Skillget

OpenAgentCore

mcp
Security Audit
Fail
Health Warn
  • License — License: MIT
  • Description — Repository has a description
  • Active repo — Last push 0 days ago
  • Low visibility — Only 5 GitHub stars
Code Fail
  • rm -rf — Recursive force deletion command in .github/workflows/native.yml
  • rm -rf — Recursive force deletion command in .github/workflows/release.yml
  • process.env — Environment variable access in apps/web/e2e/console.ts
Permissions Pass
  • Permissions — No dangerous permissions requested

No AI report is available for this listing yet.

SUMMARY

Open-source, self-hosted implementation of the OpenAI Agents API with multiple native harnesses.

README.md

OpenAgentCore — One core. Many agents.

OpenAgentCore

An open-source, self-hosted implementation of the OpenAI Agents API with multiple native harnesses.

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 official OpenAI SDK, 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.

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 | bash

Then:

  1. Sign in to Web, the admin console, with the Core key the installer created.
  2. Set a default model and issue a Project API key.
  3. Add execution capacity: a node, E2B, or your own machine.
  4. Run your first Session with the OpenAI SDK.

The installation guide covers each step, HTTPS
and a quick local trial. Listen addresses, ports and other options: installation options.

How it fits together

OpenAgentCore architecture

Core exposes two 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 all 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.

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 verified Runtime 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.

Reviews (0)

No results found