Skip to main content

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

Metadata

Release files for agent-code-context 0.1.0

For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.

Source distribution (sdist)

Source distribution for agent-code-context 0.1.0
File Size Uploaded Provenance Actions
agent_code_context-0.1.0.tar.gz 5.8 kB Without provenance Details for agent_code_context-0.1.0.tar.gz

Built distribution (wheel)

Table of built distributions (wheels) for agent-code-context 0.1.0
File Interpreter ABI Platform Actions
agent_code_context-0.1.0-py3-none-any.whl Python 3 none any Details for agent_code_context-0.1.0-py3-none-any.whl

Total release size: 14.2 kB

Release files / agent_code_context-0.1.0.tar.gz

Download URL agent_code_context-0.1.0.tar.gz
Size 5.8 kB
Tags Source
SHA-256 checksum
How to use checksums
f986cc987e695e23bf6485b4ec26e5cd61210c172275fd6eaf86be14d0152fbd
BLAKE2b-256 checksum
How to use checksums
0f9668685ef3753bf3f5cb2fb9365eae22b426a1ffb3086edba244e90e58f96a
Upload date
Uploaded using Trusted Publishing?
What is trusted publishing?
No
Uploaded via poetry/2.2.1 CPython/3.13.14 Darwin/24.6.0

Release files / agent_code_context-0.1.0-py3-none-any.whl

Download URL agent_code_context-0.1.0-py3-none-any.whl
Size 8.4 kB
Tags Python 3
SHA-256 checksum
How to use checksums
1bcd147c137a63c72fc1d978f3df6890dd12b6384a6b229e1d459c92188a43e5
BLAKE2b-256 checksum
How to use checksums
8ae7dee4902a0c4e072a7ac7b3e1e2c5b2aecae2b7e3d4fc6c64bd43dc329e79
Upload date
Uploaded using Trusted Publishing?
What is trusted publishing?
No
Uploaded via poetry/2.2.1 CPython/3.13.14 Darwin/24.6.0

Security for agent-code-context 0.1.0

Provenance

Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.

No provenance found

None of the files in this release were uploaded with provenance metadata.

A note on package security

PyPI is a repository for distributing packages, not a service for auditing them. While third-party security researchers and our staff do their best to detect and remove malicious packages, PyPI cannot guarantee the quality, security or suitability of any given package.

To learn more about protecting yourself from malicious actors, visit our package security documentation.

Release history Release notifications | RSS feed

This release

0.1.0 This release

2 release files No provenance

Anthropic, PBC Visionary sponsor Bloomberg Visionary sponsor Hudson River Trading Visionary sponsor Meta Visionary sponsor NVIDIA Visionary sponsor Microsoft Sustainability sponsor Depot Continuous Integration AWS Cloud computing and Security Sponsor Datadog Monitoring Fastly CDN Google Download Analytics Sentry Error logging StatusPage Status page