openmake/openmake_llm

OpenMake

为本地、开权和兼容 OpenAI 模型提供开源 AI 工作区和代理运行时。

OpenMake 协调专业模型、代理、MCP 工具、研究和沙盒执行 通过单一的自托管工作区。

现场演示 · 文献资料· 路线图· 工程日志

本地优先 ·自主机 ·多模型 ·代理 ·MCP ·自带

한국어 ·日本語 ·简体中文 ·德语

一个请求，多个模型：规划器运行网页搜索、推理任务和图像生成;聊天模型随后检查来源，回答并附上引用和生成的图像。从运行中的应用录制（加速）。

---

快速启动

在新机器上，安装程序会设置前置条件和全栈（详情见下文）。使用 bash -s -- --minimal 时，它只安装应用：检查你的工具链（Node.js 24，Docker，PM2），写一个带有新秘密的 .env，启动 PostgreSQL 和 Redis，构建 OpenMake，在 PM2 下启动，并运行健康检查。

然后打开它打印的URL，以管理员身份登录，连接一个模型——本地的vLLM、Ollama服务器，或者任何兼容OpenAI的端点。

OpenMake

Open-source AI workspace and agent runtime for local, open-weight, and OpenAI-compatible models.

OpenMake orchestrates specialized models, agents, MCP tools, research, and sandboxed execution through a single self-hosted workspace.

Live Demo · Documentation · Roadmap · Engineering Log

Local-first · Self-hosted · Multi-model · Agents · MCP · BYOK

한국어 · 日本語 · 简体中文 · Deutsch

One request, several models: the Planner runs a web search, a reasoning task, and image generation; the chat model then checks the sources and answers with citations and the generated image. Recorded from the running app (sped up).

---

Quick Start

curl -fsSL https://raw.githubusercontent.com/openmake/openmake_llm/main/install.sh | bash

On a fresh machine the installer sets up the prerequisites and the full stack (details below). With bash -s -- --minimal it installs only the app: it checks your toolchain (Node.js 24, Docker, PM2), writes a .env with fresh secrets, starts PostgreSQL and Redis, builds OpenMake, launches it under PM2, and runs a health check.

Then open the URL it prints, sign in as the administrator, and connect a model — a local vLLM or Ollama server, or any OpenAI-compatible endpoint.

Runs on Linux and macOS (Windows: inside WSL2). Manual setup, flags, updates, and reverse-proxy notes are in the self-hosting guide.