# LocalAI

Framework · https://godooo.ai/en/framework/localai

> LocalAI is an open-source AI framework, launched in 2023, made for developers and businesses.

A self-hosted engine that serves LLMs, speech, image and video models behind an OpenAI-compatible API.

Main jobs: LLM API, Model serving, Run models locally. It is open source and free to use. You can use it on your own server, offline on your own machine, through an API and in the terminal.

## At a glance

- **Type:** [Framework](https://godooo.ai/en/browse#framework)
- **Launched:** 2023
- **Galaxy:** [Models & APIs](https://godooo.ai/en/galaxy/builders)
- **Open source:** Yes · MIT
- **Source code:** [github.com/mudler/LocalAI](https://github.com/mudler/LocalAI)
- **GitHub stars:** 49,253
- **How you run it:** Self-host · Runs offline · API · Terminal
- **Made for:** Developers · Businesses
- **Protocols:** [OpenAI-compatible API](https://godooo.ai/en/protocol/openai-compatible-api)
- **Website:** [localai.io](https://localai.io)

## What it can do

- **[LLM API](https://godooo.ai/en/capability/llm-api)** — main job, _proposed by a machine, awaiting calibration_. “Drop-in API compatibility : OpenAI, Anthropic, and ElevenLabs APIs across every backend” (read on [github.com](https://github.com/mudler/LocalAI), 2026-09-24)
- **[Model serving](https://godooo.ai/en/capability/model-serving)** — main job, _proposed by a machine, awaiting calibration_. “One binary with an OpenAI-compatible API in front of it.” (read on [localai.io](https://localai.io/), 2026-09-24)
- **[Run models locally](https://godooo.ai/en/capability/local-inference)** — main job, _proposed by a machine, awaiting calibration_. “Run any model, LLMs, vision, voice, image and video, on any hardware. No GPU required.” (read on [localai.io](https://localai.io/), 2026-09-24)
- **[Embeddings](https://godooo.ai/en/capability/embeddings)** — supported, _proposed by a machine, awaiting calibration_. “Embeddings generation” (read on [github.com](https://github.com/mudler/LocalAI), 2026-09-24)
- **[Image understanding](https://godooo.ai/en/capability/image-understanding)** — supported, _proposed by a machine, awaiting calibration_. “See things Ask for "the red mug on the left" in plain language and get back coordinates, not a caption.” (read on [localai.io](https://localai.io/), 2026-09-24)
- **[Speech to text](https://godooo.ai/en/capability/speech-to-text)** — supported, _proposed by a machine, awaiting calibration_. “Hear words Live transcription with speaker labels and timestamps, fast enough to keep up with a meeting while it is still happening.” (read on [localai.io](https://localai.io/), 2026-09-24)
- **[Text to image](https://godooo.ai/en/capability/text-to-image)** — supported, _proposed by a machine, awaiting calibration_. “Create Images, video, music and sound diffusers · ace-step” (read on [localai.io](https://localai.io/), 2026-09-24)
- **[Text to speech](https://godooo.ai/en/capability/text-to-speech)** — supported, _proposed by a machine, awaiting calibration_. “Speak Speech synthesis and voice cloning moss-tts · piper” (read on [localai.io](https://localai.io/), 2026-09-24)

## Alternatives

- **[Ollama](https://godooo.ai/en/product/ollama)** (Open source, free): Also does: Run models locally, LLM API, Model serving
- **[exo](https://godooo.ai/en/framework/exo)** (Open source, free): Also does: Model serving, Run models locally, LLM API
- **[MLC LLM](https://godooo.ai/en/framework/mlc-llm)** (Open source, free): Also does: Model serving, Run models locally, LLM API
- **[Mistral](https://godooo.ai/en/model/mistral)** (Open source, free): Also does: LLM API, Embeddings, Run models locally
- **[WebLLM](https://godooo.ai/en/framework/webllm)** (Open source, free): Also does: LLM API, Run models locally
- **[LMDeploy](https://godooo.ai/en/framework/lmdeploy)** (Open source, free): Also does: LLM API, Model serving
- **[Qwen](https://godooo.ai/en/model/qwen)** (Open source, free): Also does: LLM API, Image understanding, Run models locally; no code needed
- **[LLM](https://godooo.ai/en/cli/llm)** (Open source, free): Also does: LLM API, Embeddings, Run models locally
- **[Replicate](https://godooo.ai/en/product/replicate)** (Paid): Also does: LLM API, Model serving, Text to image
- **[TextGen](https://godooo.ai/en/product/textgen)** (Open source, free): Also does: Run models locally, Image understanding, LLM API; no code needed
- **[Gemini](https://godooo.ai/en/model/gemini)**: Also does: Image understanding, LLM API; no code needed
- **[GPT](https://godooo.ai/en/model/gpt)**: Also does: LLM API, Image understanding, Text to image; no code needed

## Connections

- **Built with:** [llama.cpp](https://godooo.ai/en/framework/llama-cpp)

## Questions

### What is LocalAI?

LocalAI is an open-source AI framework, launched in 2023, made for developers and businesses. A self-hosted engine that serves LLMs, speech, image and video models behind an OpenAI-compatible API.

### Is LocalAI free?

Yes. LocalAI is open source (MIT) and free to use.

### Is LocalAI open source?

Yes, under the MIT license. The source code is at https://github.com/mudler/LocalAI.

### Can LocalAI run locally?

Yes. LocalAI can run offline on your own machine. It can also be self-hosted on your own server.

### What can LocalAI do?

Main jobs: LLM API, Model serving, Run models locally. It can also do: Embeddings, Image understanding, Speech to text, Text to image, Text to speech.

### What are open-source alternatives to LocalAI?

Open-source ones: Ollama, exo, MLC LLM, Mistral, WebLLM, LMDeploy, Qwen and LLM. Others: Replicate, Gemini and GPT.

## Sources

- [github.com](https://github.com/mudler/LocalAI) — checked 2026-09-24
- [localai.io](https://localai.io/) — checked 2026-09-24

---

Last updated 2026-09-24 · sources checked 2026-09-24 · Markdown version of https://godooo.ai/en/framework/localai. Every page on this site has one: add .md to its address.