Hermes Agent is an open-source autonomous agent from Nous Research that runs on your server — not tethered to an IDE. It lives on CLI, Telegram, Discord, Slack, WhatsApp, and 10+ other platforms, with persistent memory, self-improving skills, and full terminal/browser control. Hermes works with any OpenAI-compatible endpoint, which makes Portkey a drop-in gateway. Route Hermes through Portkey to get full observability, cost tracking, budget controls, fallbacks, and access to 200+ models — without changing how you use Hermes.

Quick start

Install Hermes

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

Supports Linux, macOS, and WSL2. See the Hermes installation docs for details.

Add a provider in Portkey

Go to AI Providers → Add Provider → select your LLM provider (OpenAI, Anthropic, Google, etc.).Enter your provider API key and create a slug like openai-prod or anthropic-prod.

Get your Portkey API key

Go to API Keys → Generate a new key.

Configure Hermes to use Portkey

Edit ~/.hermes/config.yaml to point the main model at Portkey’s OpenAI-compatible endpoint:

model:
  provider: custom
  default: "@openai-prod/gpt-4o"
  base_url: https://api.portkey.ai/v1
  api_key: YOUR_PORTKEY_API_KEY

Replace:

YOUR_PORTKEY_API_KEY with your Portkey API key
@openai-prod with your provider slug
gpt-4o with any model that provider supports

The model format is @<provider-slug>/<model-name> — this maps directly to a provider integration in your Portkey workspace.

Use hermes config set to save values without opening the file:

hermes config set model.provider custom
hermes config set model.base_url https://api.portkey.ai/v1
hermes config set model.default "@openai-prod/gpt-4o"
hermes config set OPENAI_API_KEY YOUR_PORTKEY_API_KEY

API keys are saved to ~/.hermes/.env; everything else goes to config.yaml.

Start chatting

hermes chat

All Hermes requests now route through Portkey. Monitor usage, costs, and traces in the Portkey Dashboard.

Reliability

All reliability controls are configured through Portkey Configs and attached to a scoped API key. Hermes sends the key as a Bearer token — Portkey applies the logic server-side, so Hermes config stays simple. Create a Config at Configs, then attach the Config ID to a scoped API key at API Keys → Create Key → Advanced Settings. Use that scoped key as OPENAI_API_KEY in Hermes.

Fallbacks

Route to backup providers when the primary fails — critical for long-running autonomous Hermes sessions where a provider outage shouldn’t break the task:

{
    "strategy": { "mode": "fallback" },
    "targets": [
        { "provider": "@openai-prod" },
        { "provider": "@anthropic-prod" },
        { "provider": "@bedrock-prod" }
    ]
}

Load balancing

Distribute requests across multiple keys or providers:

{
    "strategy": { "mode": "loadbalance" },
    "targets": [
        { "provider": "@openai-key-1", "weight": 0.5 },
        { "provider": "@openai-key-2", "weight": 0.5 }
    ]
}

Caching

Reduce costs and latency for repeated queries (common with Hermes’s scheduled cron jobs):

{
    "provider": "@openai-prod",
    "cache": { "mode": "simple" }
}

Retries

Automatically retry failed requests:

{
    "provider": "@openai-prod",
    "retry": { "attempts": 3, "on_status_codes": [429, 500, 502, 503] }
}

Metadata for tracing

Attach metadata in the same Config to group and filter logs by session, host, environment, or user:

{
    "provider": "@openai-prod",
    "metadata": {
        "agent": "hermes",
        "environment": "production",
        "host": "vps-01"
    }
}

Budget limits

Hermes runs unattended via cron, messaging gateways, and subagents — costs can spiral without controls. Set provider-level limits in Portkey:

Go to AI Providers → select your provider
Click Budget & Limits
Configure:
- Cost limit: e.g., $200/month
- Token limit: e.g., 10M tokens/week
- Rate limit: requests per minute

Budget limits automatically block further requests when thresholds are hit, preventing runaway costs from autonomous sessions.

Switch models mid-session

Inside a Hermes chat, use /model to switch to any model available in your Portkey workspace:

/model custom:@anthropic-prod/claude-sonnet-4-6
/model custom:@gemini-prod/gemini-2.5-pro

Multiple Portkey providers

To keep multiple Portkey-backed routes distinct — say, a production key for your main agent and a separate key for subagents — define them as named custom providers in ~/.hermes/config.yaml:

custom_providers:
  - name: portkey-prod
    base_url: https://api.portkey.ai/v1
    key_env: PORTKEY_API_KEY
    api_mode: chat_completions
  - name: portkey-dev
    base_url: https://api.portkey.ai/v1
    key_env: PORTKEY_DEV_KEY
    api_mode: chat_completions

model:
  provider: custom
  default: "@openai-prod/gpt-4o"
  base_url: https://api.portkey.ai/v1
  api_key: ${PORTKEY_API_KEY}

Set both keys in ~/.hermes/.env:

PORTKEY_API_KEY=pk-...
PORTKEY_DEV_KEY=pk-...

Switch between them mid-session:

/model custom:portkey-prod:@openai-prod/gpt-4o
/model custom:portkey-dev:@anthropic-prod/claude-sonnet-4-6

3. Set Up Enterprise Governance

Why Enterprise Governance?

Cost Management: Controlling and tracking AI spending across teams
Access Control: Managing team access and workspaces
Usage Analytics: Understanding how AI is being used across the organization
Security & Compliance: Maintaining enterprise security standards
Reliability: Ensuring consistent service across all users
Model Management: Managing what models are being used in your setup

Portkey adds a comprehensive governance layer to address these enterprise needs. Enterprise Implementation Guide

Step 1: Implement Budget Controls & Rate Limits

Model Catalog enables you to have granular control over LLM access at the team/department level. This helps you:

Set up budget limits
Prevent unexpected usage spikes using Rate limits
Track departmental spending

Setting Up Department-Specific Controls:

Navigate to Model Catalog in Portkey dashboard
Create new Provider for each engineering team with budget limits and rate limits
Configure department-specific limits

Step 2: Define Model Access Rules

As your AI usage scales, controlling which teams can access specific models becomes crucial. You can simply manage AI models in your org by provisioning model at the top integration level.

Step 4: Set Routing Configuration

Portkey allows you to control your routing logic very simply with it’s Configs feature. Portkey Configs provide this control layer with things like:

Data Protection: Implement guardrails for sensitive code and data
Reliability Controls: Add fallbacks, load-balance, retry and smart conditional routing logic
Caching: Implement Simple and Semantic Caching. and more…

Example Configuration:

Here’s a basic configuration to load-balance requests to OpenAI and Anthropic:

{
	"strategy": {
		"mode": "load-balance"
	},
	"targets": [
		{
			"override_params": {
				"model": "@YOUR_OPENAI_PROVIDER_SLUG/gpt-model"
			}
		},
		{
			"override_params": {
				"model": "@YOUR_ANTHROPIC_PROVIDER/claude-sonnet-model"
			}
		}
	]
}

Create your config on the Configs page in your Portkey dashboard. You’ll need the config ID for connecting.

Configs can be updated anytime to adjust controls without affecting running applications.

Step 4: Implement Access Controls

Step 3: Implement Access Controls

Create User-specific API keys that automatically:

Track usage per developer/team with the help of metadata
Apply appropriate configs to route requests
Collect relevant metadata to filter logs
Enforce access permissions

Create API keys through:

Example using Python SDK:

from portkey_ai import Portkey

portkey = Portkey(api_key="YOUR_ADMIN_API_KEY")

api_key = portkey.api_keys.create(
    name="frontend-engineering",
    type="organisation",
    workspace_id="YOUR_WORKSPACE_ID",
    defaults={
        "config_id": "your-config-id",
        "metadata": {
            "environment": "development",
            "department": "engineering",
            "team": "frontend"
        }
    },
    scopes=["logs.view", "configs.read"]
)

For detailed key management instructions, see our API Keys documentation.

Step 5: Deploy & Monitor

Step 4: Deploy & Monitor

After distributing API keys to your engineering teams, your enterprise-ready setup is ready to go. Each developer can now use their designated API keys with appropriate access levels and budget controls. Apply your governance setup using the integration steps from earlier sections Monitor usage in Portkey dashboard:

Cost tracking by engineering team
Model usage patterns for AI agent tasks
Request volumes
Error rates and debugging logs

Enterprise Features Now Available

You now have:

Departmental budget controls
Model access governance
Usage tracking & attribution
Security guardrails
Reliability features

Portkey Features

Now that you have an enterprise-grade setup, let’s explore the comprehensive features Portkey provides to ensure secure, efficient, and cost-effective AI operations.

1. Comprehensive Metrics

Using Portkey you can track 40+ key metrics including cost, token usage, response time, and performance across all your LLM providers in real time. You can also filter these metrics based on custom metadata that you can set in your configs. Learn more about metadata here.

2. Advanced Logs

Portkey’s logging dashboard provides detailed logs for every request made to your LLMs. These logs include:

Complete request and response tracking
Metadata tags for filtering
Cost attribution and much more…

3. Unified Access to 1600+ LLMs

You can easily switch between 1600+ LLMs. Call various LLMs such as Anthropic, Gemini, Mistral, Azure OpenAI, Google Vertex AI, AWS Bedrock, and many more by simply changing the provider slug in your default config object.

4. Advanced Metadata Tracking

Using Portkey, you can add custom metadata to your LLM requests for detailed tracking and analytics. Use metadata tags to filter logs, track usage, and attribute costs across departments and teams.

Custom Metata

5. Enterprise Access Management

Budget Controls

Set and manage spending limits across teams and departments. Control costs with granular budget limits and usage tracking.

Single Sign-On (SSO)

Enterprise-grade SSO integration with support for SAML 2.0, Okta, Azure AD, and custom providers for secure authentication.

Organization Management

Hierarchical organization structure with workspaces, teams, and role-based access control for enterprise-scale deployments.

Access Rules & Audit Logs

Comprehensive access control rules and detailed audit logging for security compliance and usage tracking.

6. Reliability Features

Fallbacks

Automatically switch to backup targets if the primary target fails.

Conditional Routing

Route requests to different targets based on specified conditions.

Load Balancing

Distribute requests across multiple targets based on defined weights.

Caching

Enable caching of responses to improve performance and reduce costs.

Smart Retries

Automatic retry handling with exponential backoff for failed requests

Budget Limits

Set and manage budget limits across teams and departments. Control costs with granular budget limits and usage tracking.

7. Advanced Guardrails

Protect your Project’s data and enhance reliability with real-time checks on LLM inputs and outputs. Leverage guardrails to:

Prevent sensitive data leaks
Enforce compliance with organizational policies
PII detection and masking
Content filtering
Custom security rules
Data compliance checks

Guardrails

Implement real-time protection for your LLM interactions with automatic detection and filtering of sensitive content, PII, and custom security rules. Enable comprehensive data protection while maintaining compliance with organizational policies.

FAQs

How do I update my AI Provider limits after creation?

Update AI Provider limits at any time from Model Catalog: 1. Open the provider you want to modify. 2. Update the budget or rate limits. 3. Save your changes.

Can I use multiple LLM providers with the same API key?

Yes! Add multiple AI Providers to Model Catalog (one for each provider) and attach them to a single config. This config can then be connected to your API key, allowing you to use multiple providers through a single API key.

How do I track costs for different teams?

Portkey provides several ways to track team costs:

Create separate AI Providers for each team
Use metadata tags in your configs
Set up team-specific API keys
Monitor usage in the analytics dashboard

What happens if a team exceeds their budget limit?

When a team reaches their budget limit:

Further requests will be blocked
Team admins receive notifications
Usage statistics remain available in dashboard
Limits can be adjusted if needed

Next Steps

Join our Community

For enterprise support and custom features, contact our enterprise team.

Ecosystem

LLM Integrations

Cloud Platforms

Guardrails

Plugins

Vector Databases

Agents

AI Apps

Libraries

Tracing Providers

MCP Clients

MCP Servers

Documentation Index

​Quick start

​Reliability

​Fallbacks

​Load balancing

​Caching

​Retries

​Metadata for tracing

​Budget limits

​Switch models mid-session

​Multiple Portkey providers

​3. Set Up Enterprise Governance

​Step 1: Implement Budget Controls & Rate Limits

​Setting Up Department-Specific Controls:

​Step 2: Define Model Access Rules

​Example Configuration:

​Step 3: Implement Access Controls

​Step 4: Deploy & Monitor

​Enterprise Features Now Available

​Portkey Features

​1. Comprehensive Metrics

​2. Advanced Logs

​3. Unified Access to 1600+ LLMs

​4. Advanced Metadata Tracking

Custom Metata

​5. Enterprise Access Management

Budget Controls

Single Sign-On (SSO)

Organization Management

Access Rules & Audit Logs

​6. Reliability Features

Fallbacks

Conditional Routing

Load Balancing

Caching

Smart Retries

Budget Limits

​7. Advanced Guardrails

Guardrails

​FAQs

​Next Steps

Quick start

Reliability

Fallbacks

Load balancing

Caching

Retries

Metadata for tracing

Budget limits

Switch models mid-session

Multiple Portkey providers

3. Set Up Enterprise Governance

Step 1: Implement Budget Controls & Rate Limits

Setting Up Department-Specific Controls:

Step 2: Define Model Access Rules

Example Configuration:

Step 3: Implement Access Controls

Step 4: Deploy & Monitor

Enterprise Features Now Available

Portkey Features

1. Comprehensive Metrics

2. Advanced Logs

3. Unified Access to 1600+ LLMs

4. Advanced Metadata Tracking

5. Enterprise Access Management

6. Reliability Features

7. Advanced Guardrails

FAQs

Next Steps