SelfHostLLM
SelfHostLLM is a specialized GPU memory calculator designed to help users efficiently plan and manage the resources needed for self-hosted large language model (LLM) inference. It supports popular models such as Llama, Qwen, DeepSeek, and Mistral, enabling users to estimate GPU VRAM requirements and the maximum number of concurrent requests their hardware can handle. By factoring in model size, quantization, context length, and system overhead, SelfHostLLM provides a detailed breakdown of memory usage, helping developers and AI infrastructure planners optimize deployment configurations. This tool is essential for anyone running LLMs locally or on private servers, ensuring cost-effective and performant AI inference without over-provisioning hardware. With its clear formulas and step-by-step calculations, SelfHostLLM empowers users to make informed decisions about GPU allocation, model selection, and expected throughput, bridging the gap between complex AI models and practical hardware constraints.
Share your honest experience with SelfHostLLM
Website
selfhostllm.orgCategory
Open SourceTags
A2A Registry
A2A Registry is a community-driven directory that hosts live, production-ready AI agents compliant with the A2A (Agent-to-Agent) Protocol. It enables developers and organizations to easily discover, explore, and integrate AI agents that communicate seamlessly using a standardized protocol. The registry provides detailed information about each agent, including capabilities and integration examples, facilitating smooth adoption and interoperability. With Python SDK support, developers can connect to these agents programmatically, accelerating AI integration workflows. The platform promotes transparency and collaboration by listing verified agents and offering open access to the registry and client tools. A2A Registry serves as a vital resource for anyone looking to leverage AI agents in real-world applications, fostering an ecosystem where AI agents can interact, cooperate, and deliver enhanced automation and intelligence across diverse domains.
Konsta UI
Konsta UI is a comprehensive library of mobile UI components designed specifically for Tailwind CSS. It provides developers with a rich set of ready-to-use, customizable components that enable rapid development of mobile applications with a consistent and modern design. Konsta UI supports multiple frameworks including React, Vue, and Svelte, making it versatile for various development environments. The components are optimized for mobile experiences, featuring iOS and Material Design styles, which help developers build native-like user interfaces efficiently. By leveraging Tailwind CSS utility classes, Konsta UI ensures that the components are highly customizable and easy to integrate into existing projects. This UI kit is ideal for developers looking to accelerate their mobile app development process while maintaining high design standards and responsiveness.
Agentic Signal
Agentic Signal is a cutting-edge platform designed to empower users to build AI workflows visually with an emphasis on privacy and local execution. It enables developers, data scientists, and AI enthusiasts to create complex, extensible automation pipelines without relying on cloud services, ensuring that all data and processes remain fully local and secure. The platform supports a modular node ecosystem, allowing users to integrate various AI models, data sources, and custom logic into seamless workflows. By providing a visual interface for workflow construction, Agentic Signal lowers the barrier to entry for AI automation, making it accessible to a broader audience. Its architecture supports extensibility and customization, enabling users to tailor AI-driven solutions to their specific needs. With a focus on privacy, local intelligence, and ease of use, Agentic Signal is ideal for organizations and individuals seeking to harness AI capabilities while maintaining full control over their data and infrastructure.
mcp-use
MCP-USE is an open source software development kit (SDK) and infrastructure platform designed to facilitate the deployment and management of MCP (Multi-Channel Protocol) servers and agents. It provides developers and organizations with the tools necessary to build scalable, reliable, and efficient MCP-based communication systems. By leveraging MCP-USE, users can easily integrate multiple communication channels, automate messaging workflows, and maintain robust server-agent interactions. The platform emphasizes open source principles, ensuring transparency, flexibility, and community-driven enhancements. MCP-USE is ideal for applications requiring multi-channel communication capabilities, such as customer support systems, IoT device management, and distributed messaging networks. Its modular architecture and comprehensive SDK enable rapid development and seamless integration into existing infrastructures, making it a valuable resource for developers aiming to implement advanced communication protocols with minimal overhead.
Notes Migrator
Notes Migrator is a free, secure, browser-based tool designed to seamlessly convert and migrate notes between popular platforms such as Google Keep, Apple Notes, Evernote (.enex), and Markdown formats compatible with Notion. It operates entirely on the client side, ensuring 100% privacy and security by never uploading your data to any server. The tool supports easy import and export workflows, allowing users to handle their notes effortlessly without losing formatting or content integrity. With a user-friendly interface, Notes Migrator simplifies the complex process of transferring notes across different ecosystems, making it ideal for users switching devices or consolidating their note-taking apps. It supports large file uploads up to 200 MB and provides clear instructions for exporting and importing notes, enhancing productivity and data portability for individuals and professionals alike.
Custom Dashboards in OpenLIT
Custom Dashboards in OpenLIT provide a powerful, customizable, and self-hosted observability solution specifically designed for GenAI and large language model (LLM) applications. Built on the OpenTelemetry framework, OpenLIT enables developers and organizations to unify traces and metrics into a single, intuitive interface, simplifying the monitoring and performance analysis of complex AI-driven systems. These dashboards allow users to tailor the visualization and data presentation to their unique needs, offering deep insights into application behavior, performance bottlenecks, and operational health. By leveraging OpenLIT's open-source platform, teams gain full control over their observability infrastructure without vendor lock-in, enhancing transparency and security. The developer-friendly interface supports seamless integration with existing workflows and provides real-time monitoring capabilities that help accelerate debugging, optimize resource usage, and improve overall application reliability. OpenLIT’s custom dashboards empower users to transform how they track and understand their AI applications, making observability accessible, flexible, and efficient.