Guides

Hermes Agent

Run Hermes Agent on any MiniRouter model through its custom endpoint.

Hermes Agent is Nous Research's always-on personal agent. Add MiniRouter as its custom endpoint to run it on any model in the catalog, move side tasks to cheaper models, and cap unattended spend with rate limits.

1. Install Hermes

Terminal
curl -fsSL https://hermes-agent.nousresearch.com/install.sh | bash

2. Save your key

Create a key, then add it to Hermes's env file.

~/.hermes/.env
MINIROUTER_KEY=mr-live-YOUR-KEY-HERE

3. Point Hermes at MiniRouter

Terminal
hermes model
SettingValue
hermes modelCustom endpoint (self-hosted / VLLM / etc.)
model.base_urlhttps://api.minirouter.sh/v1Paste it complete, including /v1.
model.providercustom
model.defaultzai/glm-5.3-flash
model.key_envMINIROUTER_KEY
MINIROUTER_KEYmr-live-… (your key)In ~/.hermes/.env, not config.yaml.

4. Start and verify

Terminal
hermes

Send one message, then open Request logs. The request lists its model, tokens and exact cost. If nothing arrives, run hermes doctor.

Switch models

WhereScope
/model custom:openai/gpt-5.6-lunaThis session.
/model custom:openai/gpt-5.6-sol --onceThe next turn only.
/model custom:openai/gpt-5.6-luna --globalThis session and new ones.
hermes chat -m openai/gpt-5.6-lunaOne run.
model.defaultNew sessions, in ~/.hermes/config.yaml.
Model IDAnswers with
minirouter/autoA model Auto picks. Tool calls get a tool-capable one.
@preset/your-slugYour saved preset, editable in the dashboard.

Run from scripts

-m overrides the model for that run only.

Terminal
hermes -z "Summarize today's inbox" \
  -m zai/glm-5.3-flash \
  --usage-file usage.json
CommandPrints
hermes -zThe final answer only.
hermes chat --oneshot -qThe answer and tool output, then exits.

Move side tasks and add fallbacks

Compression, vision and titles run on your main model unless you move them. A fallback takes over when the main model fails.

~/.hermes/config.yaml
auxiliary:
  compression:
    base_url: https://api.minirouter.sh/v1
    model: deepseek/deepseek-v4-flash-0731
    api_key: ${MINIROUTER_KEY}

fallback_providers:
  - provider: custom
    model: openai/gpt-5.6-luna
    base_url: https://api.minirouter.sh/v1
    key_env: MINIROUTER_KEY

Compare rates for side-task models on Models, or read Model fallbacks for server-side fallbacks.

Keep spend in check

Restrict models or filter content with Guardrails.

Troubleshooting

Provider loads but every model call 404s

Paste https://api.minirouter.sh/v1 complete, including the /v1. These clients treat the base URL as the OpenAI-compatible root and append /chat/completions themselves, so trimming the /v1 leaves them calling a path that does not exist.

Error: 400 invalid_request.

Credits gone overnight with nothing to show

An agent in a retry loop spends at machine speed. Set dailyLimitNano on the key the agent uses — one key per agent, so a runaway is contained to that key rather than the whole balance.

Error: 402 insufficient_credits.

401 on every request

Wrong or rotated key. Keys start with mr-live-; after a rotation the old key keeps working for 24 hours, then dies.

Error: 401 invalid_api_key.

Response stops mid-sentence with a credits message

Balance hit $0 mid-stream. The stream ends with a terminal error naming the exact charge for tokens delivered — never a silent close.

Error: 402 insufficient_credits.

Every error code, with its fix: Errors.

Next steps