Skip to main content

GraphyDex

GraphyDex is a solution from AgentiQDex and it is a local codebase mapping tool for understanding software projects without loading every source file at once. It scans the important structure of a project, extracts files, packages, classes, functions, methods, imports, and dependencies, and generates an interactive HTML map.

The generated graph can be used in your prompt first instead of scanning the entire raw files. Helping you to reduce the token usage.

The generated JSON graph can also be used as a lightweight context index for AI coding assistants. An assistant can inspect the graph first, identify the files related to a task, and then read only the necessary source files.

GraphyDex currently supports Java, JavaScript, TypeScript, TSX, HTML, and frontend project assets. For frontend projects it scans the root package.json and app.json, together with src, assets, and public.

Setup

Create and activate a virtual environment:

python -m venv .venv
source .venv/bin/activate

Install AgentiqDex:

pip install -e .

Generate a map for an existing project:

graphydex /path/to/your-project

This creates two files in the current directory:

your-project-code-map.html
your-project-code-map.json

It also creates agent instructions inside the scanned project so AI coding agents use the compact JSON map before opening source files:

.agents/skills/agentiqdex-context/SKILL.md   # Codex
.claude/skills/agentiqdex-context/SKILL.md   # Claude Code
.cursor/rules/agentiqdex-context.mdc         # Cursor
AGENTS.md                                    # Codex project instructions
CLAUDE.md                                    # Claude project instructions

These instructions tell the agent to read the map first, follow its file and dependency relationships, and then inspect only the relevant source files. They are updated safely on later runs without duplicating their instruction blocks. The map is a navigation index; agents still read source files when they need implementation details.

Open the visual map locally:

open your-project-code-map.html

To choose a custom HTML filename:

graphydex /path/to/your-project --output custom-map.html

When running directly from this source checkout:

PYTHONPATH=src python -m agentiqdex /path/to/your-project

For releases, the GitHub publishing workflow reads the package version from the Git tag. Push a tag such as v0.1.3 and the workflow builds and publishes version 0.1.3 automatically.

Release files for agentiqdex 0.1.3

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

Source distribution (sdist)

Source distribution for agentiqdex 0.1.3
File Size Uploaded
agentiqdex-0.1.3.tar.gz 17.8 kB Details

Built distribution (wheel)

Table of built distributions (wheels) for agentiqdex 0.1.3
File Interpreter ABI Platform
agentiqdex-0.1.3-py3-none-any.whl Python 3 none any Details

Total release size: 36.6 kB

Release files / agentiqdex-0.1.3.tar.gz

Download URL agentiqdex-0.1.3.tar.gz
Size 17.8 kB
Tags Source
SHA-256 checksum
How to use checksums
35a81aa888750f0c946f50d0267006a6c1c3c64609899a53b9f4fdf616dc7971
BLAKE2b-256 checksum
How to use checksums
3a68a3b2c5483f23b76ba0e4598d79dce5b31108165e2d6a7e441be44717c7e3
Upload date
Uploaded using Trusted Publishing?
What is trusted publishing?
Yes
Uploaded via twine/7.0.0 CPython/3.13.14

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.

PyPI Publish Attestation

PyPI verified that this artifact, at this checksum, originated from the publisher listed below.

Signed by GitHub Actions, verified by PyPI on Sep 29, 2026.

Transparency log

Release files / agentiqdex-0.1.3-py3-none-any.whl

Download URL agentiqdex-0.1.3-py3-none-any.whl
Size 18.8 kB
Tags Python 3
SHA-256 checksum
How to use checksums
aaf9278f864d102e3fc409155f8d415c2f0825119a07f4494ba8f43a5ac94dc6
BLAKE2b-256 checksum
How to use checksums
6b98d8c99259622fd86b41a6cd79ecdacf7cd1258fd7d4b37bdf129b30f560fd
Upload date
Uploaded using Trusted Publishing?
What is trusted publishing?
Yes
Uploaded via twine/7.0.0 CPython/3.13.14

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.

PyPI Publish Attestation

PyPI verified that this artifact, at this checksum, originated from the publisher listed below.

Signed by GitHub Actions, verified by PyPI on Sep 29, 2026.

Transparency log

Release history Release notifications | RSS feed

This release

0.1.3 This release

2 release files

0.1.2

2 release files

0.1.1

2 release files

0.1.0

2 release files

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