Show HN: Self hosting a modern LLM stack (github.com)

llmaker, an open-source platform, has emerged as a revolutionary tool for self-hosting modern large language model (LLM) stacks on personal infrastructure. This streamlined solution enables users to deploy comprehensive setups—including LLMs, vector databases, embeddings, and observability tools—through a single command, eliminating the complexities traditionally associated with configuring multiple services and dependencies. With llmaker, developers can build private chatbots, FAQ assistants, and recommendation systems without relying on third-party API keys or risking data exposure, ensuring total control over their applications. This innovation is significant for the AI/ML community as it democratizes access to advanced LLM capabilities by simplifying the deployment process, making it accessible for smaller teams and individual developers. Key features include automatic service discovery, a built-in retrieval and agent layer for multi-turn interactions, and integrated observability tools that allow for real-time tracking of model performance and resource usage. The platform also supports OpenAI-compatible APIs and facilitates declarative stack management, which not only streamlines the deployment process but also promotes cost-effective utilization of local infrastructure without the burdens of variable pricing or vendor lock-in.