A CLI for querying a panel of llms and returning a combined, cross-referended response, with extensive customisation and usage modes.
Project description
Amalgam
If you're anything like me, towards the end of your projects, you're always querying multiple (5+) llm models at the same time, hoping to catch the last of the tiny issues, and trying to get the best out of every llm. But having seven opencode instances in numerous ghostty windows is messy, screen-constrained, and for my humble laptop, resource intensive. Amalgam aims to solve this by quering multiple llms at the same time (with multiple instances of the same model at different temperatures) and then merging the results together, giving you the best of all worlds in one place. Highly customisable, with cli flags covering temperatures, number of models, timeout, preview lengths, and more. Enjoy!
Installation
pip install amalgam-panel
Usage
amalgam --key <your key> --timeout 120 --max_temperature 1 'What is life?'
Download files
Download the file for your platform. If you're not sure which to choose, learn more about installing packages.
Source Distribution
Built Distribution
Filter files by name, interpreter, ABI, and platform.
If you're not sure about the file name format, learn more about wheel file names.
Copy a direct link to the current filters
File details
Details for the file amalgam_panel-0.1.2.tar.gz.
File metadata
- Download URL: amalgam_panel-0.1.2.tar.gz
- Upload date:
- Size: 43.4 kB
- Tags: Source
- Uploaded using Trusted Publishing? No
- Uploaded via: twine/6.2.0 CPython/3.14.6
File hashes
| Algorithm | Hash digest | |
|---|---|---|
| SHA256 |
e59ee2c734f66dbe826bf562729258b6140e99a80c7156130dd5f7e603cd014b
|
|
| MD5 |
74f4e9ca6f3362cd5733811bd1a14260
|
|
| BLAKE2b-256 |
48cdf36479283e0df9b00f82a86919eafb61bbc610a967ae9d1deb9ae4b30424
|
File details
Details for the file amalgam_panel-0.1.2-py3-none-any.whl.
File metadata
- Download URL: amalgam_panel-0.1.2-py3-none-any.whl
- Upload date:
- Size: 32.2 kB
- Tags: Python 3
- Uploaded using Trusted Publishing? No
- Uploaded via: twine/6.2.0 CPython/3.14.6
File hashes
| Algorithm | Hash digest | |
|---|---|---|
| SHA256 |
287f3e8ec2c0a7e2542e418973aed19ba64e0e52d0e7ebba17ae3d84b833d3f1
|
|
| MD5 |
3311b9e22cb6776f45dfcb6513b35a5e
|
|
| BLAKE2b-256 |
e8b77f650d2da4f64e162b3c93f4a29b9508c1abab557a9d4bd05d53b644813e
|
