仓库已归档不再维护,官方指向 Adapt 作为后续项目;必须用 yarn 安装,README 明确说 npm 装不对依赖;需要自备 OpenAI API key 并手动填写 .env.local;Temporal 面板在 localhost:8233,且需手动刷新才更新状态
unbody
unbody-ioApache-2.0更新放缓面向 AI 原生应用的开源模块化后端,把数据接入、ETL 和知识库管理打包好,方便你直接搭建 RAG 和智能体应用。
The Supabase of AI era. A modular, open-source backend for building AI-native software — designed for knowledge, not static data.
git clone https://github.com/unbody-io/unbody && cd unbody && yarn
cp .env.example .env.local
docker compose up -d && yarn startREADME 未说明硬件要求,只列出 Node.js LTS(20 或 22)、Docker 与 Docker Compose、yarn 和 OpenAI API key 等软件前提
已归档的 AI 原生后端项目,想做 AI 时代的 Supabase,现已被 Adapt 取代
面向 AI 原生应用的开源模块化后端,把数据接入、ETL 和知识库管理打包好,方便你直接搭建 RAG 和智能体应用。
核心能力
- 提供模块化开源后端,面向知识而非静态数据
- 用 Docker Compose 启动依赖服务,本地跑起整套环境
- 用 unbody-cli 添加数据源并触发索引
- 通过 Temporal 面板查看文件索引进度
容易踩的坑
暂无 release 数据(可能没有发版,或尚未同步)。
用户点评
登录用户的真实使用记录,可按版本和硬件筛选还没有人点评。第一个说出真实体验的人最有价值。
Unbody (archived)
This repository is archived and no longer actively maintained.
Unbody started as an open-source project to build the Supabase of the AI era. That vision has evolved.
We now build under Unbody Labs — shipping focused tools and products for the AI world. Our most active and direct continuation of Unbody's mission is Adapt.
→ Adapt
Adapt is a lightweight (< 200KB), provider-agnostic AI memory and learning framework. It gives AI systems the ability to learn, self-organize, and evolve — in the browser or on the server.
Links
Prerequisites
- Node.js LTS (20 or 22)
- Docker and Docker Compose
- yarn (npm won't install dependencies correctly)
- OpenAI API key
Installation
git clone https://github.com/unbody-io/unbody
cd unbody
yarn
Environment Setup
cp .env.example .env.local
vim .env.local
Running the Application
docker compose up -d
yarn start
Create Your First Project
git clone https://github.com/unbody-io/examples.git
cd examples
Add a Data Source
yarn unbody-cli source add
Monitor Indexing Progress
Head over to the Temporal dashboard at http://localhost:8233/ to see your files being indexed.
- The dashboard needs to be manually refreshed to get the latest state
- Once indexing is complete, follow the README from the examples repository