Add xAI and Xiaomi MiMo Providers
TL;DR
First-class support for xAI (Grok) and Xiaomi MiMo providers, including direct API access, model catalog integration, and setup wizard support.
## What changed Hermes Agent added first-class support for xAI and Xiaomi MiMo providers. The update includes direct API access, full model catalog integration, and setup wizard guidance for both.
The change arrived on May 18, 2026. Users can now select these providers through the existing /model command without extra configuration files.
## Why it matters This move gives Vibe Builders more options to balance cost against output quality. xAI Grok handles reasoning tasks at competitive rates while Xiaomi MiMo offers fast responses for routine automation.
The addition pressures single-provider agents to expand or lose ground. It signals Hermes Agent's bet that builders want live switching across 400-plus models rather than locked-in stacks.
## How to use it Update to the latest Hermes Agent release through the built-in /update command. Run the setup wizard once, then select xAI or Xiaomi MiMo from the model list.
Bring your own API keys for either provider. Switch models mid-session with the /model command and test latency on your typical Telegram or Discord workflows.
## Watch for Confirm the bet if usage logs show frequent switches between Grok and MiMo for different task types. The bet breaks if API stability lags behind OpenAI or Anthropic routes. Expect the next move to add rate-limit controls inside the web dashboard.
Harsh’s take
For a solo Vibe Builder running a business in 2026, this means one less reason to maintain separate accounts across providers. You can now route cheap monitoring tasks to MiMo and keep Grok for anything that needs chain-of-thought without leaving the same agent instance.
The real trade-off is still the always-on VPS requirement. Adding two more models does not remove the need for a $5-20 monthly server or the YAML edits for each messaging gateway.
Do this now: update Hermes Agent today, add one xAI key, and run three recurring tasks through the new provider to measure actual token spend before committing further.
by Harsh Desai
About Hermes Agent
View the full Hermes Agent page →All Hermes Agent updatesGo deeper
More AI news
- Daily RoundupGLM 5.3 and Vercel agent tools land, Gemini SAT practice, plus fresh models on Hugging Face
Google and Vercel released new agent and model features while Hugging Face and Replicate added trending models; OpenAI tightened safety after agent issues.
- Daily RoundupVercel-Origin beta and GPT-5.6 Sol discount, plus agent tools for builders
Vercel rolled out Origin repository deployments and a month-long GPT-5.6 Sol discount on AI Gateway while Product Hunt featured new agent layers and Hugging Face highlighted an uncensored Qwen model, with industry moves around data use and automation exits.
- Weekly DigestHermes Agent v0.20 voice and A2A protocol, OpenClaw mobile updates, and multi-agent tools to test now
Hermes Agent rolled out v0.20 releases with voice streaming, A2A interoperability, desktop artifacts, and self-recovery tools while OpenClaw added Android switching, iOS caching, and plugin provenance checks across the week.