Overlay-Translator

Screen overlay translator: select any region (like Win+Shift+S) - OCR reads the text, an LLM translates it with context-aware prompts…

A new way for AI to search for data
View on GitHub
6GitHub stars

Python

What XERJ indexed

Snapshot

Whole repository

The whole repository at commit 1502e37d38 (2026-10-21).

Selected work

Oleksandr
@alhite

“added model version picker that lists hugging face tags, matches loca…”. 4 files, 582 lines in translate, ui, tests.

Licence

The repository

MIT

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

The XERJ corpus

MIT, with credit

The author agreed by email on 2026-10-22. 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

llmoverlay-toolpyqt5pythonscreen-capturewindowsocrtranslation

Example questions

The prompt

Paste it into your AI agent. It clones Vrihe/Overlay-Translator at the pinned commit and indexes it on your machine.

Search the GitHub repository Vrihe/Overlay-Translator with XERJ (https://hub.xerj.org/corpus/vrihe--overlay-translator).
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/Vrihe/Overlay-Translator Overlay-Translator && git -C Overlay-Translator checkout 1502e37d385c56a1cf8a89abf73db14f60b048b7
3. Start a local node and leave it running: xerj --insecure --data-dir ./xerj-data
4. xerj autoindex ./Overlay-Translator --url http://127.0.0.1:9200 --prefix overlay-translator --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.