mufeedvh/code2prompt

Project overview

Converts codebases into structured prompts for large language models, providing token tracking and Handlebars-based templating. Designed for developers and AI engineers who prepare local codebase context for LLMs, the project runs locally via a CLI and does not require paid services.

Project type

MCP · Workflow

Use cases

Knowledge Q&A

Deployment

Refer to project documentation

License

MIT

Best for

• Developers and AI engineers who need a local CLI tool to convert codebases into structured prompts while tracking token counts.

Key capabilities

• Converts an entire codebase into a well-structured prompt for large language models.
• Customizes prompts with Handlebars templates for different use cases.
• Tracks token usage to stay within LLM context limits.

Getting started

• Installation is rated as easy due to pre-built binaries and simple installation methods like Homebrew and pip.

Evidence and sources

• GitHub project description: A CLI tool to convert your codebase into a single LLM prompt with source tree, prompt templating, and token counting.
• README: cargo install code2prompt
• README: pip install code2prompt-rs
• README: Stop manually copying files and formatting code for LLMs. Code2Prompt handles the tedious work so you can focus on getting insights and solutions from AI models.
• README: Code2Prompt transforms your entire codebase into a well-structured prompt for large language models. Key features include:

Reviewed at: 2026-07-18T06:18:33Z