DEDUPED Hot AI repos, turned into use cases Get the Monday 5

How to route Bots to a local model when sign-in fails with Hermes Bot Forge

Set a fallback model so new Bots still run when their inherited login is not ready.

Who it is forA user whose main model uses OAuth sign-in, who wants new Bots to keep working on a local model server.

The problemAn OAuth-based Bot needs a per-Bot sign-in before it can answer, which stops it from working right away.

The outcomeNew Bots switch to a configured local model when their inherited model cannot sign in.

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

  1. Run hermes plugins enable bot-forge on the profile that creates Bots
  2. Open that profile's config.yaml and set plugins.entries.bot-forge.settings.fallback_model to a local model with its base_url
  3. Run hermes bot-forge-doctor to confirm which sandbox backends and models this machine can run
  4. Create a Bot and check its result for the sign-in status

Prompt for your agent

Using the repo BkashJEE/hermes-bot-forge, set fallback_model in the bot-forge settings to a local model at <base_url> and create a Bot. Expected output: a result that names the model the Bot is using and whether a sign-in is still needed. Verify by running hermes bot-forge-doctor and checking the model status it reports.

Caveat. The README says a local model server must be running at the base_url you set, and it does not say the plugin starts one.

Share: 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 The use cases, steps, and prompts are written by AI and may be incomplete, outdated, or just wrong.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