Inference Exchange
From its catalog listing
Serve local Inference Exchange models while Hermes CLI is idle.
Good to know before installing
when `sell_enabled` is turned on (off by default), runs the Python interpreter and Inference Exchange checkout you configure as a background process that registers this machine as an open-trust inference provider with your configured coordinator (for example the author-operated `alpha.inferenceex.com`), passes it your `IE_PROVIDER_TOKEN`, and serves third-party prompts on your local llama-server while Hermes is idle; it can block a turn if it cannot stop that process.
From its catalog listing.
How to install
- Install it. Hermes asks for any API keys it needs, then asks whether to turn it on.
hermes plugins install inference-exchange - Said no? Turn it on later:
hermes plugins enable inference-exchange - Restart Hermes so it loads the plugin.
Some plugins also need a sign-in or settings: see Full setup & settings. Memory plugins ask whether to become your memory provider instead. Steps follow the official plugins guide (opens in a new tab).
- Category
- AI models & providers · Automation & multi-agent
- Maintained by
- qzyu999 (Community)
- Needs
- No API keys declared
- Adds hooks
on_session_startpre_llm_callpost_llm_callon_session_endon_session_finalize- Needs Hermes
- 0.23.0 or newer
- Version
- 0.1.0
- In the catalog
- 2026-11-09
Using the Hermes desktop app? See where plugins live

Full setup & settings ↗Source code ↗
More in ai models & providers
All ai models & providers plugins
New Hermes Agent updates every day on X. Follow @HermesWatcher