STOP WASTING PAID TOKENS. START POOLING ACCOUNTS TODAY. [ GET YOUR VAULT ]

Connect Hermes Agent to SpiderGate

Who this is for: anyone running Nous Research's Hermes Agent who wants its model calls to go through SpiderGate.

What this does: walks you through setting SpiderGate as Hermes Agent's custom endpoint, with the wizard or in ~/.hermes/config.yaml.

Before you begin

  • Hermes Agent installed.

  • Permission to mint agent tokens for your brand in SpiderGate.

  • A SpiderGate model with at least 64,000 tokens of context. Hermes says smaller windows "will be rejected at startup".

  • About 5 minutes.

Steps

Step 1 — Mint an agent token

In SpiderGate, open Keys (/dashboard/gate/keys) and choose Connect an agent. Name it after the tool, set its limits, and create it. Copy the token now: SpiderGate shows it exactly once. See Agent Keys for budgets and scopes; the tool needs gate:chat and gate:models, which new tokens have by default.

Agent tokens expire, by default after 30 days. Note the date, and mint a new one before then.

Step 2 — Set the custom endpoint

Run hermes model and choose Custom endpoint (self-hosted / VLLM / etc.). Enter:

  • API base URL: https://spideriq.ai/api/gate/v1

  • API key: your SpiderGate token

  • Model name: a task alias such as spideriq/coding

  • API mode: chat_completions

  • Context length: the context of the model behind your alias, at least 64000. Leave it blank to let Hermes detect it.

Or edit ~/.hermes/config.yaml yourself:

model:
  default: spideriq/coding
  provider: custom
  base_url: https://spideriq.ai/api/gate/v1
  key_env: SPIDERGATE_API_KEY   # the token lives in ~/.hermes/.env
  context_length: 128000        # optional; must be at least 64000

Hermes keeps secrets in ~/.hermes/.env and settings in config.yaml. Put SPIDERGATE_API_KEY=… in the .env file.

Note: OPENAI_BASE_URL does not work here. Hermes honours it only for its built-in OpenAI provider; a custom endpoint is set with hermes model or model.base_url.

Warning: If the model you name is one of your own routing aliases backed by a coding-plan key (Z.ai, Alibaba Qwen, BytePlus, MiniMax), automated traffic from this tool can break that provider's plan terms. Back any alias an automation calls with pay-as-you-go keys.

Verify it worked

Start Hermes and ask it something short. Open Traces in the SpiderGate dashboard (Traces). Your request appears under the agent token you minted, with the model that served it.

Troubleshoot

Hermes refuses to start and mentions context. The model's context is under 64,000 tokens, or Hermes could not detect it. Set context_length in config.yaml to the real value, or pick a larger model.

Vision or web summaries go somewhere unexpected. Hermes sends these "auxiliary" tasks to your main model by default. Check auxiliary.* in config.yaml.

A 401 from SpiderGate. The token is wrong or expired. Mint a new one (Step 1) and update ~/.hermes/.env.

Related