Overview
Hermes Agent provides a self-hosted inference server for NousResearch Hermes models and other open-weight large language models optimised for agentic tasks. It supports structured function calling, tool use, and constrained JSON output, making it suitable for building AI agents, code assistants, and automated pipelines. The server exposes an OpenAI-compatible API so existing integrations and SDKs work without modification. Run it on your own infrastructure for data privacy, predictable latency, and cost control compared to managed inference endpoints.
Highlights
- OpenAI-compatible API means existing SDKs, LangChain, and AutoGen integrations work with no code changes
- Native structured function calling and JSON mode for reliable tool use in agentic and automation workflows
- Self-hosted inference keeps sensitive prompts within your own VPC with no data leaving your account
Details
Introducing multi-product solutions
You can now purchase comprehensive solutions tailored to use cases and industries.
Features and programs
Financing for AWS Marketplace purchases
Pricing
Dimension | Description | Cost/hour |
|---|---|---|
Hermes Agent - Self-Hosted Autonomous AI Agent | Hourly software fee per running container task | $0.01 |
Vendor refund policy
Contact support@waltsoft.net within 30 days.
How can we make this page better?
Legal
Vendor terms and conditions
Content disclaimer
Delivery details
ECS Container
- Amazon ECS
Container image
Containers are lightweight, portable execution environments that wrap server application software in a filesystem that includes everything it needs to run. Container applications run on supported container runtimes and orchestration services, such as Amazon Elastic Container Service (Amazon ECS) or Amazon Elastic Kubernetes Service (Amazon EKS). Both eliminate the need for you to install and operate your own container orchestration software by managing and scheduling containers on a scalable cluster of virtual machines.
Version release notes
Initial container release v1.0.0.
Additional details
Usage instructions
Quick Start
Pull the container image
Run with Docker
Deploy on Amazon ECS
- Create an ECS cluster (Fargate or EC2 launch type)
- Register a task definition using the image above
- Map container port 8642 to the host or load balancer
- Attach a persistent volume at /data for configuration
- Run the service and note the assigned public IP or ALB DNS
Access the application
- Open http://YOUR-HOST:8642 in your browser
- Complete the first-run setup wizard if prompted
- Create your administrator account
Port Mappings
- 8642: Primary web interface
Persistent Data
Mount a volume at /data to preserve configuration across restarts.
Support
Contact support@waltsoft.net for deployment assistance. Response within 24 hours.
Support
Vendor support
For support, contact support@waltsoft.net or visit
AWS infrastructure support
AWS Support is a one-on-one, fast-response support channel that is staffed 24x7x365 with experienced and technical support engineers. The service helps customers of all sizes and technical abilities to successfully utilize the products and features provided by Amazon Web Services.