Vibe Coding DiscoverTensorSharp
View on GitHubA native .NET LLM inference engine and agent runtime for GGUF models. TensorSharp provides a console application, a web-based chatbot interface, iPhone App, and Ollama/OpenAI-compatible HTTP APIs for programmatic access. It supports Windows/MacOS/iOS/Linux with full GPU capability
A native .NET inference engine for running GGUF language and multimodal models on CPU or GPU. Includes CLI, web chat, mobile and desktop apps, OpenAI- and Ollama-compatible APIs, embeddings, and an optional tool-using agent runtime.
Use Cases
Run local GGUF language modelsServe models through OpenAI-compatible APIsServe models through Ollama-compatible APIsBuild .NET applications with local LLM inferenceRun multimodal text, image, audio, and video workflowsGenerate and edit imagesGenerate video with audioCreate text and code embeddingsBuild tool-using agents with skills and subagent delegation
Built With
- Language
- C#
- Frameworks
- .NET · GGUF · CUDA · Metal · Vulkan
Tags
LLM inference · GGUF · local inference · multimodal · GPU acceleration · embeddings · image generation · video generation · agent runtime · C# · OpenAI-compatible API · Ollama-compatible API