Console

Home / Agents / Hermes Agent

Hermes Agent

Nous Research's self-improving agent

Nous Research OpenAI-compatible macOSLinuxWindows
Official install page All tools

Hermes Agent is Nous Research's open-source agent that runs in the terminal, on the desktop, and on messaging platforms, with tool calling, persistent memory, and self-improving skills. It suits teams that want a long-running, multi-surface agent wired to any OpenAI-compatible backend. It points at a custom endpoint via model.base_url / OPENAI_BASE_URL.

Base URL (root)https://quantoport.comPut this in each tool's base_url or *_BASE_URL setting.
OpenAI-compatible pathhttps://quantoport.com/v1Append /v1 for anything speaking the OpenAI wire (/v1/chat/completions).
Recommended modelsdeepseek-v4-proclaude-sonnet-5gpt-5.5Names published in our own catalogue — confirm the live list for your key with GET /v1/models.

Skip it — one-line setup

The script installs Hermes Agent from its official source, writes the gateway settings into the tool's own config file (backing up any existing one) and runs a live check. It asks for your gateway key, or take it from --key / --key-file. --uninstall restores exactly what it wrote.

shell
curl -fsSL https://quantoport.com/agents/hermes/setup | bash

1 · Install

Install Hermes Agent from its own official source.

install
curl -fsSL https://hermes-agent.nousresearch.com/install.sh | bash
# or via PyPI:
pip install hermes-agent

2 · Configure — point it at QuantoPort

Gateway base URL https://quantoport.com; get your key from the console.

config
International site https://quantoport.com (OpenAI format, supported directly):
Option A (env vars, in ~/.hermes/.env or your shell):
   export OPENAI_BASE_URL=https://quantoport.com/v1
   export OPENAI_API_KEY=<your gateway key>
   then run hermes model to pick the provider (or hermes setup).
Option B (config.yaml, via hermes config edit):
   model:
     provider: <your custom provider name>
     base_url: https://quantoport.com/v1
     api_key: <your gateway key>
CN site https://api.shinlinkai.com (OpenAI format, supported directly): change the URL to https://api.shinlinkai.com/v1.

3 · Verify

One request proves you are on our channel.

verify
hermes chat -q "say hi"
# a reply means the connection works; hermes doctor also checks the config.

4 · Common pitfalls

  • Routing lives in config.yaml (model/provider); the script writes model.provider=custom:<site> plus a providers.<site> block, with .env OPENAI_BASE_URL only as a fallback.
  • Your existing ~/.hermes/config.yaml is backed up first (as config.yaml.<site>.bak); --uninstall restores it.
  • If you already had model:/providers: sections, they are commented out (leaving a '# [site] your original value' note) to avoid duplicate-key YAML errors.

Sources for the tool-side steps: hermes-agent.nousresearch.com/docs hermes-agent.nousresearch.com/docs/reference/environment-var hermes-agent.nousresearch.com/docs/getting-started/installat