Hermes model router
Intent-based model routing overlay for Hermes Agent. Use when a request should be mapped to a configured provider/model route such as image-prompt to Qwen 4B, debugging to Sonnet, cheap routine chat, or a user-defined route in skills.config.model-router.routes.From its SKILL.md
npx -y skills add Zelray/hermes-model-routerAssembled from the repository path, not quoted from the project. Check it against their README if it does not work.
One thing to look at
- 0 stars0 stars. Stars are a popularity signal and not a quality one, but at this level it is likely that nobody has read this closely except its author, and you would be relying on your own review.
SKILL.md
2.7 KB, 574 tokens by cl100k_base, as published. Nobody here has run it
Model Router for Hermes Agent
This Hermes skill adds intent-based model-routing guidance on top of stock Hermes. Hermes already supports auxiliary.*, delegation.*, fallback_model, custom providers, /model, and per-run --provider --model overrides. This skill does not add a Hermes core feature; it reads user-editable route settings from skills.config.model-router and returns the safest command or session-switch recommendation.
Load the routing table
Read ~/.hermes/config.yaml and inspect:
skills:
config:
model-router:
default_route: routine_chat
execution_mode: advise_or_oneshot
routes: {}
If the table is absent, ask the user to add the sample from assets/config.yaml.routed. Do not invent a root intent_routes: key.
Route selection policy
Prefer native auxiliary.* slots for built-in fixed tasks. Use this skill only for semantic user intent. Match the user request against each route's keywords and intent. If multiple routes match, prefer the more specific and higher-capability route. If no route matches, use default_route.
Execution policy
command_mode | Behavior |
|---|---|
oneshot | Build an isolated hermes -z "..." --provider <provider> --model <model> command. |
advise | Recommend the exact /model provider:model or hermes chat --provider ... --model ... -q ... command. |
delegate | Use Hermes delegation only when the task can be isolated as a subtask and the configured delegate model is appropriate. |
current_session | Stay on the current/default session model. |
Always state selected route, provider, model, rationale, fallback route, and exact command. Never use /model ... --global unless the user explicitly asks to persist the change.
Optional helper
When terminal access is available, run:
python scripts/model_router.py --prompt "<user request>" --config ~/.hermes/config.yaml
Use --execute only after the user confirms that an isolated hermes -z call is acceptable.
What ships with it: 6 files
20.3 KB alongside SKILL.md, 1 of them executable
examples/
- AGENTS.md.example2.0 KB
- config.yaml.routed3.3 KB
scripts/
- model_router.pyruns7.7 KB
- .gitignore69 B
- LICENSE1.0 KB
- README.md6.2 KB