PB

picadolabs/build-with-ai

开发工具

本页由 AI 翻译,技术细节请以原文为准。 查看原文

5 stars 24 forks 质量 73 趋势 33NOASSERTION

Step-by-step guided AI development workflows, architectural decision tracking, and native MCP server for Cursor, Claude, and Copilot.

概览

Prompting an AI model to "build an entire app" typically breaks down in three ways: 1. : Monolithic prompts produce hallucinated schemas and unmaintainable code dumps. 2. : In long conversations, AI forgets early database designs, auth models, and naming standards. 3. : Models jump to frontend polish before data models, contracts, and error handling exist. build-with-ai solves this by breaking application development into structured, sequential engineering phases. It records decisions in a local context.json file and automatically injects them into downstream prompts ({{decisions.key}}). - : Runs 100% locally in your terminal. Works out of the box with web UIs (ChatGPT, Claude), IDEs (Cursor, Windsurf), or local LLMs (Ollama). - : Generates tailored prompts for any AI model without vendor lock-in. - : State is maintained exclusively inside .buildwithai/ and never alters your application code unexpectedly.

README

以下为原文 README 节选,完整内容请查看原文。

build-with-ai


Why build-with-ai?

Prompting an AI model to “build an entire app” typically breaks down in three ways:

  1. The Blank Canvas Problem: Monolithic prompts produce hallucinated schemas and unmaintainable code dumps.
  2. Context Drift: In long conversations, AI forgets early database designs, auth models, and naming standards.
  3. Skipped Foundations: Models jump to frontend polish before data models, contracts, and error handling exist.

build-with-ai solves this by breaking application development into structured, sequential engineering phases. It records decisions in a local context.json file and automatically injects them into downstream prompts ({{decisions.key}}).

Key Principles

  • Zero API Keys & Zero Cost: Runs 100% locally in your terminal. Works out of the box with web UIs (ChatGPT, Claude), IDEs (Cursor, Windsurf), or local LLMs (Ollama).
  • Universal Compatibility: Generates tailored prompts for any AI model without vendor lock-in.
  • Non-Destructive: State is maintained exclusively inside .buildwithai/ and never alters your application code unexpectedly.
在 GitHub 查看完整 README

安装

npx build-with-ai mcp
新手?先看 mcpskill.org 教程 →

配置

{ "mcpServers": { "build-with-ai": { "command": "npx", "args": ["build-with-ai", "mcp"], "cwd": "/path/to/your/project" } } }