Comput3 Tutorials

# Comput3 Tutorials In this post I'm compiling a growing list of tutorials covering various applications that you can fuel with your comput3 account. Some of these will be fairly simple that everyone can follow while others target advanced users as they require additional server setups. First of all lets set the stage and explain why you wanna run open source apps on your machines. ## What is Comput3 ? Comput3.ai allow users to own a stake in gpu infrastructure via [$com token](https://dexscreener.com/solana/34qhkhrhyningwruftqjnb2vfv8oqyqd5tvdwwde1man) which can be staked to access llm inference and aswell as gpu hours to spin up ComfyUI, Ollama and other services to run genAI workload and fuel more complex pipelines with compute. <iframe style="width:100%;display:inline-block;padding:0px" height="420"src="https://www.youtube.com/embed/8aJF1sAhWKY " title="YouTube video player" frameborder="0" allow="accelerometer; autoplay; clipboard-write; encrypted-media; gyroscope; picture-in-picture" allowfullscreen></iframe> Compared to Anthropic, OpenAI they don't store your data. Their business model isn't built around collecting customer data which cloud providers do to train models etc which is very important as you don't want your software pipelines to leak data. With different tiers of monthly budget, companies and individuals can fuel their apps and workflows with AI to enrich the user experience for themselves and their users across various facets. [<img src="https://hackmd.io/_uploads/rJtdXkVHlg.png"/>](https://hackmd.io/_uploads/rJtdXkVHlg.png) *Outdated screenshot: The API now serves Kimi K2 (1 trillion params), the new Deepseek 3.1 and Qwen3 Coder 480b in q8 with their respective max context windows. For Qwen3 thats 256k tokens and for the other open source SOTA models its 128k.* Looking at the staking tiers you'll realize that 1mn $com effective enables you to run heavy genAI workload 24/7 as an entire month as around 720 hours. At the same time 10k $com already grant unlimited tool enabled Llama3:70b inference, enabling most of these tutorial. <br> ## Vibecoding ### Visual Studio Code Vscode is one of the best Vibecoding Setups out there. The Compatibility with Open Source models and mcps is amazing. You can set this up in under 10 mins. [<img src="https://hackmd.io/_uploads/SkOxMDDFel.png"/>](https://hackmd.io/@reneil1337/c3-vibe) Learn how: https://hackmd.io/@reneil1337/c3-vibe ### Cursor Probable the most used Vibecoding IDE out there. Similarly to vscode you can plug in your own open source models via Kilo and get things going in under 10 mins. [<img src="https://hackmd.io/_uploads/HJipTGoYlg.png"/>](https://hackmd.io/@reneil1337/c3-vibe) Learn how: https://hackmd.io/@reneil1337/c3-vibe ### Claude Code - CLI based agentic coding tool Claude Code is an agentic coding tool that lives in your terminal, understands your codebase, and helps you code faster by executing routine tasks, explaining complex code, and handling git workflows -- all through natural language commands. Use it in your terminal, IDE, or tag @claude on Github. [<img src="https://hackmd.io/_uploads/r1kZ0zmKge.png"/>](https://hackmd.io/@reneil1337/c3-vibe) Learn how: https://hackmd.io/@reneil1337/c3-vibe ## Simple: AI tools for your personal computer Lets start with some basic llm apps that you can run on your computer. You can already use these with the base tier as those services don't require gpu hours. You'll see that the barrier of entry is extremely low which makes comput3 so interesting. ### Jan - An Open Source ChatGPT [<img src="https://hackmd.io/_uploads/HkN2I6Xrxl.png"/>](https://hackmd.io/@reneil1337/c3-jan) The open source software Jan is a simple chat interface for Linux, Mac and Windows that allows you to bring your own open source llms and talk to them. All the data is stored on your local machine and more features are being added by their community. Learn how: https://hackmd.io/@reneil1337/c3-jan <br> ### Leo - Brave Browser Assistant [<img src="https://hackmd.io/_uploads/rJLnk14Bex.png"/>](https://hackmd.io/@reneil1337/c3-leo) Leo is an AI assistant that is integrated into Brave Browser. You can open the sidebar via ctrl-B on every website while you're browsing, let it summarize the page with a single click and ask all sorts of questions about the content thats displayed on your screen. Learn how: https://hackmd.io/@reneil1337/c3-leo <br> ## Advanced: Fuel server-side applications with intelligence In this section you find ai-driven solutions that are more sophisticated and can massively increase productivity that either help to automate all sorts of things for your private life and businesses or make comput3 fueled intelligence available across multiple devices. ### n8n - Workflow Automation [<img src="https://hackmd.io/_uploads/B1M9IZSSxx.png"/>](https://hackmd.io/@reneil1337/c3-n8n) n8n is a workflow automation platform that gives technical teams the flexibility of code with the speed of no-code. With 400+ integrations, native AI capabilities, and a fair-code license, n8n lets you build powerful automations while maintaining full control over your data and deployments. The ability to drive these flows via AI agents make it stand out. There are two ways to get started with n8n: Either you decide to use the n8n cloud where you can create an account with few clicks or you decide to self-host the community edition yourself in your own homelab or on a small VPS that you're running. Learn how: https://hackmd.io/@reneil1337/c3-n8n ### Open WebUI - Private ChatGPT for all your devices [<img src="https://hackmd.io/_uploads/rJVJ7hYFlx.png"/>](https://hackmd.io/@reneil1337/c3-openwebui ) Open WebUI is an extensible, feature-rich, and user-friendly self-hosted AI platform designed to operate entirely offline. It supports various LLM runners like Ollama and OpenAI-compatible APIs, with built-in inference engine for RAG, making it a powerful AI deployment solution. Learn how: https://hackmd.io/@reneil1337/c3-openwebui --- ### Bookmark this post as more and more tutorials will be added!