The easiest way to run open models locally and serve them through a developer-friendly API.

The C/C++ engine powering local AI — lightning-fast inference that Ollama and LM Studio build on.

Desktop app for discovering, running, chatting with, and serving local AI models.

Single-file portable local LLM — download and run anywhere

Self-hosted AI interface for Ollama, OpenAI-compatible APIs, tools, RAG, and teams.

High-throughput LLM serving engine — the production standard for GPU inference at scale.

Open-source ChatGPT alternative that runs 100% offline on your computer.

Free, local, privacy-aware AI — run chatbots on consumer hardware with no GPU required.

Open-source web UI for running, testing, and serving local language models.

Self-hosted OpenAI-compatible API — drop-in replacement for cloud AI in your infrastructure.

Open local AI writing and roleplay ecosystem centered on KoboldCpp and KoboldAI Lite.