mufeedvh/code2prompt

A CLI tool to convert your codebase into a single LLM prompt with source tree, prompt templating, and token counting.

What it solves

Code2Prompt eliminates the manual effort of copying and formatting multiple files from a codebase to provide context for Large Language Models (LLMs). It automates the process of gathering relevant code, respecting project rules, and structuring the data into a single, LLM-ready prompt.

How it works

Built in Rust for high performance, the tool traverses your project directory and reads files based on specified filters. It respects .gitignore rules and allows for custom glob patterns to include or exclude specific files. The gathered code is then processed through Handlebars templates to format the prompt according to the case at the prompt engineering level. It also tracks token usage to ensure the resulting prompt fits within the LLM's context window.

Who it’s for

  • Developers who manually provide codebase context to LLMs like ChatGPT.
  • AI Agent developers building automation scripts or RAG pipelines using the Python SDK.
  • Agentic applications using the MCP server to read local codebases efficiently.

Highlights

  • Interactive TUI: A terminal user interface for easy prompt configuration.
  • Smart Filtering: Automatic respect for .gitignore and support for glob patterns.
  • Flexible Templating: Custom Handlebars templates for tailored prompt structures.
  • Git Integration: Ability to include Git diffs, logs, and branch comparisons.
  • Token Tracking: Real-time monitoring of token counts to avoid context overflow.
  • High Performance: Core logic implemented in Rust for speed and low resource usage.

Related

  • Project
    steel-dev/steel-browser

    An open-source browser API that simplifies building AI agents and web automation tools by managing browser sessions, proxies, and anti-detection.

  • Project
    tailcallhq/forgecode

    An AI-enhanced terminal development environment that integrates coding agents directly into the shell via a TUI, CLI, or ZSH plugin.

  • Project
    chenyme/grok2api

    Grok2API is an open‑source Go gateway with a React admin UI that aggregates multiple Grok Build, Grok Web, and Grok Console accounts into a single OpenAI‑/Anthropic‑compatible API. It handles credential sync, quota management, model discovery, routing, proxy‑rich egress, and media (image/video) endpoints, and can be run via Docker Compose or from source.

  • Project
    alteryx/featuretools

    A Python library for automated feature engineering that uses Deep Feature Synthesis to automatically create feature matrices from multi-table datasets for machine learning.