chatgpt-web-adapter

Local Python SDK and CLI for integrating consumer AI web products into apps and agents, with browser-backed sessions

A new way for AI to search for data
View on GitHub
19GitHub stars

Python

What XERJ indexed

Snapshot

Whole repository

The whole repository at commit e7f3cb804e (2026-10-09).

Selected work

Ikymuco
@kymuco

“close cross-format export index race and publish manifests exclu…”. 3 files, 214 lines in src/chatgpt_web_adapter, tests.

Licence

The repository

MIT

Checked by a person at the pinned commit.

The XERJ corpus

MIT, with credit

The author agreed by email on 2026-10-23. 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

chatgptpythondeveloper-toolspython-sdkautomationbrowser-automationcliweb-automation

Example questions

The prompt

Paste it into your AI agent. It clones kymuco/chatgpt-web-adapter at the pinned commit and indexes it on your machine.

Search the GitHub repository kymuco/chatgpt-web-adapter with XERJ (https://hub.xerj.org/corpus/kymuco--chatgpt-web-adapter).
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/kymuco/chatgpt-web-adapter chatgpt-web-adapter && git -C chatgpt-web-adapter checkout e7f3cb804e2348bfee92a8f6e640232264fd8c59
3. Start a local node and leave it running: xerj --insecure --data-dir ./xerj-data
4. xerj autoindex ./chatgpt-web-adapter --url http://127.0.0.1:9200 --prefix chatgpt-web-adapter --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.