Credentials. The helper copies your root profile's auth.json, so every Bot receives a copy of that login and you must protect those files.
Who it is forA user with an OAuth model subscription who wants new Bots to work without a sign-in for each one, and accepts that the helper is unsupported.
The problemEvery new Bot needs its own sign-in for an OAuth model, which adds a manual step for each one.
The outcomeNew Bots can use the shared login, copied as an independent file with permissions 0600.
What you need first
- Hermes Agent 0.21 or newer with the hermes CLI on your PATH
- Hermes Desktop for Bot Mode (the CLI also works, since Bots are profiles)
- Linux or macOS (Windows is not supported)
- A model provider configured in Hermes
Steps
- Review the README section on the shared login helper and confirm you accept that it is unsupported
- Run
python extras/share_login.pyfrom the repo - Create a new Bot and check its result for the sign-in status
- Confirm the Bot's credential file has permissions 0600
Prompt for your agent
Using the repo BkashJEE/hermes-bot-forge, run python extras/share_login.py and then create a Bot for <job>. Expected output: a Bot whose result does not ask for a per-Bot sign-in. Verify that the copied auth file has permissions 0600 and that auth.lock was not copied.
Caveat. The README says the plugin itself never touches credentials and that this helper is unsupported and runs only when you run it yourself.
Every Monday: the 5 hottest repos and exactly how to use them. Free, one email a week, unsubscribe anytime.
Get them freeShare: X LinkedIn Hacker News Email Copy link
Disclaimer
Deduped lists open-source repositories that belong to other people. We do not own, maintain, audit, or vouch for any of them, and a repo appearing here is not an endorsement or a safety check. The use cases, steps, and prompts are written by AI and may be incomplete, outdated, or just wrong. Where a use case is marked "Seen in the wild", we link to public posts where someone described something similar, but we have not verified those posts and the use case itself is still our AI's own write-up. Use all of this at your own risk. Only run code, commands, or agents on systems and accounts you are authorized to use, and read the code and every command before you run it, especially anything that touches credentials, files, or the network. Nothing here is professional, security, legal, or financial advice. All trademarks and project names belong to their respective owners, and their use here does not imply affiliation. Content is provided as is, without warranties of any kind. Found a mistake, a safety problem, or something you want removed? Email [email protected] and we will look at it promptly. Full disclaimer page