DEDUPED Hot AI repos, turned into use cases Get 5 a day

How to swap models mid-chat from the LiquidGlass panel with Opengrok

Change the model an agent uses during a conversation and confirm the switch with a verified hop receipt.

Who it is forA user running a long Grok Bot session who wants to move a task to a different model without restarting the agent.

The problemA conversation may need a different model partway through, but restarting the agent would lose the thread's momentum.

The outcomeThe agent's next reply uses the newly chosen model, and the switch is confirmed end to end with a copyable proof.

What you need first

  • A working Grok Bot desktop install
  • Python 3.9+ and Node 18+
  • API keys for each provider you plan to bind

Steps

  1. Complete the setup with python setup.py so the LiquidGlass HUD is in place.
  2. Confirm the HUD is injected with python tools/glass-inject.py --check.
  3. Open the agent in Grok Bot and choose a bound model from the glass dropdown.
  4. Wait for the VERIFIED HOP confirmation, then use Copy Proof if you need the receipt.
  5. Watch the Context Guardian bar against the 256k window during long runs.

Prompt for your agent

Using the OnlyTerp/opengrok repo, run `python tools/glass-inject.py --check` and report whether the LiquidGlass HUD is present in the Grok Bot app. Then switch the active agent to <target-model> from the glass dropdown. Verify the VERIFIED HOP confirmation appears before reporting success.

Caveat. The HUD lives inside the Grok Bot window, so it only appears after glass-inject has run against your installed app version.

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 The use cases, steps, and prompts are written by AI and may be incomplete, outdated, or just wrong.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