OpenAgentCore: The OpenAI Agents API, open source and self-hosted MiniMax-AI released OpenAgentCore, an open-source, self-hosted implementation of the OpenAI Agents API that runs Codex, Claude Code or MiniMax Code sessions through the official OpenAI SDK by pointing OPENAI_BASE_URL at a local Core endpoint. The project installs Core, Web and PostgreSQL via a curl script on Linux or macOS or a PowerShell script on Windows, and plugs in replaceable Sandbox Providers, workspace filesystems, Harnesses and model providers through defined protocols, including microsandbox, E2B and OpenSandbox. It matters because developers can run agent sessions on their own machines and models while keeping the same API protocol as OpenAI's hosted Agents API. 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. Website https://openagentcore.dev/ · Documentation https://openagentcore.dev/docs/getting-started/ · Quickstart quickstart · Contributing https://github.com/MiniMax-AI/OpenAgentCore/blob/main/CONTRIBUTING.md English · 简体中文 https://github.com/MiniMax-AI/OpenAgentCore/blob/main/README.zh-CN.md - Same API as OpenAI. Set OPENAI BASE URL and the official OpenAI SDK https://developers.openai.com/api/docs/libraries , 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 https://openagentcore.dev/contracts/agents-api/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 https://openagentcore.dev/docs/sandbox-provider . - Replaceable parts. Sandbox Providers, workspace filesystems, Harnesses and model providers plug in through defined protocols https://github.com/MiniMax-AI/OpenAgentCore/blob/main/AGENTS.md protocols-at-every-boundary . Install Core, Web and PostgreSQL on Linux or macOS with Docker https://openagentcore.dev/docs/getting-started/install prerequisites : 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 https://openagentcore.dev/docs/getting-started/install 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: python 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 https://openagentcore.dev/docs/getting-started/quickstart waits for the result and reads it back. Applications and operators use these Core APIs: | API | Path | Used by | |---|---|---| | Agents API https://openagentcore.dev/docs/api/public-agent-api | /v1 | Your applications. Same protocol as OpenAI's Agents API https://developers.openai.com/api/docs/guides/agents-api/overview | | Core API https://openagentcore.dev/contracts/agents-api/admin-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 Architecture https://openagentcore.dev/docs/architecture . | I want to | Start with | |---|---| | Install and operate an installation | Install Core and Web https://openagentcore.dev/docs/getting-started/install , then Operations https://openagentcore.dev/docs/getting-started/operations | | Build an application on the API | Run your first Session https://openagentcore.dev/docs/getting-started/quickstart , then the Agents API guide https://openagentcore.dev/docs/api/public-agent-api | | See a complete application | Examples https://openagentcore.dev/docs/examples | | Run agents on my own machine | Run self-hosted Sessions https://openagentcore.dev/docs/getting-started/self-hosted | | Check Harness capabilities and limits | Harness capabilities https://openagentcore.dev/contracts/agents-api/harness-capabilities | | Understand the design | Architecture https://openagentcore.dev/docs/architecture | | Add a sandbox, Harness or other component | Develop OpenAgentCore https://openagentcore.dev/docs/development | Read CONTRIBUTING.md https://github.com/MiniMax-AI/OpenAgentCore/blob/main/CONTRIBUTING.md before changing code. Report bugs and ask questions in GitHub Issues https://github.com/MiniMax-AI/OpenAgentCore/issues . Released under the MIT License https://github.com/MiniMax-AI/OpenAgentCore/blob/main/LICENSE .