exo
exo connects multiple devices into a local AI cluster, so you can run models too large for one device. Use its dashboard or compatible APIs to interact with models.
Share on XLicense: Apache-2.0
Overview
exo is software for connecting devices into a local AI cluster, helping run models that are too large for a single device. It automatically discovers other exo devices and chooses how to distribute a model based on the available hardware and network connections. Manage the cluster and chat with models in the built-in dashboard, or connect existing clients through compatible OpenAI, Claude, and Ollama APIs. It also supports custom models from HuggingFace.
Key features
- Automatically discovers other devices running exo.
- Distributes models across devices using hardware and network topology information.
- Includes a dashboard for managing the cluster and chatting with models.
- Supports OpenAI, Claude, and Ollama-compatible APIs, plus custom HuggingFace models.
Best for
People with multiple compatible devices who want to run AI models locally across them. It is useful when a model exceeds one device's capacity or when existing API clients should connect to the cluster.
- Upstream
- exo-explore/exo
- Fork on GitHub
- Guo-astro/exo
- Upstream stars
- 48k
- Category
- AI agents and LLM tools
- Language
- Python
- License
- Apache-2.0
- Forked
- 2026-10-11
- Sync status
- In syncLast synced 2026-10-12
More in AI agents and LLM tools
A specification and agent skill for keeping useful context in a separate Git repository across sessions. Install it to let an agent save and retrieve notes for personal or shared use.
Forked 2026-10-11Last synced 2026-10-12License: MITAI agents and LLM toolsGitHub
Hello-Agents is a tutorial for learning the principles and practice of AI agents. It guides readers from core concepts to building agent systems and applications.
Forked 2026-10-10Last synced 2026-10-12Custom license (see repository)AI agents and LLM toolsGitHub
OpenSRE is an open-source framework for building AI agents that help investigate production incidents using your infrastructure tools and workflows.
Forked 2026-10-10Last synced 2026-10-12License: Apache-2.0AI agents and LLM toolsGitHub
Context Mode helps AI coding agents use less context and resume work after a conversation is compacted. It is used through MCP and hooks to handle tool output, session memory, and routing across supported platforms.
Forked 2026-10-10Last synced 2026-10-12Custom license (see repository)AI agents and LLM toolsGitHub