mudlerLocalAI
LocalAI is the open-source AI engine. Run any model - LLMs, vision, voice, image, video - on any hardware. No GPU required.
TL;DR · 30-second scan
LocalAI (Go) — LocalAI is the open-source AI engine. Run any model - LLMs, vision, voice, image, video - on any hardware. No GPU required.
You have code written against the OpenAI API and want to move inference in-house without rewriting it.
AI & ML · Self-Hosted
A drop-in replacement for the OpenAI API that runs models on your own hardware. Point an existing application at it by changing the base URL and it serves chat, embeddings, image generation, transcription and text-to-speech from the same endpoint. No GPU required, though one helps. MIT, Go, and it handles multiple model backends behind one interface. The tradeoff is the one every local-inference project has: compatibility is close but not exact, so applications that lean on newer OpenAI features — structured outputs, specific tool-calling behaviour — will hit gaps. Also more surface area than Ollama, which means more configuration when something misbehaves.
You have code written against the OpenAI API and want to move inference in-house without rewriting it.
You only need chat completions locally — Ollama is simpler — or you depend on the newest API features.
Add this badge to your README to show your project is curated on StackPicks. Free, lightweight (180×28 SVG), and gives your visitors a one-click way to see honest take + alternatives.
[](https://stackpicks.dev/repo/mudler-localai)
<a href="https://stackpicks.dev/repo/mudler-localai"><img src="https://stackpicks.dev/api/badge/mudler-localai" alt="Featured on StackPicks" width="180" height="28" /></a>
Are you the maintainer of mudler/LocalAI? Add the badge and we'll feature your project in the weekly curator newsletter.