pi-distill

Adaptive memory and context for Pi: distill sessions into lasting knowledge and automatically bring relevant history into new…

A new way for AI to search for data

View on GitHub

1GitHub stars

JavaScript, TypeScript

What XERJ indexed

Snapshot

Whole repository

The whole repository at commit 3a4fd4db98.

Selected work

dyxcode
@dyxcode

“fit memory retrieval into model context”. 10 files, 447 lines in tests, src.

Licence

The repository

MIT

Checked by a person at the pinned commit.

The XERJ corpus

MIT, with credit

The author agreed by email on 2026-10-24. 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 pi-distill handle “fit memory retrieval into model context”?

The prompt

Paste it into your AI agent. It clones dyxcode/pi-distill at the pinned commit and indexes it on your machine.

Search the GitHub repository dyxcode/pi-distill with XERJ (https://hub.xerj.org/corpus/dyxcode--pi-distill).
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/dyxcode/pi-distill pi-distill && git -C pi-distill checkout 3a4fd4db9839e2d1fc0561ed518fe6ab9331a23e
3. Start a local node and leave it running: xerj --insecure --data-dir ./xerj-data
4. xerj autoindex ./pi-distill --url http://127.0.0.1:9200 --prefix pi-distill --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.

dyxcode API design and specification corpora

Selected work and consent: the XERJ registry.