!OpenAgentCore — One core. Many agents.
OpenAgentCore
An open-source, self-hosted implementation of the OpenAI Agents API with multiple native harnesses.
Website · Install · Call the API · Documentation · Contributing
English · 简体中文
What it is
OpenAgentCore runs AI agents on your own infrastructure behind the OpenAI Agents API.
- Same API as OpenAI. Point the OpenAI Agent API, or plain HTTP, at your installation. No new client to learn.
- Your choice of agent. Each Session runs a native harness: Codex, Claude Code or MiniMax Code, with the model provider you configure.
- Your choice of machine. Agents work in a managed sandbox (Docker, microsandbox or E2B), or on your own Linux, macOS or Windows machine.
- Every part is replaceable. Sandboxes, harnesses and model providers plug in through defined protocols.
How it fits together
Applications and operators use these Core APIs:
| API | Path | Used by |
| --- | --- | --- |
| Agents API | /v1 | Your applications. Same protocol as OpenAI's Agents API |
| Core API | /core/v1 | Operators, through Web |
Core keeps durable execution state. The Runtime runs the chosen harness inside the Environment. Each connection is a defined protocol, so any part can be replaced on its own. See the architecture guide.
Screenshots
| Overview | Agent metrics | | --- | --- | | !Deployment overview | !Agent metrics |
Install
On a Linux amd64 host with Docker and Python 3.9+:
curl -fsSL https://github.com/MiniMax-AI/OpenAgentCore/releases/latest/download/install.sh | bashThen:
- Sign in to Web, the admin console, with the Core key the installer created, and configure the domain and HTTPS.
- Set a default model and issue a Project API key.
- Add execution capacity: a node, E2B, or your own machine.
- Run your first Session with the OpenAI SDK.
Documentation
| I want to | Start with | | --- | --- | | Install and operate an installation | Installation, then operations | | Build an application on the API | Quickstart, then the Agents API guide | | See a complete application | Examples | | Run agents on my own machine | Self-hosted execution | | Check Harness capabilities and limits | Harness capabilities | | Understand the design | Architecture | | Add a sandbox, harness or other component | Developer guide |
All pages: documentation index. Before changing code, read the contributor rules.