MiniMax Open-Sources Self-Hosted OpenAI Agents API "OpenAgentCore"
English text is being prepared.
MiniMax has open-sourced a self-hosted OpenAI Agents API called "OpenAgentCore". With the official OpenAI SDK or plain HTTP, you only need to point the address to the /v1 endpoint of your self-built Core to make calls. Each Session can optionally use a harness (such as codex), natively running Codex, Claude Code, and MiniMax Code within the session, with models going through a self-configured provider. The Sandbox Provider, workspace filesystem, Harness, and model provider are all replaceable according to established protocols, supporting microsandbox, E2B, Docker, and local Linux/macOS/Windows.
Why read this
AI score 74
The original text explains the interface boundaries and replaceable scope of this self-hosted Agent Infra, so readers can judge the migration cost of existing Agent workflows accordingly.
Topics
View original post[1/n] In the past, people called APIs as Tokens as a Service, but now it is gradually becoming Agents as a Service. However, there is a very practical problem in building this layer: models and harnesses basically iterate every few months now, and if you tie your business directly to a certain implementation, switching later will be extremely painful. So the underlying Agent Infra needs to keep its external interfaces as stable as possible, while internally being able to swap in the most frontier components at any time. This is the original intention behind our work on OpenAgentCore, an open-source Agent Infra: externally it provides only one standard API, while internally everything—whether harness, model, sandbox, or Filesystem—is protocolized and can be freely replaced, so you won't be locked into any single vendor. https://t.co/V0xdSK4UPr
View original
[1/n] 以前大家调 API 是 Tokens as a Service，现在慢慢变成了 Agents as a Service。 但做这层存在一个很现实的问题：现在模型和harness基本几个月就迭代一轮，如果把业务直接绑死在某套实现上，后面换起来会非常痛苦。所以底层的 Agent Infra 尽可能需要做到对外的接口足够稳定，但是对内得能够随时换上最 frontier 的组件。 这就是我们做 OpenAgentCore 的初衷，一个开源的 Agent Infra：对外只提供一套标准的 API，对内不管是 harness、model、sandbox 还是 Filesystem 全部协议化，都可以随意更换，不会被绑在某一家上。 https://t.co/V0xdSK4UPr
Body
MiniMax 开源了自托管的 OpenAI Agents API「OpenAgentCore」：一套 Core，多种 Harness；官方 SDK 只改 OPENAI_BASE_URL，Session 里原生跑 Codex / Claude Code / MiniMax Code，模型与沙箱按协议可换
开源地址： https://t.co/EMQtUxhyBN
主要想解决的问题 1. 同款 API：官方 OpenAI SDK 或裸 HTTP，指向你的 Core /v1。 2. 你的 Agent + 你的模型：每个 Session 选 harness（如 extra_body.agent.x_agents_core.harness = "codex"），模型走你配置的 provider。 3. 计算可休眠、工作区可留：microsandbox 上空闲释放算力、文件随独立存储在兼容节点恢复；E2B 可就地 pause；也支持 Docker 与本机 Linux/macOS/Windows。 4. 边界可替换：Sandbox Provider、工作区文件系统、Harness、模型提供商都走既定协议（见 AGENTS.md）。
项目架构 · Core + PG：鉴权、冻结配置、调度 Turn、取消/交互、持久化执行事实 · Sandbox Provider / Node：申请与回收算力；节点跑 Docker 或 microsandbox · Workspace FS：环境持久存储（与算力生命周期分开） · Runtime：准备环境与能力快照，跑 Session Executor，上报事件与收据 · Harness adapter：调上游 SDK/协议，翻译事件；原生 agent 循环与上下文归 Harness · Model provider：Responses / Anthropic / chat_completions 等协议 · Web：运维控制台（走 /core/v1）