All guides

Complete setup guide for Strimzi - an open-source Kubernetes operator for running Apache Kafka clusters in a cloud-native way. Originally created by Red Hat, now a CNCF Sandbox project. Includes installation, cluster configuration, topic management, and production best practices for running Kafka workloads on Kubernetes.

Build cloud-native microservices with Kratos - a lightweight Go framework with Protobuf APIs, HTTP/gRPC transport, and middleware.

Official comprehensive guide for LLaMA model inference, fine-tuning, RAG, and end-to-end use cases. Includes examples for domain adaptation and LLM applications.

Framework for fine-tuning LLMs with synthetic data using the LAB (Large-Scale Alignment for ChatBots) method. Now refactored into SDG Hub and Training Hub components.

Ray is an AI compute engine for scaling AI and Python applications. It consists of a core distributed runtime and a set of AI Libraries for accelerating ML workloads.

Use gRPC-Go to build high-performance RPC services with HTTP/2, code generation, and streaming support.

Deploy RAGFlow, a leading open-source Retrieval-Augmented Generation (RAG) engine that fuses cutting-edge RAG with Agent capabilities to create a superior context layer for LLMs.

Hire, schedule, and report on your entire AI agent team with 7x24 operations. A comprehensive framework for agent collaboration, memory, and scheduling.

A lightweight, offline-capable AI tool for automatic ID photo generation with portrait matting, background replacement, and layout photo creation.

Enable AI agents to autonomously execute 150+ cybersecurity tools for penetration testing, vulnerability discovery, and security research via Model Context Protocol.

Open-source infrastructure for running AI-generated code in secure isolated cloud sandboxes, enabling safe execution of LLM outputs for enterprise-grade AI agents.

Computer vision-based automation tool for Genshin Impact using AI recognition and OCR for task automation without game file modification.

AI-based tool for removing hardcoded subtitles and text watermarks from videos and images using advanced inpainting models. Local processing without third-party APIs.

Create animated short dramas from novels and scripts using AI. Integrated scriptwriting, storyboarding, character generation, and video creation in a cross-platform desktop application.

A comprehensive collection of production-tested AI infrastructure tools for AGI development, including GPU kernels, distributed systems, parallel file systems, and MoE training components.

Build and run Everywhere, the AI-powered desktop assistant that provides context-aware support with screen awareness, system command execution, and intelligent automation.

Set up DeerFlow 2.0, ByteDance's open-source long-horizon SuperAgent harness built on LangGraph and LangChain. Handle complex multi-step tasks with sandboxed execution, memory management, skills, and sub-agent orchestration.

Build production-ready real-time collaborative applications with Supabase, Yjs CRDTs, Tauri 2 desktop framework, and SvelteKit. Includes real-time sync, offline-first strategies, and multi-platform packaging.

Complete setup guide for building a full-stack Web3 application with AI capabilities using Next.js, IPFS, The Graph, RainbowKit, LangChain, and Vercel Edge Functions.

A comprehensive guide to building high-performance edge applications with Rust WebAssembly, Deno Deploy, Cloudflare Workers, and React 19. Learn to compile Rust to Wasm, deploy to edge platforms, and implement advanced caching strategies.

Build a modern serverless application with Astro 5 Islands architecture, Cloudflare R2 storage, Drizzle ORM, Qwik resumability, and edge caching.

Pass an RTX 3090 through to a dedicated Ubuntu 24.04 VM using VFIO. Covers IOMMU verification, driver blacklisting, VM creation strategy (install OS first, attach GPU after), and a snapshot discipline tailored to PCI-passthrough VMs.

Run multiple AI runtimes — OpenClaw, Hermes, and Claude Code — on one Ollama VM with serialised local inference via agents.defaults.maxConcurrent: 1, an issue-board orchestrator (Multica), and a workflow for inviting collaborators into the same workspace.

Keep vote counts and aggregate columns in sync atomically using Postgres triggers, instead of racing application code.