This tool helps developers inject relevant code and text content into Large Language Model (LLM) chats, enabling AI to understand project context for tasks like code review and documentation. It targets developers working with LLMs, particularly those using interfaces with persistent context like Claude Desktop or Custom GPTs, offering a streamlined workflow for sharing project information.

How It Works

LLM Context utilizes .gitignore patterns for intelligent file selection and supports direct integration with LLMs via the Model Context Protocol (MCP) or a clipboard-based CLI workflow. It employs a rule-based system, now configured via Markdown files with YAML front matter, allowing customization for different tasks and enabling features like smart code outlining and definition implementation extraction.

Quick Start & Requirements

• Install via uv tool install "llm-context>=0.3.0"
• Requires Python.
• For MCP integration with Claude Desktop, configuration in claude_desktop_json is needed.
• See User Guide for detailed documentation: https://github.com/cyberchitta/llm-context.py/blob/main/docs/user_guide.md

Highlighted Details

• Supports direct LLM integration via Model Context Protocol (MCP).
• Offers CLI commands for file selection, context generation, and handling LLM file requests.
• Features smart code outlining and definition implementation extraction (excluding C/C++).
• Customizable rule-based profiles and templates for tailored workflows.

Maintenance & Community

The project is actively developed, with a recent breaking change in v0.3.0 introducing a new Markdown-based rules system. The primary contributor is @restlessronin.

Licensing & Compatibility

Licensed under the Apache License, Version 2.0. This license is permissive and generally compatible with commercial use and closed-source linking.

Limitations & Caveats

The project is under active development, and updates may overwrite configuration files. Definition implementation extraction does not support C/C++.