Skip to main content
Pre-release

This release is a pre-release and may not be stable for production use.

DragonGlass

DragonGlass CLI Python Gemini

LLM CLI engineered for developer workflows. Built on Hexagonal Architecture for strict typing, modularity, and speed.


██████╗ ██████╗  █████╗  ██████╗  ██████╗ ███╗   ██╗
██╔══██╗██╔══██╗██╔══██╗██╔════╝ █     ██╝████╗  ██║
██║  ██║██████╔╝███████║██║  ███╗██║   █ ╗██╔██╗ ██║
██║  ██║██╔══██╗██╔══██║██║   ██║██║   ██║██║╚██╗██║
██████╔╝██║  ██║██║  ██║╚██████╔╝╚██████╔╝██║ ╚████║
╚═════╝ ╚═╝  ╚═╝╚═╝  ╚═╝ ╚═════╝  ╚═════╝ ╚═╝  ╚═══╝

             ██████╗ ██╗      █████╗ ███████╗███████╗
            ██╔════╝ ██║     ██╔══██╗██╔════╝██╔════╝
            ██║  ███╗██║     ███████║███████╗███████╗  
            ██║   ██║██║     ██╔══██║╚════██║╚════██║  
            ╚██████╔╝███████╗██║  ██║███████║███████║
             ╚═════╝ ╚══════╝╚═╝  ╚═╝╚══════╝╚══════╝

$ dg 
$ cat error.log | dg chat "Analyze the log" 
$ cat error.log | dg chat "Fix the Error" --image screenshot.png

Features

Optimized for the Google Gemini ecosystem.

  • Multimodal: Native support for text, images, and audio.
  • Fast: Streams responses in real-time.
  • Efficient: Uses gemini-embedding-001 for high-quality semantic search.
  • Unix Philosophy: Designed to be piped.
    • cat logs.txt | dg chat "Analyze this error" --image screenshot.png
  • Hexagonal Architecture: Core logic is completely decoupled from infrastructure (DB, API).
  • XDG Compliant: respect your system's config standards (~/.config/dg, ~/.local/share/dg).

Installation

Requires Python 3.10+.

pipx install dragonglass

Configuration

Set your Gemini API key via environment variable:


Linux: ~/.config/dg/config.toml                                           
macOS: ~/Library/Application Support/dg/config.toml

# config.toml
    [gemini]
    google_api_key="A....D2E"
    default_model="gemini-3-pro-preview"
    temperature=0.7
    top_p=1.0
    safe_settings="BLOCK_NONE"
    grounding_enabled=true


Or run a command, and dg will guide you.

Usage

cat error.log | python -m dg chat "Fix this error" --image screenshot.png # Multimodal One-Shot (Pipe + Image)

Pipelines

Process files and data streams.

# Summarize a README
cat README.md | dg chat "Summarize the key features"

History

View your conversation logs.

dg log

Roadmap

  • Core Architecture (Hexagonal)
  • Gemini Integration (Streaming)
  • SQLite Persistence
  • Local RAG (Numpy + Embeddings)
  • Interactive TUI: Full chat interface with Textual.
  • Multimodal Inputs: dg chat --image screenshot.png "Fix this UI"
  • Project Awareness: Auto-index git repositories for context.

LICENSE

Apache License 2.0

Release files for dragonglass 0.1.0b4

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

Source distribution (sdist)

Source distribution for dragonglass 0.1.0b4
File Size Uploaded
dragonglass-0.1.0b4.tar.gz 199.5 kB Details

Built distribution (wheel)

Table of built distributions (wheels) for dragonglass 0.1.0b4
File Interpreter ABI Platform
dragonglass-0.1.0b4-py3-none-any.whl Python 3 none any Details

Total release size:218.6 kB

Release files / dragonglass-0.1.0b4.tar.gz

Download URL dragonglass-0.1.0b4.tar.gz
Size 199.5 kB
Tags Source
SHA-256 checksum
How to use checksums
01e5825ff830caaee0589764dd4ad38534fcec0b9d4a73f53325d367c472b629
BLAKE2b-256 checksum
How to use checksums
23c73ca75531d4de7f41ab211a4185a401b05b3c8b2dfdcd0d2b3c7b98612716
Upload date
Uploaded using Trusted Publishing?
What is trusted publishing?
No
Uploaded via twine/6.2.0 CPython/3.10.17

Release files / dragonglass-0.1.0b4-py3-none-any.whl

Download URL dragonglass-0.1.0b4-py3-none-any.whl
Size 19.1 kB
Tags Python 3
SHA-256 checksum
How to use checksums
517f8c904e1d3dbacac26efdcab4eb51f135ac776d327559503a911a14c26676
BLAKE2b-256 checksum
How to use checksums
3f899ab7d718b824055ebbb476a4d47ca71d1249e109f50ee45d3cb1ee4ae161
Upload date
Uploaded using Trusted Publishing?
What is trusted publishing?
No
Uploaded via twine/6.2.0 CPython/3.10.17
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