PPI
PPI is a small C++ prototype for a simple.pd language. It started as a lexer and grew into a tiny parser/interpreter that can read a file
A new way for AI to search for data
3GitHub stars
What XERJ indexed
Selected work

“Let keyword”. 6 files, 222 lines in examples, the project root, interpreter.
Licence
The repository
Apache-2.0
Checked by a person at the pinned commit.
The XERJ corpus
Apache-2.0, with credit
The author agreed by email on 2026-10-24. 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
- Where does PPI handle “Let keyword”?
- What does interpreter do in PPI?
The prompt
Paste it into your AI agent. It clones PranishDhital/PPI at the pinned commit and indexes it on your machine.
Search the GitHub repository PranishDhital/PPI with XERJ (https://hub.xerj.org/corpus/pranishdhital--ppi). 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/PranishDhital/PPI PPI && git -C PPI checkout 3001bbdb67bc24e92e40cc48c405a36a01dd3f48 3. Start a local node and leave it running: xerj --insecure --data-dir ./xerj-data 4. xerj autoindex ./PPI --url http://127.0.0.1:9200 --prefix ppi --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
Pranish DhitalAPI design and specification corpora
Selected work and consent: the XERJ registry.