erdos

An open record of the Erdős problems

A new way for AI to search for data
View on GitHub
15GitHub stars

shell

What XERJ indexed

Snapshot

Whole repository

The whole repository at commit 1ab58af687 (2026-10-14).

Selected work

Andrew Turner
@acturner

“Record Plasma AI's resolution of Problem 408's first two questions”. 7 files, 687 lines in library, the project root.

Licence

The repository

Apache-2.0

From GitHub's licence detection. A person still checks the LICENSE file at the pinned commit.

The XERJ corpus

Apache-2.0, with credit

The author agreed by email on 2026-10-15. 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

Example questions

The prompt

Paste it into your AI agent. It clones plasma-ai/erdos at the pinned commit and indexes it on your machine.

Search the GitHub repository plasma-ai/erdos with XERJ (https://hub.xerj.org/corpus/plasma-ai--erdos).
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/plasma-ai/erdos erdos && git -C erdos checkout 1ab58af6873264e61abc0fae5a5149df79e19d48
3. Start a local node and leave it running: xerj --insecure --data-dir ./xerj-data
4. xerj autoindex ./erdos --url http://127.0.0.1:9200 --prefix erdos --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.

Related

Selected work and consent: the XERJ registry.