polynx

pandas-style query/eval/assign for Polars: string expressions compiled to native Polars expressions. Eager + lazy, @var, UDFs, agent-ready

A new way for AI to search for data
View on GitHub
7GitHub stars

Python

What XERJ indexed

Snapshot

Whole repository

The whole repository at commit 87e7131aaf (2026-10-06).

Selected work

Lowell Winston
@LowellWinston

“Enhance engine: Add Polars plx namespace, optimize methods, add CI wo…”. 7 files, 267 lines in src/polynx, tests, the project root.

Licence

The repository

MIT

Checked by a person at the pinned commit.

The XERJ corpus

MIT, with credit

The author agreed by email on 2026-10-20. Same terms as the repository. Answers name the repo, the commit and the file:line.

in licence reviewnot in the hub yetsuggested use: adapt with attribution

dataframeevalllm-toolspandaspolarspythonquerystring-expression

Example questions

The prompt

Paste it into your AI agent. It clones LowellWinston/polynx at the pinned commit and indexes it on your machine.

Search the GitHub repository LowellWinston/polynx with XERJ (https://hub.xerj.org/corpus/lowellwinston--polynx).
Run these in a shell, in order, and check each result before the next:
1. xerj --help  (success: it prints usage). If xerj is missing: curl -fsSL https://xerj.org/get | sh
2. git clone https://github.com/LowellWinston/polynx polynx && git -C polynx checkout 87e7131aafc7c33af007e7e8b8217b8f7167f33c
3. Start a local node and leave it running: xerj --insecure --data-dir ./xerj-data
4. xerj autoindex ./polynx --url http://127.0.0.1:9200 --prefix polynx --progress plain
5. xerj autoindex map --url http://127.0.0.1:9200
Then answer my question from the indexed files and cite the ax_path of every hit. Query syntax: https://xerj.org/llms.txt
Licence: MIT. Keep the copyright notice and credit the authors.

Related

Selected work and consent: the XERJ registry.