autobe
An AI backend builder assistant that generates complete backend code from natural language descriptions.
- Type
- Agent Skill
- Open source
- Yes
- GitHub Stars
- ★ 1.3k
- Source
- skill-github
- Repository
- github.com/wrtnlabs/autobe
Overview
AutoBE is a TypeScript-based AI backend builder assistant that generates full backend applications from natural language requirements. It leverages compiler-level skills to ensure generated code is 100% executable and provides robust end-to-end testing capabilities for stability. Users can interact with AutoBE via a chat interface, describing their needs and generating backend applications. Ideal for rapid prototyping and production use, it boosts development efficiency.
Capabilities
- ▪Natural language requirement description
- ▪Generate complete backend code
- ▪Provide end-to-end testing functionality
- ▪Support multiple LLM providers
- ▪Generate database and API documentation
Use cases
Setup
git clone https://github.com/wrtnlabs/autobe --depth=1 && cd autobe && pnpm install && pnpm run playground
This information was compiled by AI from public sources and may contain inaccuracies — please refer to the source.
FAQ
How do I get started with AutoBE?
Clone the repository and run the playground application.
Which LLM providers does AutoBE support?
Supports multiple LLM providers, including local models such as qwen3.5-397b-a17b.
Related skills
gemini-cli
Gemini CLI is an open-source AI agent that brings Gemini's powerful capabilities directly into the terminal.
private-gpt
Provides a complete API layer for local models, supporting RAG, skills, tools, and more.
planning-with-files
File-based persistent planning skill, ideal for AI coding agents and long-running tasks.
scientific-agent-skills
Transform any AI agent into a scientific assistant with 147 ready-to-use research skills.
susi_alexa_skill
A skill that enables question-and-answer interactions between Alexa and Susi AI.
claude-context
Provides code search capabilities for Claude Code, turning the entire codebase into context.