llm-model-filter
Filter the llm models list to show only your favorite "starred" models. Especially useful for LLM agents that need a clean list of available capabilities.
Installation
Install this plugin in the same environment as LLM:
llm install llm-model-filter
Usage
1. Configure Filtering
By default, the plugin doesn't filter anything. You can enable "starred-only" mode:
llm models config starred-only
To revert:
llm models config all
2. Starring Models
Add models to your favorites:
llm models star gpt-4o
llm models star claude-3.5-sonnet
3. Viewing Models
When configured to starred-only, the standard llm models command will only show your favorites:
llm models
To see all models regardless of configuration:
llm models list --all
4. Unstarring
Remove models from your favorites:
llm models unstar gpt-4o
How it works
This plugin wraps the llm models list command. It uses a robust callback-modification technique to ensure compatibility with existing flags while providing the filtering logic.
Starred models and configuration are stored in llm.user_dir() / "models_mod_starred.json".
Metadata
Release files for llm-model-filter 0.1.1
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 | |
|---|---|---|---|---|
| llm_model_filter-0.1.1.tar.gz | 3.6 kB | Without provenance | Details |
Built distribution (wheel)
| File | Interpreter | ABI | Platform | Reset |
|---|---|---|---|---|
| llm_model_filter-0.1.1-py3-none-any.whl | Python 3 | none | any | Details |
Total release size: 6.8 kB
Release files / llm_model_filter-0.1.1.tar.gz
| Download URL | llm_model_filter-0.1.1.tar.gz |
|---|---|
| Size | 3.6 kB |
| Tags | Source |
|
SHA-256 checksum How to use checksums |
8966ebf7f0d0372f8fdf2f173fc9f64ea9b726d0824f685df61fba7e9c0ba38e
|
|
BLAKE2b-256 checksum How to use checksums |
210b5dadc29d3717fe81e0c6a966fb4252cbdd442f459964df3fea776e466040
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
No |
| Uploaded via |
twine/6.2.0 CPython/3.14.3
|
Release files / llm_model_filter-0.1.1-py3-none-any.whl
| Download URL | llm_model_filter-0.1.1-py3-none-any.whl |
|---|---|
| Size | 3.2 kB |
| Tags | Python 3 |
|
SHA-256 checksum How to use checksums |
85f3f974cb9a9721d8cf99ade38c87dfa68b560adc6736864553db2e43658c83
|
|
BLAKE2b-256 checksum How to use checksums |
33d83b2e1dca308db657f48e8412f92ef0f3b6f44e5446677885b177cbace465
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
No |
| Uploaded via |
twine/6.2.0 CPython/3.14.3
|
Security for llm-model-filter 0.1.1
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.