This release is a pre-release and may not be stable for production use.
DragonGlass
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-001for 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
Metadata
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)
| File | Size | Uploaded | Provenance | Actions |
|---|---|---|---|---|
| dragonglass-0.1.0b4.tar.gz | 199.5 kB | Without provenance | Details for dragonglass-0.1.0b4.tar.gz |
Built distribution (wheel)
| File | Interpreter | ABI | Platform | Actions Reset |
|---|---|---|---|---|
| dragonglass-0.1.0b4-py3-none-any.whl | Python 3 | none | any | Details for dragonglass-0.1.0b4-py3-none-any.whl |
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
|
Security for dragonglass 0.1.0b4
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.