Aryan Srivastava
Aryan Srivastava's work was selected for the XERJ Corpus Hub, the open reference memory AI coding agents search before they write code. When an agent meets the same problem, it gets this implementation back as a worked example, with the author and the repository attached.
Totals across every corpus @aryansri05 appears in; a commit selected for two corpora counts once. Files and lines count the selected commits; each corpus indexes the whole repository at its pinned commit.
What an agent can do with the cudf corpus
NVIDIA/cudf: cuDF - GPU DataFrame Library
- Look up how cudf implements gpu, rapids, arrow, with answers cited to file and line.
- Reuse a worked example: the commit “Preserve row order for ordered multi-rank Union” (6 files · Python).
- Answer from cudf's real Python source instead of memory (API design and specification).
- Where does cudf handle “Preserve row order for ordered multi-rank Union”?
- How does cudf implement gpu?
- What does python do in cudf?
Search the GitHub repository NVIDIA/cudf with XERJ (https://hub.xerj.org/corpus/nvidia--cudf). 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/NVIDIA/cudf cudf && git -C cudf checkout e0dcaf69d171b6d8fc44fdc157f798046692b5f0 3. Start a local node and leave it running: xerj --insecure --data-dir ./xerj-data 4. xerj autoindex ./cudf --url http://127.0.0.1:9200 --prefix cudf --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: Apache-2.0. Keep the copyright notice and credit the authors.
corpus nvidia--cudf · API design and specification
Related corpora: datafusion, polars, LowellWinston/polynx, nikfio/forex_data
Search an OpenAPI spec from an agent · Case study: reference coding for agents
Selected work
NVIDIA/cudf
The corpus is the whole repository at the pinned commit, not only the files of the selected commit.
Sign in with GitHub or Hugging Face to see more: every selected commit in full (commit date, every folder, licence review state, pin) and the pack builds of each corpus.
[](https://hub.xerj.org/contributors/aryansri05)
Included with the author's permission (email, 2026-10-30), under each repository's own licence, with attribution. Own more repositories? Sign in with GitHub and add them. Want something removed? Reply to the email, withdraw it on /add, or open an issue on xerj-org/xerj.