A personal AI model-routing stack that learns from your usage
Project description
quillm 🦔
A personal AI model-routing stack that learns from your usage.
A quill is a hedgehog's spine. quillm routes each query to the model that answers it best — and learns that routing from your usage over time. It stays small (the routing brain is tiny), runs local-first, and grows sharper the more you use it.
"The fox knows many things, but the hedgehog knows one big thing." — Archilochus
Big models try to do everything. quillm does one thing: knowing which model answers this question best.
This is a pre-alpha placeholder reserving the name. The full stack — gateway, agent, knowledge graph, and a learned coordinator that cuts strong-model calls while preserving quality — is in active development:
👉 https://github.com/Createyouracccount/quillm
Install
pip install quillm
quillm --version
License
Apache-2.0
Release history Release notifications | RSS feed
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 quillm-0.0.1.tar.gz.
File metadata
- Download URL: quillm-0.0.1.tar.gz
- Upload date:
- Size: 1.9 kB
- Tags: Source
- Uploaded using Trusted Publishing? No
- Uploaded via: twine/6.2.0 CPython/3.12.9
File hashes
| Algorithm | Hash digest | |
|---|---|---|
| SHA256 |
ab40a87233e9a9006d99ae156b68b7ae4204f9a5563b0fd8ddc92aaa73e04fc1
|
|
| MD5 |
c6a041f61bf288b5b0531020f76c329b
|
|
| BLAKE2b-256 |
7964cc9bd103185b68ca1d6cde3e104246e99ef9b837c7510f32078163d11898
|
File details
Details for the file quillm-0.0.1-py3-none-any.whl.
File metadata
- Download URL: quillm-0.0.1-py3-none-any.whl
- Upload date:
- Size: 2.6 kB
- Tags: Python 3
- Uploaded using Trusted Publishing? No
- Uploaded via: twine/6.2.0 CPython/3.12.9
File hashes
| Algorithm | Hash digest | |
|---|---|---|
| SHA256 |
4741d8988f76a2fa822530c7e1706969127f8c82c2234a5159813ad5752a1c71
|
|
| MD5 |
a279df18d6863939b1284a80a7ec96df
|
|
| BLAKE2b-256 |
64e4311e487a4079a57c3a04d97a7022de917a54c72d11023b6fc0c188dec84d
|
