opensource.fyi — AI & Machine LearningModels, runtimes, agents and tooling for building with machine learning.https://opensource.fyi/categories/ai-ml/llama.cpp — LLM inference in plain C/C++, from laptops to servers.https://opensource.fyi/projects/llama-cpp/https://opensource.fyi/projects/llama-cpp/llama.cpp is an open source C/C++ engine for running large language models locally, with quantisation, GPU backends and an OpenAI-compatible server.Tue, 10 Nov 2026 08:30:00 GMTllminferencelocal-aiquantizationOpen WebUI — A self-hosted, offline-capable chat interface for local and remote AI models.https://opensource.fyi/projects/open-webui/https://opensource.fyi/projects/open-webui/Open WebUI is a self-hosted web interface for chatting with AI models. It works with Ollama and OpenAI-compatible APIs, supports RAG and runs fully offline.Tue, 10 Nov 2026 08:20:00 GMTllmchat-uiself-hostedlocal-aiTransformers — Pretrained models for text, vision, audio and multimodal tasks, with one consistent API.https://opensource.fyi/projects/transformers/https://opensource.fyi/projects/transformers/Hugging Face Transformers is an open source library that provides thousands of pretrained models for text, vision, audio and multimodal tasks behind one API.Tue, 10 Nov 2026 08:10:00 GMTmachine-learningdeep-learningpytorchnlpLangChain — A framework for building applications and agents on top of large language models.https://opensource.fyi/projects/langchain/https://opensource.fyi/projects/langchain/LangChain is an open source Python framework for building LLM applications and agents, with integrations for hundreds of model providers, vector stores and tools.Tue, 10 Nov 2026 08:00:00 GMTllmagentsragframeworkOllama — Download and run large language models on your own machine with one command.https://opensource.fyi/projects/ollama/https://opensource.fyi/projects/ollama/Ollama is an open source tool for running large language models locally. It handles model downloads, GPU acceleration and serves a local HTTP API on macOS, Linux and Windows.Fri, 06 Nov 2026 00:00:00 GMTllmlocal-aiinferencemodel-runner