LocalAI

A local AI engine with OpenAI, Anthropic and ElevenLabs compatible APIs for text, vision, voice, image and video models, on any hardware, no GPU required.

50.1k stars, 4.6k forks Go On GitHub since March 2023

Visit website View on GitHub How to run it

What is LocalAI?

LocalAI serves many kinds of models behind familiar APIs. Its core is small: each backend, such as llama.cpp, vLLM, whisper.cpp, Stable Diffusion or MLX, comes as a separate image that is pulled only when a model needs it. It runs on NVIDIA, AMD, Intel, Apple silicon, Vulkan or plain CPUs, and adds API keys, user quotas and roles for shared use. Apps written for the OpenAI API can usually point at LocalAI without code changes.

Good fit if

  • You need speech, image and text models behind one local API, not only chat.
  • You run on mixed or CPU-only hardware.
  • You want existing OpenAI-based software to use local models instead.

Look elsewhere if

  • You only want local chat models with simple downloads: Ollama.
  • You serve heavy GPU traffic: vLLM.

Before you adopt it

LocalAI is MIT-licensed, with no paid edition. It started as Ettore Di Giacinto's personal project and is still led by him, with about ten active contributors.

Drafted with AI from the project's README and repository data, then checked against that data on 30 October 2026. Report a correction

LocalAI health: is it still maintained?

75 of 100, actively developed

  • Activity
    1,433 commits in the last 90 days, the latest on 31 October 2026.
    30 / 30
  • Contributors
    3 people wrote the latest 100 commits; the most active wrote 75% of them.
    8 / 20
  • Releases
    15 releases in the last 12 months; the latest, v4.12.1, on 23 October 2026.
    19 / 20
  • Replies to issues
    Maintainers answered 11% of recent issues, with a median first reply after 9 hours.
    13 / 20
  • Security practices
    No OpenSSF Scorecard for this repository yet, so this part gets a neutral score.
    5 / 10

Read from GitHub on 1 November 2026. How the score works

LocalAI license: is it open source?

LocalAI uses MIT, an open-source license approved by the OSI.

  1. March 2023First published on GitHub.
  2. TodayMIT.

How to run LocalAI yourself

Docker
Dockerfile or compose file in the repository
Compose file
docker-compose.yaml: 1 service
Setup effort
1 of 5, judged from the compose file
Kubernetes
No Helm chart in the repository
Desktop and mobile
Builds for Linux, macOS, including ARM in GitHub releases
Interface languages
7 languages

Install instructions: localai.io or the README on GitHub.

Alternatives to LocalAI

  • DocsGPTPrivate AI platform for agents, assistants and enterprise search. Built-in Agent Builder, Deep research,… 84 health · MIT · 18.4k stars
  • HarborStop configuring your AI stack. Start using it. One command brings a complete pre-wired LLM stack with… 80 health · Apache-2.0 · 3.3k stars
  • Open WebUIUser-friendly AI Interface (Supports Ollama, OpenAI API, ...) 76 health · Open WebUI License · 157k stars
  • vLLMA high-throughput and memory-efficient inference and serving engine for LLMs 84 health · Apache-2.0 · 96k stars
  • FastGPTFastGPT is a knowledge-based platform built on the LLMs, offers a comprehensive suite of out-of-the-box… 82 health · FastGPT Open Source License · 30k stars

All 36 projects in AI chat & local LLMs

Questions about LocalAI

Is LocalAI open source?

Yes. LocalAI is published under MIT, an OSI-approved open-source license.

Is LocalAI still maintained?

Its health score is 75 of 100 (actively developed). It had 1,433 commits in the last 90 days, the latest on 31 October 2026, and its latest release came out on 23 October 2026.

How do I run LocalAI?

You can run it with Docker, as an app for Linux, macOS, including ARM. The README on GitHub has the exact steps.

What are the alternatives to LocalAI?

Close alternatives in the AI chat & local LLMs category include DocsGPT, Harbor, Open WebUI.