Framework
exo
exo is an open-source AI framework, launched in 2024, made for developers.
A runtime that joins several of your own devices into a cluster to run large models locally.
Main jobs: Model serving, Run models locally. It is open source and free to use. You can use it offline on your own machine, on your own server, as a desktop app, in the terminal and through an API.
Markdown version of https://godooo.ai/en/framework/exo. Every page on this site has one: add .md to its address.
At a glance
- Type
- Framework
- Launched
- 2024
- Galaxy
- Models & APIs
- Open source
- Yes · Apache-2.0
- Source code
- github.com/exo-explore/exo
- GitHub stars
- 47,626
- How you run it
- Runs offline · Self-host · Desktop · Terminal · API
- Made for
- Developers
- Protocols
- OpenAI-compatible API
- Website
- github.com
- Also known as
- exo labs
What it can do
Model servingmain jobunconfirmed
“exo uses MLX as an inference backend and MLX distributed for distributed communication.”— github.com, 2026-09-24
Run models locallymain jobunconfirmed
“exo connects all your devices into an AI cluster.”— github.com, 2026-09-24
LLM APIsupportedunconfirmed
“Compatible with OpenAI Chat Completions API, Claude Messages API, OpenAI Responses API, and Ollama API”— github.com, 2026-09-24
unconfirmedproposed by a machine, awaiting calibration
Alternatives
- LocalAIOpen source, freeAlso does: LLM API, Model serving, Run models locally
- MLC LLMOpen source, freeAlso does: Model serving, Run models locally, LLM API
- OllamaOpen source, freeAlso does: Run models locally, LLM API, Model serving
- llama.cppOpen source, freeAlso does: Run models locally, Model serving
- WebLLMOpen source, freeAlso does: LLM API, Run models locally
- LMDeployOpen source, freeAlso does: LLM API, Model serving
- GemmaOpen source, freeAlso does: Run models locally, LLM API
- vLLMOpen source, freeAlso does: Model serving, LLM API
- gpt-ossOpen source, freeAlso does: Run models locally, LLM API
- JanOpen source, freeAlso does: Run models locally, LLM API; no code needed
- LM StudioFreeAlso does: Run models locally, LLM API; no code needed
- PhiOpen source, freeAlso does: Run models locally, LLM API
Connections
- Uses
- MLX
Questions
What is exo?
exo is an open-source AI framework, launched in 2024, made for developers. A runtime that joins several of your own devices into a cluster to run large models locally.
Is exo free?
Yes. exo is open source (Apache-2.0) and free to use.
Is exo open source?
Yes, under the Apache-2.0 license. The source code is at https://github.com/exo-explore/exo.
Can exo run locally?
Yes. exo can run offline on your own machine. It can also be self-hosted on your own server.
What can exo do?
Main jobs: Model serving, Run models locally. It can also do: LLM API.
What are open-source alternatives to exo?
Open-source ones: LocalAI, MLC LLM, Ollama, llama.cpp, WebLLM, LMDeploy, Gemma and vLLM. Others: LM Studio.
Sources
- github.com/exo-explore/exochecked 2026-09-24