turkmenistan_addresses

Offline address search for Turkmenistan: settlements, streets and houses in a 292 KB on-device database, no network at runtime

A new way for AI to search for data
View on GitHub
3GitHub stars

Dart, Python

What XERJ indexed

Snapshot

Whole repository

The whole repository at commit 32c84750b1 (2026-10-19).

Selected work

Perhat
@petyaas

“1.1.0: public places, border polygon, fresh OSM data”. 6 files, 756 lines in tool, lib/src, test.

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

address-searchdartfluttergeocodingofflineopenstreetmapturkmenistan

Example questions

The prompt

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

Search the GitHub repository petyaas/turkmenistan_addresses with XERJ (https://hub.xerj.org/corpus/petyaas--turkmenistan-addresses).
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/petyaas/turkmenistan_addresses turkmenistan_addresses && git -C turkmenistan_addresses checkout 32c84750b11388cec2eb42ae6f8d6525e36edec3
3. Start a local node and leave it running: xerj --insecure --data-dir ./xerj-data
4. xerj autoindex ./turkmenistan_addresses --url http://127.0.0.1:9200 --prefix turkmenistan-addresses --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.