lol. Thats semi-blackbox level stuff if you ask me.

  • @Jim1Dean
    @Jim1Dean 6 หลายเดือนก่อน +1

    how can I use my local llama3.1 model? I use textgen webui with OPENAI API

  • @whizadree
    @whizadree 6 หลายเดือนก่อน

    Can it create a structure file system and able to edit individual files…

  • @nAme-bf9uz
    @nAme-bf9uz 6 หลายเดือนก่อน

    This looks like a more complicated version of open-interpreter

  • @hypertectonics7009
    @hypertectonics7009 6 หลายเดือนก่อน

    So conceptually this system should be able to improve its own code and execute it...

  • @victorbecerra5700
    @victorbecerra5700 6 หลายเดือนก่อน

    Amazing 😃🌏🌎

  • @aaagaming2023
    @aaagaming2023 6 หลายเดือนก่อน +1

    Neni to nahodou Hynek Cermak? Uzasna prace, take jsi s tim pohraju.

  • @hackmedia7755
    @hackmedia7755 6 หลายเดือนก่อน

    does this integrate into IDEs like Xcode?

  • @thewebstylist
    @thewebstylist 6 หลายเดือนก่อน

    Ahhhgh wish bro you had a 15 min version of this video

  • @jimmyjam77
    @jimmyjam77 6 หลายเดือนก่อน

    How does this compare to Aider?

  • @doghashisday4612
    @doghashisday4612 6 หลายเดือนก่อน

    Llama 3.1 integration ?

  • @atz6212
    @atz6212 5 หลายเดือนก่อน

    So basically it can build a coding stack for you!? And basically any other coding stack!?

  • @johnstarr2001
    @johnstarr2001 6 หลายเดือนก่อน +1

    I can't get the API. The site won't except my credit card? I can't go further!?

    • @johnstarr2001
      @johnstarr2001 6 หลายเดือนก่อน

      Always something wrong...

  • @AeroMagic_Official
    @AeroMagic_Official 5 หลายเดือนก่อน

    THIS I SOMETHING UNERRRREAL

  • @miroslavacizmarova6809
    @miroslavacizmarova6809 6 หลายเดือนก่อน

    Wow. Great job!

  • @tareqkhammash9245
    @tareqkhammash9245 6 หลายเดือนก่อน

    U should have more subscribers

  • @six1free
    @six1free 6 หลายเดือนก่อน

    I've been writing similar... project abandoned :D
    (I assume) embedding_llm = models.get_embedding_ollama() ??? can we specify the model inside the brackets like in get_ollama(X)?

  • @ccdj35
    @ccdj35 6 หลายเดือนก่อน

    I cannot make the Nvidia drivers installed in Ubuntu otherwise I would have definitely used this kind of agent.

  • @MatichekYoutube
    @MatichekYoutube 6 หลายเดือนก่อน

    would be possible to use ollama 3.1?

    • @AgentZeroFW
      @AgentZeroFW 6 หลายเดือนก่อน +1

      Yes, but it's not very good from what I've heard from users. Maybe try gemma2 instead with ollama.

  • @andrewwall2730
    @andrewwall2730 3 หลายเดือนก่อน

    Ok, $97 a month and you don't really explain how I can make money with AI. I've watched nearly all your vids but still don't get it. I've been a software dev for nearly 20 years, mostly with javascript but also some python. Just exactly will I get for my $97 a month?
    And there are dozens of AI Agents, LLMs; just which ones do I choose or do I need to learn them all.

  • @d.d.z.
    @d.d.z. 6 หลายเดือนก่อน

    Another useful tool. Thank you

  • @johnstarr2001
    @johnstarr2001 6 หลายเดือนก่อน

    Why not build docker a person can download.

  • @jessicalewisjessielew3399
    @jessicalewisjessielew3399 6 หลายเดือนก่อน

    1:05:00 what is your custom GPT for coding ?

  • @dailyrd
    @dailyrd 6 หลายเดือนก่อน +1

    im so dumb i can't even install this without asking to llm

  • @BigBandoonthebeat
    @BigBandoonthebeat 6 หลายเดือนก่อน +2

    This like open interpreter or soc r sum

    • @aliabassi1
      @aliabassi1 6 หลายเดือนก่อน

      Exact same thought, very similar to open interpreter

    • @BigBandoonthebeat
      @BigBandoonthebeat 6 หลายเดือนก่อน

      @@aliabassi1 Self operating computer tuff shouldve copied that

  • @RocketLR
    @RocketLR 6 หลายเดือนก่อน

    I dont understand why i need perplexity or openai for this?
    I redid the code to use my local LLMs from my ollama instance.
    It does a great job but at the end of its completed response it gets a errors trying to reach openai or perplexity.. which i dont want to use.

    • @RocketLR
      @RocketLR 6 หลายเดือนก่อน +1

      @@mircorichter1375 I dont hink theres a need for a whole pr for that. I literally switched out the original line models.get_openai_chat()
      With models.get_ollama(model="llama3.1:8b").
      Then switch the embedding_llm = models.get_embedding_openai()
      with
      embedding_llm = models.get_embedding_hf()
      These methods that are in the models class are already there. I did zero contribution :(
      so it can already use ollama.. question is why the heck it needs perplexity or openai at all if you want to run all this localy.

    • @mircorichter1375
      @mircorichter1375 6 หลายเดือนก่อน

      @@RocketLR Not many people can run advanced local llms with enough TPS to make them useful

    • @javi-to-msaas
      @javi-to-msaas 6 หลายเดือนก่อน

      Knowledge database, things agent zero doesn't know. ​@@RocketLR

    • @MohamadAhmed-i6g
      @MohamadAhmed-i6g 5 หลายเดือนก่อน

      @@RocketLR can you tell me how to run it using Docker or do I need to use Anaconda, I just need help thank you.