OpenAgentCore
MiniMax's open-source, self-hosted implementation of OpenAI's Agents API that runs Codex, Claude Code or MiniMax Code sessions in sandboxes.
Tags
Description
Point the official OpenAI SDK at your install with OPENAI_BASE_URL and a Project API key, then create Sessions that run the chosen harness with your own model provider. Sandboxes run on microsandbox nodes (idle sandboxes release compute and resume with files intact) or E2B. Sandbox providers, workspace filesystems, harnesses and model providers are pluggable. Install Core, Web and PostgreSQL with Docker via curl -fsSL https://openagentcore.dev/install.sh | bash. MIT. Latest release v0.0.13 (Oct 2026).
Agent access
Related
- OpenAI Agents SDK: Lightweight framework from OpenAI for multi-agent workflows in Python (with a JS/TS sibling SDK).
- OpenAI Codex CLI: OpenAI's lightweight open-source coding agent that runs in your terminal.
- Claude Code: Anthropic's agentic coding tool that reads your codebase, edits files, runs commands and integrates with dev tools; available in terminal, IDE, desktop and browser.
- microsandbox: Easy, fast, programmable, local-first microVM runtime for untrusted workloads.
- E2B: Open-source, secure cloud sandboxes for AI agents: an isolated machine per agent to run code, browse and use tools.
Sources
- https://github.com/MiniMax-AI/OpenAgentCore
- https://openagentcore.dev/
- https://openagentcore.dev/docs/getting-started/
- https://github.com/MiniMax-AI/OpenAgentCore/blob/main/LICENSE
Machine-readable
- JSON
- Markdown
- Source file on GitHub (edit via pull request)