Is LocalAI still maintained?

Yes, active. Last change today. Latest release v4.12.1, 19 days ago.

Widely used. 50k stars, 3 years old. As with any download, get it from the official repo.

How to install on Windows

mudler/LocalAI

LocalAI is the open-source AI engine. Run any model - LLMs, vision, voice, image, video - on any hardware. No GPU required.

Go#agents#ai#api#audio-generation

Before you start

Is it free?: YesOpen source (MIT).
Still maintained?: Yes, activeLast change today. Latest release v4.12.1, 19 days ago.
Can I trust it?: Widely used50k stars, 3 years old. As with any download, get it from the official repo.

Difficulty: Easy
Time: about 5 min
Stars: ★ 50,310
Activity: Updated this month

Saved setup from 11 h ago

Will it work on Windows?

Yes, with Docker on Windows

Apps are only published for macOS and Linux.
It's a self-hosted app: the README runs it with Docker, and you open it in your browser.
On Windows that means installing Docker Desktop first.

Your system

macOS Windows Linux

Start here

Website ↗localai.ioThe project's own site.

Also: In the browser ↗

Run it with Docker

A self-hosted app: Docker runs it on your computer and you open it in the browser. Needs Docker Desktop (or Docker Engine on Linux). Run docker compose commands inside the cloned repo folder.

Docker

docker run -ti --name local-ai -p 8080:8080 localai/localai:latest

Docker

docker run -ti --name local-ai -p 8080:8080 --gpus all localai/localai:latest-gpu-nvidia-cuda-13

From the README, exactly as the maintainers wrote it.

Did you get it running?

No reports for Windows yet.

Still stuck? Get a written guide

GitManual AI Agent reads the 14 key files and writes a step-by-step guide for Windows. Once written, it's saved for everyone.

Parts list

1×Go 1.26.0runtime
1×Docker tool

Share this manual

Is this your repo?

Add a badge to your README so newcomers find these steps.

[![Setup manual](https://gitmanual.com/mudler/LocalAI/badge.svg)](https://gitmanual.com/mudler/LocalAI)

Good to know

Several programs live in cmd/ (launcher, local-ai). Run one with go run ./cmd/<name>; the README says which is the app.
The README mentions NVIDIA CUDA. Check its hardware section: some features (or all of them) may need an NVIDIA GPU.
Dockerfile available (base image: ${BASE_IMAGE}).
Dev Container config found — you can open it in VS Code Dev Containers or GitHub Codespaces for a zero-setup environment.
Has AGENTS.md — instructions for coding agents. You can open Claude Code (or another agent) in the cloned folder and ask it to do the setup for you.
Nested projects: addons/calendar/ui/package.json, addons/contacts/ui/package.json, addons/discord/ui/package.json, addons/face/ui/package.json and 11 more

Details

License: MIT
Open issues: 185
Branch: master

Files we read (14)

.devcontainer/devcontainer.json

.github/workflows/addons-tests.yml

.github/workflows/backend_build.yml

.github/workflows/backend_build_darwin.yml

.github/workflows/build-test.yaml

.github/workflows/checksum_checker.yaml

.github/workflows/ci-tools-tests.yaml

.gitmodules

CONTRIBUTING.md

Dockerfile

Makefile

README.md

docker-compose.yaml

go.mod

9,074 files in the repo

Yes, with Docker on Windows

Start here

Run it with Docker

Did you get it running?

Still stuck? Get a written guide

More like LocalAI that run on Windows