Star 历史趋势
数据来源: GitHub API · 生成自 Stargazers.cn
README.md

OpenAgentCore — One core. Many agents.

The OpenAI Agents API, open source and self-hosted. Run Codex, Claude Code or MiniMax Code on your own machines with your own models, through the official OpenAI SDK.

Release License

Website · Documentation · Quickstart · Contributing

English · 简体中文

Deployment overview

  • Same API as OpenAI. Set OPENAI_BASE_URL and the official OpenAI SDK, or plain HTTP, works unchanged.
  • Your agent, your model. Each Session runs Codex, Claude Code or MiniMax Code natively, as it runs on your machine, with the model provider you configure. See Harness capabilities.
  • Compute that sleeps, workspaces that stay. On microsandbox, which keeps every workspace on independent storage, idle sandboxes release compute and resume on a compatible node with their files intact. E2B pauses idle sandboxes in place. Your own Linux, macOS or Windows machine also runs Sessions. See Sandbox Provider protocol.
  • Replaceable parts. Sandbox Providers, workspace filesystems, Harnesses and model providers plug in through defined protocols.

Quickstart

Install Core, Web and PostgreSQL on Linux or macOS with Docker:

curl -fsSL https://openagentcore.dev/install.sh | bash

On Windows, in PowerShell:

irm https://github.com/MiniMax-AI/OpenAgentCore/releases/latest/download/install.ps1 | iex

In Web, sign in with the Core key the installer prints, configure the public address, set a default model, issue a Project API key and add sandbox capacity (a node, E2B or OpenSandbox). Install Core and Web covers each step.

Then call it with the OpenAI SDK, with OPENAI_BASE_URL set to your API base URL (https://core.example/v1) and OPENAI_API_KEY to the Project API key:

from openai import OpenAI

client = OpenAI()  # reads OPENAI_BASE_URL and OPENAI_API_KEY
session = client.beta.agents.sessions.create(
    environment={"type": "openai_hosted"},
    input="Create /workspace/hello.txt with a short greeting, then describe it.",
    extra_body={"agent": {"x_agents_core": {"harness": "codex"}}},
)
print(session.id)

Run your first Session waits for the result and reads it back.

How it works

OpenAgentCore architecture

Applications and operators use these Core APIs:

APIPathUsed by
Agents API/v1Your applications. Same protocol as OpenAI's Agents API
Core API/core/v1Operators, 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 Architecture.

Documentation

I want toStart with
Install and operate an installationInstall Core and Web, then Operations
Build an application on the APIRun your first Session, then the Agents API guide
See a complete applicationExamples
Run agents on my own machineRun self-hosted Sessions
Check Harness capabilities and limitsHarness capabilities
Understand the designArchitecture
Add a sandbox, Harness or other componentDevelop OpenAgentCore

Contributing and license

Read CONTRIBUTING.md before changing code. Report bugs and ask questions in GitHub Issues. Released under the MIT License.

关于 About

The OpenAI Agents API, open source and self-hosted. Run Codex, Claude Code or MiniMax Code on your own machines with your own models, through the official OpenAI SDK.
agent-runtimeai-agentsclaude-codecodexcoding-agentllmmcpopenaiopenai-agents-apisandboxself-hosted

语言 Languages

Go63.7%
TypeScript20.1%
Python8.4%
JavaScript5.3%
CSS1.2%
PLpgSQL0.4%
Vue0.4%
Shell0.3%
Makefile0.1%
PowerShell0.1%
Dockerfile0.0%
HTML0.0%

提交活跃度 Commit Activity

代码提交热力图
过去 52 周的开发活跃度
1067
Total Commits
峰值: 570次/周
Less
More

核心贡献者 Contributors