WebGPU 7
Open-source browser AI components for private, offline applications
LocalMode UI is an open-source, MIT-licensed toolkit and shadcn-style registry for building privacy-first AI interfaces that run entirely in the browser. It provides more than 100 copy-owned React components and 36 installable blocks for chat, RAG, vector search, vision, audio, agents, privacy, and developer tools. Models run locally through WebGPU or a WebAssembly fallback, so applications can work without servers or API keys and keep user data on the device.
Open-source After Effects alternative for GPU-powered motion graphics
Premation is a free, open-source desktop motion-graphics editor designed as an alternative to Adobe After Effects. It combines timeline-based compositing, keyframe animation, graph editing, 2.5D cameras and lighting, text animators, rigging, vector tools, particles, effects, and deterministic GPU rendering in one application. Premation uses WebGPU when available and WebGL2 as a fallback, while its viewport and export pipeline share the same rendering engine so approved previews match final exports. Projects are saved locally as .motion files, and the editor supports formats including SVG, Lottie, MP4, WebM, ProRes, PNG sequences, GIF, image sequences, and WAV audio.
Omnibot is an in-browser AI platform that runs LLMs natively and privately.
Omnibot is an innovative AI platform that leverages WebGPU to run large language models (LLMs) natively in your browser, ensuring your data is processed securely on your device without any server-side interference. With offline functionality, Omnibot brings you an in-browser and offline AI experience. It allows you to use selected LLMs offline once the initial download of a model is processed. All AI models run locally (client side) on your hardware, ensuring that your data is processed only on your PC. You can also add custom instructions/memory to allow the AI to provide better and more personalized responses.
Browser-based private AI speech-to-text transcription
Whisper Web is a browser-based AI speech recognition tool powered by OpenAI Whisper. It transcribes audio in 100+ languages locally in your browser using WebGPU and WebAssembly, so no data leaves your device in Free mode. It also offers an Unlimited cloud plan for longer files and batch uploads.
Free, private browser-based AI tools for images, video, text, and design without sign-up.
AICreate is a comprehensive platform offering 68 free AI tools that run directly in the user's web browser. Unlike traditional AI services that process data on external servers, AICreate utilizes local device resources via WebGPU and ONNX Runtime to ensure complete privacy. The suite includes tools for image generation, background removal, video editing, text writing, and document management. It is designed to be accessible, requiring no sign-ups, no accounts, and no uploads, allowing most tools to function offline once the models are cached.
Access to DeepSeek R1, an open-source AI model for advanced reasoning.
DeepSeek R1 Online is a platform providing access to the DeepSeek R1 AI model, an open-source AI model for advanced reasoning. It offers both free and no-login access. DeepSeek R1 is designed for complex problem-solving, multilingual understanding, and production-grade code generation. It utilizes a Mixture of Experts (MoE) architecture and advanced reinforcement learning techniques to achieve high performance in mathematics, coding, and general reasoning tasks. The platform also provides access to distilled versions of the model for various use cases.
Browser-based hardware analyzer to check local AI model compatibility.
CanIRun.ai is a specialized web-based tool designed to help users determine if their local machine's hardware is capable of running various AI models. By utilizing browser APIs like WebGPU, the site analyzes the user's GPU, CPU, and RAM to provide compatibility scores and VRAM requirements for a vast library of models including Llama, Qwen, DeepSeek, and Phi. It offers detailed technical breakdowns for each model, such as architecture type, context window, and memory requirements across different quantization levels (from Q2_K to F16).
