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
Autumn
Autumn is a streamlined and flexible platform designed to simplify pricing and billing for app founders, especially AI startups. By integrating directly with Stripe, Autumn enables users to effortlessly set up and manage complex pricing models with just a few functions. The platform supports tracking usage limits, managing feature entitlements, credits, and add-ons, providing comprehensive control over monetization strategies. Autumn’s intuitive approach reduces the complexity of payment infrastructure, allowing developers to focus on building their products rather than handling billing logistics. Its seamless integration and developer-friendly API make it an ideal solution for startups looking to scale efficiently while maintaining precise control over customer billing and feature access. Autumn effectively bridges the gap between product development and payment management, making Stripe easy and accessible for AI-driven businesses.
Kelma
Kelma is an open-source, drop-in comment section provider designed for every website. It offers an ad-free and privacy-respecting platform that ensures minimal telemetry collection and never sells user data. Kelma is built for speed, delivering an incredibly snappy user experience where comments load instantly and interactions feel smooth. The solution is fully transparent and auditable, allowing users to choose between hosted or self-hosted deployments. Kelma supports effortless setup with easy customization, offering 35 themes to seamlessly integrate with any website design. It also supports multiple languages, making it accessible globally. Pricing is fair and usage-based, with no tiers, plans, hidden fees, or monthly subscriptions, allowing users to pay only for what they use. Overall, Kelma provides a modern, privacy-conscious, and highly customizable comment system that enhances user engagement without compromising performance or user data privacy.
Tiny Code Share
Tiny Code Share is a privacy-first web application designed for developers who need to share code snippets instantly and securely. Unlike traditional code sharing platforms, Tiny Code Share operates entirely on the client side, ensuring that no code is ever stored on any server. This approach guarantees complete privacy and security, as all code remains within the user's browser and is shared via URL fragments. The platform supports automatic language detection and syntax highlighting, making shared snippets easy to read and understand. It is mobile responsive and open source, catering to developers who value simplicity, privacy, and efficiency. Tiny Code Share requires no user accounts or sign-ups, streamlining the sharing process while maintaining a strong focus on user privacy. Built with modern web technologies, it supports a wide range of programming languages including JavaScript, Python, Java, C++, and more, making it a versatile tool for developers across different coding environments.
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.
AGINT
AGINT is an innovative open-source interface layer designed to empower Large Language Models (LLMs) with the ability to control your computer directly and safely. It enables AI to interact with your operating system by manipulating the mouse, keyboard, filesystem, browser, and applications, all while maintaining transparency through auditable logs and permission controls. AGINT prioritizes security by incorporating human-in-the-loop oversight, ensuring that AI actions are monitored and controlled by users. This platform is ideal for developers, researchers, and teams looking to integrate AI-driven automation and control into their workflows. With a focus on cross-platform compatibility and an MIT license, AGINT fosters an open and collaborative environment for hackers and teams to innovate. Early prototypes and demos are available on GitHub, showcasing its potential to revolutionize how AI interfaces with computing environments, making AI a practical and powerful assistant for everyday computer tasks.
Puck
Puck is an open-source visual editor designed specifically for React applications. It empowers developers to seamlessly integrate powerful visual editing capabilities into their own React projects, enabling the creation of intuitive and dynamic content editing experiences. By leveraging Puck, teams can build next-generation content tools that simplify the process of managing and customizing UI components without sacrificing developer control or flexibility. The editor supports a highly customizable and extensible architecture, making it ideal for a wide range of use cases, from content management systems to complex web applications. Puck’s open-source nature encourages community collaboration and continuous improvement, ensuring it evolves alongside the React ecosystem. Its focus on developer experience and user-friendly interfaces helps bridge the gap between design and development, accelerating workflows and enhancing productivity. Overall, Puck serves as a robust foundation for building sophisticated visual editing solutions that integrate deeply with React’s component model.