Ark-Browser

AI-powered desktop browser built on Chromium

A new way for AI to search for data

View on GitHub

2GitHub stars

Python, shell

What XERJ indexed

Snapshot

Whole repository

The whole repository at commit 7fb63524c4 (2026-09-25).

Selected work

Arkapravo Ghosh
@Arkapravo-Ghosh

“Make downloaded local models usable by the agent”. 6 files, 784 lines in tests, scripts, chromium.

Licence

The repository

AGPL-3.0

Checked by a person at the pinned commit.

The XERJ corpus

Approach only

The author agreed by email on 2026-10-24. Agents read it for how it works, not to copy it. Answers name the repo, the commit and the file:line.

in licence reviewnot in the hub yetsuggested use: approach only

Example questions

Where does Ark-Browser handle “Make downloaded local models usable by the agent”?
What does chromium do in Ark-Browser?

The prompt

Paste it into your AI agent. It clones Arkapravo-Ghosh/Ark-Browser at the pinned commit and indexes it on your machine.

Search the GitHub repository Arkapravo-Ghosh/Ark-Browser with XERJ (https://hub.xerj.org/corpus/arkapravo-ghosh--ark-browser).
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/Arkapravo-Ghosh/Ark-Browser Ark-Browser && git -C Ark-Browser checkout 7fb63524c45a2b4149e75d403366d2af6717f9f1
3. Start a local node and leave it running: xerj --insecure --data-dir ./xerj-data
4. xerj autoindex ./Ark-Browser --url http://127.0.0.1:9200 --prefix ark-browser --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: AGPL-3.0. Read it for the approach only, do not copy code.

Arkapravo Ghosh Web and frontend platform corpora

Selected work and consent: the XERJ registry.