trans

Local-first, LLM-assisted literary CAT platform (EN to IT): PDF import, entity & glossary knowledge base, human-approved translation with immutable versions, DOCX/EPUB/PDF/XLIFF export. Fully offline against your own OpenAI-compatible LLM gateway

A new way for AI to search for data

View on GitHub

1GitHub stars

10commits on main

0forks

v0.3.0-alphalatest release, 2026-10-29

Python 75.3%, TypeScript 24.4%, Dockerfile 0.1%, Just 0.1% · created 2026-10-05 · last push 2026-10-29

What XERJ indexed

Snapshot

311 files · 37.1 MB

The whole repository at commit 741056f99b (2026-10-25). main is 6 commits ahead.

Selected work

manu69x
@manu69x

“bilingual UI (Italian/English) with auto-detected locale”. 33 files, 5,260 lines in frontend.

Licence

The repository

MIT

LICENSE file checked at the pinned commit; the author agreed to inclusion.

The XERJ corpus

MIT, with credit

The author agreed by email on 2026-10-26. Same terms as the repository. Answers name the repo, the commit and the file:line.

selected for the XERJ Corpus Hublicence clearedsuggested use: adapt with attribution

cat-tooldockerfastapillmlocal-firstnextjsself-hostedtranslation

Example questions

How does trans implement cat-tool?
Where does trans handle “bilingual UI (Italian/English) with auto-detected locale”?
What does frontend do in trans?

The prompt

Paste it into your AI agent. It clones manu69x/trans at the pinned commit and indexes it on your machine.

Search the GitHub repository manu69x/trans with XERJ (https://hub.xerj.org/corpus/manu69x--trans).
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/manu69x/trans trans && git -C trans checkout 741056f99b8da76d5946ddd6dd7a0c94a86c72d1
3. Start a local node and leave it running: xerj --insecure --data-dir ./xerj-data
4. xerj autoindex ./trans --url http://127.0.0.1:9200 --prefix trans --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.

manu69x AI, prompts and agents corpora dunorth595--ai-agent-chat dunorth595--ai-agent-memory xobotyi--cc-foundry-infrastructure JeremyL691/SourceHero-AI dziksu/synkinema sameeralam3127/llm-dev-kit

Stats: GitHub API, fetched 2026-10-31. Snapshot: the git tree at the pinned commit. Selected work and consent: the XERJ registry.