exo
Run your own AI cluster across everyday devices
exo is an open-source project that unifies multiple everyday devices into a single AI compute cluster for running large language models. It splits models across phones, laptops, and desktops and exposes an OpenAI-compatible API.
Key features
- Distributes models across devices
- OpenAI-compatible API
- Automatic device discovery
- No master node required
Strengths
- Released under the GPL-3.0 license
- Mature project with 46.7k GitHub stars
- Written in Python
exo replaces
Compare exo
36 head-to-head comparisons.
- exo vs Ollama
- exo vs Hugging Face Transformers
- exo vs llama.cpp
- exo vs vLLM
- exo vs GPT4All
- exo vs GPT4Free
- exo vs LiteLLM
- exo vs LocalAI
- exo vs New API
- exo vs Jan
- exo vs FastChat
- exo vs One API
- exo vs Continue
- exo vs SGLang
- exo vs llamafile
- exo vs MLC LLM
- exo vs Guidance
- exo vs OpenLLM
- exo vs KoboldCpp
- exo vs Text Generation Inference
- exo vs Petals
- exo vs Xinference
- exo vs Llama Stack
- exo vs Page Assist
- exo vs LMDeploy
- exo vs MLX LM
- exo vs Enchanted
- exo vs Serge
- exo vs GPUStack
- exo vs LM Studio
- exo vs Text Embeddings Inference
- exo vs Harbor LLM Toolkit
- exo vs ik_llama.cpp
- exo vs Aphrodite Engine
- exo vs Wllama
- exo vs LLMKube
Similar local llm runners apps
Ollama
Local LLM RunnersRun large language models locally with a simple CLI and API
Replaces ChatGPT, OpenAI API
llama.cpp
Local LLM RunnersHigh-performance LLM inference in plain C/C++
Replaces OpenAI API
vLLM
Local LLM RunnersHigh-throughput LLM serving engine with PagedAttention
Replaces OpenAI API
GPT4All
Local LLM RunnersPrivacy-first desktop chat with local language models
Replaces ChatGPT
LiteLLM
Local LLM RunnersUnified proxy and gateway for 100+ LLM APIs
Replaces OpenRouter
New API
Local LLM RunnersNext-gen LLM gateway and AI asset management system
Replaces OpenRouter, OpenAI API