Use Hermes Agent with SaladCloud

Use the SaladCloud provider plugin to connect Hermes Agent to Salad AI Gateway, or configure a self-hosted model on SaladCloud.

Last Updated: September 17, 2026

Introduction

Hermes Agent is an open-source AI agent by Nous Research with persistent memory, 40+ built-in tools, MCP integration, and a self-improvement loop that learns from every task it completes. It supports custom OpenAI-compatible endpoints, making it straightforward to point at a model on SaladCloud.

Hermes Agent pairs especially well with SaladCloud because:

• OpenAI-compatible endpoint support - connects to any SaladCloud deployment via the built-in setup wizard
• Rich MCP integration - connect GitHub, Webflow, Playwright, and any other MCP server
• Self-improving - the agent writes structured records of what worked and what didn’t, improving future task performance automatically

Hermes Agent works with SaladCloud in two ways:

• Salad AI Gateway - install the SaladCloud provider plugin and use AI Gateway API key. No infrastructure to deploy or manage. AI Gateway is in beta, with self-service pay-per-token onboarding.
• Self-hosted model - deploy your own LLM recipe on SaladCloud Container Engine, billed per hour. Note: Hermes Agent cannot pass custom headers, so authentication must be disabled on self-hosted deployments.

Prerequisites

Before getting started, make sure you have:

• A SaladCloud account
• Linux, macOS, or Windows (WSL2)
• Python 3.10+ and Node.js 18+ (the installer handles these automatically)
• Git to install the SaladCloud provider plugin
• For AI Gateway, an AI Gateway API key

Step-by-Step Setup

Step 1: Choose Your Backend

Salad AI Gateway

Salad AI Gateway uses standard Bearer token authentication. The SaladCloud plugin supplies the endpoint and model configuration for Hermes Agent.

1. Sign in to the SaladCloud portal.
2. Follow Pay-Per-Token Onboarding to fund your organization and create its AI Gateway API key.

The plugin exposes one model:

Model	Description
qwen3.6-35b-a3b	Qwen3.6 35B-A3B for agentic tasks, coding, and reasoning

Use the organization-specific key under AI Gateway Keys, not the regular SaladCloud Current API Key. AI Gateway does not use the Salad-Api-Key header required by authenticated Container Engine endpoints.

Self-Hosted on SaladCloud

Deploy an OpenAI-compatible LLM server on SaladCloud with the Authentication toggle disabled.

Hermes Agent does not support custom HTTP headers for the main LLM provider. SaladCloud uses a Salad-Api-Key header for authentication, which Hermes Agent cannot pass yet. Deploy your SaladCloud container group with authentication disabled when using Hermes Agent or create a custom proxy to handle authentication.

• Go to the SaladCloud portal and create an account if you do not already have one.
• Create an organization or choose an existing one, then click “Deploy a container group”.
• Select an LLM recipe. For the best experience with Hermes Agent’s tool-calling capabilities, use vLLM with a Hermes-format model, or the Qwen3.6-35B-A3B (llama.cpp) recipe.
• Leave Authentication disabled - Hermes Agent cannot pass a Salad-Api-Key header at the moment.
• Once deployed, note your API endpoint URL from SaladCloud (e.g., https://your-endpoint.salad.cloud). The OpenAI-compatible API will be available at {endpoint}/v1.

Available recipes:

Ready-to-deploy recipes (best for less technical users):

• qwen3.6-35B-A3B - Mixture of Experts model optimized for instruction-following and tool-calling tasks.
• qwen3.5-9b-llama-cpp - Optimized for Qwen3.5 9B model.

Recipes for custom deployments (best for advanced users):

• vllm - Recommended; enable Hermes tool calling with --enable-auto-tool-choice --tool-call-parser hermes
• llama.cpp - Supports GGUF models
• ollama - Simple model management

Step 2: Install Hermes Agent

Run the official installer - it handles Python, Node.js, dependencies, and the hermes command automatically:

curl -fsSL https://raw.githubusercontent.com/NousResearch/hermes-agent/main/scripts/install.sh | bash

Reload your shell, then verify:

source ~/.bashrc   # or ~/.zshrc on macOS
hermes --version

Step 3: Connect Hermes Agent to Your Backend

Salad AI Gateway

Update Hermes before installing the plugin. Older versions have a fixed provider list and reject saladcloud:

hermes update

Install the SaladCloud provider plugin into Hermes’ user model-provider directory:

mkdir -p ~/.hermes/plugins/model-providers
git clone https://github.com/SaladTechnologies/hermes-saladcloud-provider.git \
  ~/.hermes/plugins/model-providers/saladcloud

If you set a custom HERMES_HOME, use $HERMES_HOME/plugins/model-providers/saladcloud instead. If the plugin is already installed, skip the clone command.

Recommended: save your connection with the setup wizard. After installing the plugin, run:

hermes setup

In the model/provider section:

1. Select SaladCloud AI Gateway.
2. Enter your organization’s AI Gateway API key when prompted.
3. For Base URL, accept https://ai.salad.cloud/v1, or enter it if needed.
4. Select qwen3.6-35b-a3b as your default model, then finish the wizard.

If you have already configured Hermes and only want to change the provider and model, run hermes setup model instead of the full wizard.

Hermes saves the API key and URL locally in ~/.hermes/.env and full configuration in ~/.hermes/config.yaml. It loads these settings in future sessions, so you do not need to export the key each time you open a terminal. With a custom HERMES_HOME, the files are saved under that directory instead. Keep the .env file private and do not commit it to Git.

Run the Git installation step before setup so that SaladCloud AI Gateway appears in the provider list. The setup wizard saves credentials; it does not install the plugin. This remains a separately installed plugin, not a provider bundled with Hermes.

Alternative: supply the key for a single terminal session

If you do not use the setup wizard, export your AI Gateway key in the terminal where you launch Hermes:

export SALAD_API_KEY="your-ai-gateway-api-key"

The plugin also accepts SALAD_CLOUD_API_KEY, but SALAD_API_KEY takes precedence if both are set. Use the explicit provider/model command in Step 5. Exporting a variable does not save it for future terminal sessions.

You do not need to edit Hermes source code. See the Hermes model-provider plugin documentation for details.

Self-Hosted on SaladCloud

Run the interactive setup wizard:

hermes setup

When the wizard asks for a model provider, select Custom OpenAI-compatible endpoint and fill in:

• Base URL: https://your-endpoint.salad.cloud/v1
• API key: dummy (any non-empty string - the endpoint has no auth)
• Context length: 262144

The wizard will auto-detect the available models from your endpoint, so you do not need to specify a model name manually.

It also configures memory, tools, terminal backend, and optional messaging channels. You can accept defaults and adjust them later with hermes config edit.

Hermes Agent can import existing OpenClaw settings automatically if you have previously configured it.

Step 4: Verify Your Configuration

Salad AI Gateway

Run the provider health checks:

hermes doctor

Check that SaladCloud AI Gateway appears in the provider connectivity results. A successful check confirms that Hermes can discover the plugin and reach the models endpoint with your key.

Self-Hosted on SaladCloud

Open the configuration file:

hermes config edit

Verify that model.base_url points to your endpoint with /v1 appended, model.api_key is a non-empty value such as dummy, and model.default is the model served by your endpoint.

Step 5: Test the Connection

Salad AI Gateway

After saving your settings with hermes setup, launch Hermes in this or a new terminal:

hermes chat

Hermes uses your saved provider, model, and API key. No additional export is required. To select the provider and model explicitly, or if you used the temporary environment-variable alternative:

hermes chat --provider saladcloud -m qwen3.6-35b-a3b

Self-Hosted on SaladCloud

Launch Hermes with the configuration from the setup wizard:

hermes chat

Test with a simple task:

“Summarize what SaladCloud is in two sentences.”

If Hermes Agent responds, your setup is complete.

Troubleshoot the AI Gateway Plugin

• invalid choice: 'saladcloud': run hermes update, then retry. The command must use a Hermes version with model-provider plugin support.
• Provider missing: confirm __init__.py and plugin.yaml are directly inside ~/.hermes/plugins/model-providers/saladcloud, or the equivalent directory under your custom HERMES_HOME, then rerun hermes setup model.
• Key missing in a new terminal: run hermes setup model to save it instead of relying on a temporary export. Make sure setup and chat use the same HERMES_HOME or Hermes profile.
• 401 Unauthorized: use the organization-specific AI Gateway key, not the regular SaladCloud API key. Run hermes setup model to replace a saved key. If you use SALAD_CLOUD_API_KEY, check that an older SALAD_API_KEY value is not taking precedence.

Built-in Tools

Hermes Agent ships with 40+ built-in tools out of the box - no MCP servers or plugins required for most common tasks.

Web & Search

Tool	What it does
web_search	Search the web and return results
web_extract	Extract and parse content from any URL
browser_navigate	Control a real browser to navigate pages
browser_snapshot	Capture the current state of a browser page
browser_vision	Interact with pages using vision (click, read, etc.)

Files & Terminal

Tool	What it does
terminal	Execute shell commands
process	Start and manage background processes
read_file	Read file contents
patch	Modify files with targeted edits
execute_code	Run code in an isolated environment

Media & Voice

Tool	What it does
text_to_speech	Convert text to spoken audio
vision_analyze	Analyze and describe images
image_generate	Create images via an image generation model

Memory & Tasks

Tool	What it does
memory	Read and write persistent memory across sessions
session_search	Search past conversation sessions
todo	Create and manage task lists
cronjob	Schedule recurring tasks
clarify	Ask the user a clarifying question before proceeding

Agent Orchestration

Tool	What it does
delegate_task	Spin up a subagent to handle a subtask in parallel
send_message	Send a message to a connected messaging channel

Most tools are enabled by default. You can enable or disable individual tools with:

hermes tools

MCP Server Integration

Hermes Agent has first-class MCP support. Add any MCP server to ~/.hermes/config.yaml under mcp_servers. More details can be found in the official MCP documentation

Filesystem MCP

mcp_servers:
  filesystem:
    command: 'npx'
    args: ['-y', '@modelcontextprotocol/server-filesystem', '/path/to/your/project']

GitHub MCP

mcp_servers:
  github:
    command: 'npx'
    args: ['-y', '@modelcontextprotocol/server-github']
    env:
      GITHUB_PERSONAL_ACCESS_TOKEN: your-github-token

Playwright MCP (Browser Automation)

mcp_servers:
  playwright:
    command: 'npx'
    args: ['-y', '@playwright/mcp@latest']

Webflow MCP

mcp_servers:
  webflow:
    command: 'npx'
    args: ['-y', 'webflow-mcp-server@latest']
    env:
      WEBFLOW_TOKEN: your-webflow-token

Remote HTTP MCP Server

mcp_servers:
  remote_api:
    url: 'https://mcp.example.com/mcp'
    headers:
      Authorization: 'Bearer your-token'

After editing the config, reload MCP servers without restarting:

/reload-mcp

You can also filter which tools each server exposes:

mcp_servers:
  github:
    command: 'npx'
    args: ['-y', '@modelcontextprotocol/server-github']
    env:
      GITHUB_PERSONAL_ACCESS_TOKEN: your-token
    tools:
      include: [create_issue, list_issues, get_file_contents]

Configure Memory

Hermes Agent’s persistent memory is one of its strongest features. It works out of the box but can be tuned:

memory:
  memory_enabled: true
  memory_char_limit: 2200 # ~800 tokens

Increase memory_char_limit if the agent is working on large projects and needs to retain more context between sessions.

Use Docker for Tool Execution

For safer code execution and better isolation, set the terminal backend to Docker:

terminal:
  backend: docker
  docker_image: 'nikolaik/python-nodejs:python3.11-nodejs20'

Model Recommendations

• Qwen 3.6-35B-A3B with llama.cpp: Good for conversational tasks and simpler agentic workflows
• Qwen 3.5-9B: Suitable for lightweight tasks; less reliable for complex multi-step tool chains