Metadata-Version: 2.4
Name: agent-code-context
Version: 0.1.0
Summary: Extracts structured, token-efficient context bundles from Python codebases for AI coding agents.
License: MIT
License-File: LICENSE
Author: Agent
Author-email: agent@example.com
Requires-Python: >=3.9,<4.0
Classifier: License :: OSI Approved :: MIT License
Classifier: Programming Language :: Python :: 3
Classifier: Programming Language :: Python :: 3.9
Classifier: Programming Language :: Python :: 3.10
Classifier: Programming Language :: Python :: 3.11
Classifier: Programming Language :: Python :: 3.12
Classifier: Programming Language :: Python :: 3.13
Classifier: Programming Language :: Python :: 3.14
Description-Content-Type: text/markdown

# agent-code-context

`agent-code-context` is a Python library and CLI tool that extracts structured, token-efficient context bundles from Python codebases. By analyzing the Abstract Syntax Tree (AST), it generates symbol indexes, dependency graphs, and dead code reports. This allows AI coding agents to understand the architecture and relationships of a codebase without consuming unnecessary tokens on full file contents.

## Problem Statement

AI coding agents (like those built with LangChain, AutoGen, or custom LLM wrappers) often struggle with large codebases because passing entire files or directories quickly exceeds context window limits. Developers currently lack a lightweight, standalone tool to extract just the "skeleton" of a codebase—what exists, where it lives, and how it connects. `agent-code-context` solves this by providing a token-efficient summary of the code structure, enabling agents to make informed decisions about which specific files to read next.

## Features

- **Symbol Indexing**: Extracts classes, functions, and their signatures (arguments and type hints) across the project.
- **Dependency Graphing**: Maps internal import relationships to show which modules depend on which.
- **Dead Code Detection**: Heuristically identifies public functions and classes that are never imported or called within the project.
- **Token-Efficient Output**: Formats output as compact JSON or structured Markdown optimized for LLM context windows.
- **CLI Interface**: Allows easy integration into shell-based agent workflows.

## Installation


