WEBVTT 00:00:00.000 --> 00:00:02.400 Ready for AI coding on steroids? 00:00:02.400 --> 00:00:04.560 Today, we're focusing Autocloud 00:00:04.560 --> 00:00:08.000 where you can get 10 times the work done on your projects 00:00:08.000 --> 00:00:13.520 with the planning and the quality coding and testing that you should demand from your AI coding system. 00:00:14.085 --> 00:00:21.685 Now AutoCloud is designed to work for all skill levels from vibe coders without any coding experience to senior developers. 00:00:22.485 --> 00:00:24.725 Hi. My name is Andre Michelson, 00:00:24.725 --> 00:00:30.910 and I use AI to code production level applications every day. And today, I'm showcasing Autocloud, 00:00:30.910 --> 00:00:33.390 a open source and free project 00:00:33.550 --> 00:00:36.510 for using your cloud code subscription 00:00:36.510 --> 00:00:38.350 to get more work done. 00:00:39.470 --> 00:00:41.470 So when you're opening Autocloud 00:00:41.470 --> 00:00:49.345 and want to connect it to a existing project or create a new one, you just come to the top left corner here, add project, 00:00:49.505 --> 00:00:51.185 open existing folder, 00:00:51.905 --> 00:00:55.665 and when you open it, it's gonna prompt you to initialize Autocloud. 00:00:55.665 --> 00:01:01.770 That's gonna create a dot Autocloud folder inside your project. You just initialize 00:01:02.170 --> 00:01:15.125 and then the project is ready for you to use. And we're gonna start with showcasing the Kanban board here, which is the system for long running agents that just runs in the background. Now how it works is that you start engaging 00:01:15.365 --> 00:01:25.925 the system by just creating a task. And we're gonna start with one simple task where I found a little bug here in actual inside of AutoCode where we have a double crosshair. 00:01:25.925 --> 00:01:37.650 So we're just gonna take a screenshot of that and just paste it into the description and we see it gets added as a reference image to the task. And we're just gonna say here, and I'll use dictation. 00:01:39.425 --> 00:01:44.945 Please see the image in terms of the double cross for closing out the project files 00:01:44.945 --> 00:01:49.265 that's overlapping with the model for closing the create task model. 00:01:50.130 --> 00:01:57.010 So you can see now when we have some options here for selecting the model and the thinking level if you want more control. 00:01:57.170 --> 00:02:03.330 If you don't want any do any manual things, we have tried to keep things at a good level. 00:02:03.985 --> 00:02:07.825 We are gonna do a little bit of a work here where the system itself 00:02:07.905 --> 00:02:11.585 figures out what model and what thinking level it's gonna use. 00:02:11.825 --> 00:02:15.745 But as you can see now, we also have the section for requiring 00:02:15.745 --> 00:02:17.985 a human review before coding. 00:02:17.985 --> 00:02:22.330 If you want to work on more complex task where you want more control. 00:02:22.410 --> 00:02:25.130 But the system will work autonomously, 00:02:25.290 --> 00:02:29.450 and also we can drag and drop part project files here into the description. 00:02:29.530 --> 00:02:34.410 But right now, it's not working correctly. So we're gonna create a second task for showcasing 00:02:34.725 --> 00:02:36.565 how the system actually 00:02:36.805 --> 00:02:37.845 identifies 00:02:38.005 --> 00:02:40.565 how a task is either simple 00:02:40.645 --> 00:02:47.925 or it's a medium sized task or it's a very complex task. So you can see now it's written the task title itself. 00:02:48.005 --> 00:02:57.430 We don't have to do that if we don't want. And we can now just start this task and it will go into a planning phase where it starts to identify 00:02:57.510 --> 00:03:02.710 all the context it needs. It finds out what it needs to create as subtasks 00:03:02.710 --> 00:03:05.510 and also the complexity level of the task itself. 00:03:06.305 --> 00:03:12.945 So while that has started, we can start to see some logs. We will also create a new task here for the issue that 00:03:13.185 --> 00:03:15.585 we can't drag and drop files. 00:03:16.305 --> 00:03:27.010 When using the project files view, we cannot drag and drop the file into the description. There's only the section for reference files further down in the task section, 00:03:27.090 --> 00:03:32.530 but I think we should just mention below the description that the user can both paste screenshots 00:03:32.785 --> 00:03:36.385 and drag and drop files from the project file 00:03:36.545 --> 00:03:37.345 explorer. 00:03:37.825 --> 00:03:46.945 So now, in many cases, this is a description that's like we could give a lot more context into the task in order for it to be a much better task. 00:03:47.265 --> 00:03:52.000 And the system we're trying to like, Autocloud is gonna try and identify 00:03:52.000 --> 00:03:56.560 everything and also have a self review process. So it's gonna create a plan. 00:03:56.800 --> 00:03:59.360 We'll go here and see the logs have started. 00:03:59.775 --> 00:04:03.935 You can see now it's in planning phase and it has 27 entries. 00:04:04.095 --> 00:04:10.575 And if you want to review and understand what the AI is actually doing, you can see the logs here with all the tools, 00:04:10.735 --> 00:04:12.335 all the writings, and everything. 00:04:12.830 --> 00:04:24.350 And it has identified here, we can see the complexity level for the fixing overlapping close buttons. It has identified as a simple task with a confidence of 90%, 00:04:24.430 --> 00:04:37.495 and that dictates how everything is gonna work. It's just gonna go and have a quick spec and create a simple test for fixing or checking that it's actually fixed once it's done. So it's not gonna produce a lot of unnecessary 00:04:37.495 --> 00:04:47.080 tests, a lot of different coding, just so it saves upon the context itself here. So we don't have to pay more for a simple task integration. 00:04:48.360 --> 00:04:53.335 And if you're wondering, we are working on the same files here and the same systems, 00:04:53.495 --> 00:05:01.015 but how AutoCloud is working is that if we have a full overview over all the work trees that are for this project itself. 00:05:01.175 --> 00:05:05.655 So that means a work tree is basically a sandbox or in a environment 00:05:05.655 --> 00:05:17.510 where the coding is happening in one place and it won't touch any of the other files so you can safely work on the same as for instance, in this case, we're working on the same files on two different tasks. 00:05:17.750 --> 00:05:23.025 And then if you're a developer, you're gonna be like, hey, we're gonna have merge conflicts. But inside Autocloud, 00:05:23.025 --> 00:05:25.585 we have this merge conflict AI layer, 00:05:25.665 --> 00:05:31.665 which is doing a little bit of programmatic things, but also having an AI that does the refactoring 00:05:31.745 --> 00:05:46.680 and handling merge conflicts if there's any in these two tasks. So we're gonna see once it's done, we're gonna see that it's actually a merge conflict and we can just quickly with one button solve it and everything gets done correctly. 00:05:47.615 --> 00:06:08.140 So as this is working, you can already see that this simple task is already going over to an AI review. So the AI is gonna review its own work, and that's the power of AutoClaw that you can just have this running in the background, and it's only ready for you once the AI has deemed it ready for you to actually test and utilize straight into the project. 00:06:09.500 --> 00:06:11.900 So we also have this agents terminal, 00:06:11.980 --> 00:06:15.660 and this is a place where you can spawn up to 12 terminals 00:06:15.395 --> 00:06:18.755 and easily invoke Claude in all of the instances. 00:06:18.995 --> 00:06:25.875 And there's also some smart functionalities we're working on because myself, I like to have this type of terminal overview 00:06:25.875 --> 00:06:28.035 that I can rename 00:06:28.035 --> 00:06:45.430 terminals to what there's they are about, So I can hold my my thoughts when I navigate around, especially when you start to get more terminals, like when you start to get six and nine and even 12. Depends how much like multitasking you want to do. But for me, when doing 00:06:45.750 --> 00:06:52.975 like tasks, I want to rename the terminals. And also there's a smart functionality here in terms of that. You can add tasks 00:06:53.215 --> 00:06:57.775 just straight from the terminal view and you can also reference them 00:06:58.255 --> 00:07:02.660 basically like this and it will rename the terminal into the task description, 00:07:02.740 --> 00:07:19.255 and it will also give the description straight into the Cloud Code terminal. So you quickly can start new tasks if you have planned out things, but want to not utilize AI system with everything happening in the background, you want to be more hands on. This is the system that allows you to do that. 00:07:19.655 --> 00:07:28.215 We also have some session restoring so that you can close down the application and spawn it up again, and it will save the session so you can continue if anything happens. 00:07:28.710 --> 00:07:34.630 And we'll continue to iterate on this based upon how many people use the agent terminals in their day to day. 00:07:36.070 --> 00:07:49.785 We also have insights, which is basically just a chat with history, which is a cloud called instance that have access to your project, and you can spawn chat history here. Myself, I like to use this for more, like, just 00:07:50.185 --> 00:08:03.020 investigating things that I'm wondering about, maybe having a sparring partner, something like that is nice to have. And also the roadmap functionality is a very good thing for you actually getting good traction 00:08:03.020 --> 00:08:04.300 with your project. 00:08:04.620 --> 00:08:09.820 So here you can see we have different views for creating a roadmap and we're also gonna be integrating 00:08:09.980 --> 00:08:16.275 third party software like Canny in order to get feedback from users from those softwares 00:08:16.275 --> 00:08:19.715 and just incorporating it straight into the Autocloud system. 00:08:19.955 --> 00:08:24.035 So here you can see the AI has tried to identify your target audience, 00:08:24.195 --> 00:08:34.090 and then it's breaking down features that you should implement into your project. This is just gonna become better and better as the more you use it because 00:08:34.330 --> 00:08:43.735 Autocloud has its own memory layer. So we can go here to context, and the first thing you'll see is the project index. So it's basically what we can programmatically 00:08:43.735 --> 00:08:57.830 figure out what the project is about. It has identified we are in the auto cloud repo here, and it is in in identify the electron front end and the Python back end with the API routes and the dependencies 00:08:57.910 --> 00:09:01.910 just so that things like this, the actual project infrastructure 00:09:01.990 --> 00:09:04.870 is quickly given as context to the user. 00:09:05.430 --> 00:09:11.945 And something we're working very heavily on is the memory system. It's a graph memory system 00:09:12.105 --> 00:09:12.825 also 00:09:12.985 --> 00:09:21.465 incorporated with semantic rag. If you don't know what that means, it's basically that we have different methods for letting the AI know about your project. 00:09:21.625 --> 00:09:24.665 And as you're doing and you're working with tasks here, 00:09:25.220 --> 00:09:28.020 the more you use it, the smarter the system becomes. 00:09:28.340 --> 00:09:32.500 And for people who has a little bit more knowledge about context windows 00:09:32.660 --> 00:09:44.645 and token usage, the more you use Autocloud, the smarter it becomes at actually retrieving context at a smaller token usage. So it will become cheaper to actually use Autocloud 00:09:44.645 --> 00:09:47.605 over cloud code when you use it over time. 00:09:48.405 --> 00:09:57.470 So the roadmap functionality definitely is something to check out and see what it suggests that you should do for your project. But also we have the ideation 00:09:57.470 --> 00:10:04.750 tab here where we just can get some quick tasks if you're not sure about what you should do. And also if you have something like, 00:10:04.910 --> 00:10:08.645 I just want to see, for instance security 00:10:08.965 --> 00:10:23.990 and code improvements at a general step, you can generate that and Autocloud will figure out based upon your project, investigate where how do we have some security issues. We also have performance, so we can do performance enhancement. 00:10:24.150 --> 00:10:26.790 But also like code improvements is generally 00:10:26.950 --> 00:10:30.870 is trying to locate a low hanging fruits, quick wins, 00:10:31.030 --> 00:10:35.990 where we can quickly incorporate something that has good value for the users of the project. 00:10:37.005 --> 00:10:49.325 So let's go just go back here and see. You can see now that the two tasks that we have done is done with AI review. We can see here it hasn't identified actually that there is any merge conflicts ready for this. 00:10:50.340 --> 00:10:52.020 Let's just recheck it. 00:10:53.060 --> 00:11:08.025 In these tasks, you can go in and see the sub tasks, what it has done. You can also check the full logs in terms of what it did for validation, what it did for coding, so you have full overview over what the AI system has actually done for each of these. 00:11:08.505 --> 00:11:13.145 We're just gonna let this run because it finds five different things with each category. 00:11:13.385 --> 00:11:24.320 And while we do that, we'll talk about the change log functionality inside AutoCloud, and it's something I really like. It has the possibility to create change logs and also it's integrated with GitHub, 00:11:24.560 --> 00:11:30.560 so you can create a change log based upon either all the tasks you have done inside AutoCloud. 00:11:30.560 --> 00:11:33.280 But what we use most is to get history 00:11:33.625 --> 00:11:45.225 because I like to work with both the task Kanban board, but also like I showcased more manually. So I'm manually doing commits to GitHub, and I'm manually doing work with AI. 00:11:45.990 --> 00:11:58.870 That makes it so that when you go into Git history here, you can for instance say since last version, say, and we are version 2.1 right now, and it would actually load all the commits that's happening since that version, 00:11:59.030 --> 00:12:00.070 and you can just continue. 00:12:01.115 --> 00:12:04.075 And we will say two point o version, 00:12:04.955 --> 00:12:08.555 and this is a GitHub release, and we want some emojis. 00:12:08.875 --> 00:12:12.475 And it's done just like that, it's gonna generate a change log, 00:12:13.330 --> 00:12:23.170 And it's quite quick. We don't use opens for this functionality right now, and you'll see it identifies the new features, improvements, bug fixes, and also all the changes. 00:12:23.410 --> 00:12:32.285 So we can quickly just save this to the change log. And once it does that, we can just click create release, and that goes straight up until GitHub. 00:12:32.605 --> 00:12:37.325 So that's a very fast way to get good change logs and do GitHub releases. 00:12:37.645 --> 00:12:40.445 If you want something like that for your project, 00:12:40.685 --> 00:12:44.720 I do recommend using the change log for actually 00:12:44.880 --> 00:12:50.000 keeping track of what's happening inside your project just so you have control over time. 00:12:50.480 --> 00:13:06.255 So we talked about the context as well. It's something we really are working hard on and there's integrations with GitHub issues. So GitHub issues will come straight into Autocloud, and you can create tasks, and it can start to identify what's wrong and fix it automatically in the background. 00:13:08.170 --> 00:13:13.130 There's a lot of other things that's coming. There's a lot of good things in the settings. 00:13:13.370 --> 00:13:16.890 For instance, if you are a very heavy power user 00:13:17.050 --> 00:13:19.290 like me, you can utilize 00:13:19.930 --> 00:13:29.205 the integrations tab here. We have multiple cloud accounts. Because what AutoCloud actually allows you to do is to create a lot of tasks 00:13:29.285 --> 00:13:33.765 and just run them in the background, so you get a lot of features done quickly. 00:13:34.085 --> 00:13:37.045 But that also implies that you're getting things done 00:13:37.540 --> 00:13:45.780 not only quicker, but for instance, I get a lot of tasks done while I sleep. So basically, all my Cloud Code usage has doubled, 00:13:45.780 --> 00:14:10.550 so I need two Cloud Code Max plans. And we have created a system that you can incorporate both of them into the AutoCloud system and easily swap between them, and we will incorporate some type of like auto switching, so it knows about what the rate limits for one account and it swaps when you need to swap, basically. So now we can go ahead and just get the task into our project. 00:14:10.790 --> 00:14:14.230 We open the task which is ready now for human review, 00:14:14.390 --> 00:14:16.470 and we just press stage changes. 00:14:17.165 --> 00:14:22.845 And that makes it so that if there's any merge conflicts, it's gonna solve that by itself. 00:14:23.165 --> 00:14:39.060 And we can go here into the IDE now and we see that the changes have come into our repo and we can repute review them if we want And we now also can just go into the you can see here the changes staged successfully. 00:14:39.380 --> 00:14:49.345 So if there is any merge conflicts, and this is a very good, which I appreciate, which is the merge conflict AI layer that fixes merge conflicts automatically. 00:14:49.585 --> 00:14:54.305 So you can work on a lot of tasks and also work manually in other branches, 00:14:54.625 --> 00:14:57.825 and the system will follow along as files evolve. 00:14:58.400 --> 00:15:02.960 But we can now go and see if this is successful. This was the fix overlapping buttons 00:15:03.040 --> 00:15:26.045 and that was that if we go here and we see it browse the files, you can see now the task was successful. It implemented it and we can go ahead and merge this with our main branch. So what's coming next? We have a great focus on the framework itself that runs behind the hood. We also have the Python CLI that you can utilize if you don't want to use the front end electron application. 00:15:26.820 --> 00:15:28.980 Now we're also working on incorporating 00:15:28.980 --> 00:15:32.420 the bMAD method for context engineering, 00:15:32.420 --> 00:15:34.180 AI coding, validation, 00:15:34.260 --> 00:15:38.180 and we're just gonna put it on steroids by putting it inside AutoCloud 00:15:38.180 --> 00:15:43.395 where we get, like, the long running agents, QA looping, rag memory system, 00:15:43.635 --> 00:15:54.515 and much more. We also welcome everybody to our free Discord community. The link is in the description to talk about features, bugs, and you can also network with like minded AI enthusiasts, 00:15:54.590 --> 00:16:04.030 developers, entrepreneurs, marketers, and also a lot of people there, and then generally a nice community to feel at home. So stay tuned for big productivity 00:16:04.030 --> 00:16:04.670 update. 00:16:05.550 --> 00:16:22.665 So I just wanted to showcase how you can install AutoCloud if you're wondering about how to do that. We have a very descriptive quick install description if you want to follow along that. If not, here's how you do it quickly. You download the zip file here on GitHub and the link is down in the description. 00:16:24.670 --> 00:16:26.270 Then you go and 00:16:26.430 --> 00:16:31.070 you create either a new folder or you unzip the autocloud folder 00:16:31.230 --> 00:16:33.230 which is which you downloaded. 00:16:33.470 --> 00:16:46.655 And you just go to your favorite IDE. Here, we're using cursor just because it's simple to use with AI especially if you're a beginner and we just open up the folder that we just unzipped. 00:16:47.775 --> 00:16:50.335 Now we have the Autocloud 00:16:51.775 --> 00:16:56.010 project open here. And the first thing you're gonna do is that if you 00:16:56.970 --> 00:16:59.450 is that if you haven't installed 00:16:59.690 --> 00:17:01.770 the NodeJS 00:17:01.770 --> 00:17:04.010 Python and Docker desktop, 00:17:04.170 --> 00:17:04.890 just follow 00:17:05.385 --> 00:17:13.225 the instructions or just what you also can do is basically just copy and paste this into something like 00:17:14.025 --> 00:17:16.025 cursor and just say help me 00:17:16.425 --> 00:17:19.500 install this and it will help you do that 00:17:19.820 --> 00:17:27.020 based upon your system and that's actually a very quick way for you to get started. Once everything is installed, 00:17:27.500 --> 00:17:29.660 you're just gonna do the 00:17:30.035 --> 00:17:32.115 first step here which is to 00:17:32.515 --> 00:17:46.020 do these commands inside the terminal here. So if you don't have UV, you can basically just tell Opus to or or the agent you have inside cursor or any other a AI agent to just help me use 00:17:46.580 --> 00:17:52.340 UV, which is basically just for managing the packages here in a environment. 00:17:52.580 --> 00:17:55.940 Or you can use this you can try this also 00:17:56.020 --> 00:17:56.660 if you're 00:17:57.605 --> 00:18:00.565 if the first command here is failing. 00:18:01.925 --> 00:18:04.805 That will basically spin up a virtual 00:18:04.805 --> 00:18:05.685 environment 00:18:05.685 --> 00:18:08.885 and install everything, so now it's ready to be used. 00:18:10.980 --> 00:18:16.740 The next step is to actually start the memory layer, and here we need Docker Compose in order to do that. 00:18:17.060 --> 00:18:21.460 So you will just go and do this command in its own database. 00:18:22.035 --> 00:18:26.915 It will create the database and spin up what's necessary for the memory to work. 00:18:27.235 --> 00:18:34.195 And the last thing is to actually just install and launch the application. So we're gonna do p n p m install that installs everything, 00:18:35.250 --> 00:18:37.810 And then just command copy this command 00:18:38.130 --> 00:18:47.810 once it's done here. So now it will just build everything and it will start the application as soon as it's done. And it's taking quite a short amount of time. 00:18:48.975 --> 00:18:52.095 And now we can see we're getting a new application 00:18:52.495 --> 00:18:53.935 up and going here. 00:18:54.575 --> 00:18:55.215 So 00:18:55.375 --> 00:18:57.855 there you have it. It's up and going. 00:18:59.535 --> 00:19:08.800 And if you have any questions, I highly suggest you join our Discord community. I will be very interactive there in terms of helping you if you have any issues or bugs. 00:19:09.120 --> 00:19:13.200 And if you have liked the video, be sure to subscribe 00:19:13.200 --> 00:19:15.280 and like it and 00:19:16.090 --> 00:19:27.370 help other people find this amazing system that we are working on so we can get going with our projects at lightning speed while keep keep still keeping that quality that we want from our AI coding.