Sold by: Waltsoft Inc.
Deployed on AWS
Free Trial
AWS Free Tier
Self-hosted AI agent with persistent memory, autonomous skill creation, and multi-platform messaging. OpenAI-compatible API. BYO model provider. 200K+ GitHub stars. MIT licensed.
Overview
Overview
Hermes Agent by Nous Research is a self-hosted autonomous AI agent with persistent memory, skill creation, and multi-platform messaging. It connects to your LLM provider (OpenAI, Anthropic, local models) and runs as a background service exposing an OpenAI-compatible API on port 8642.
Unlike cloud-hosted AI assistants, Hermes Agent runs entirely in your AWS account. Your conversations, memories, skills, and API keys never leave your infrastructure. The agent learns from interactions, creates reusable skills autonomously, and integrates with Telegram, Discord, Slack, and WhatsApp.
Key Features
- Persistent Memory - The agent remembers across sessions. Conversations, preferences, and context persist in a local store under your control.
- Autonomous Skill Creation - Hermes creates reusable skills from interactions. Skills are saved locally and improve the agent over time.
- Multi-Platform Messaging - Connect Telegram, Discord, Slack, or WhatsApp bots. One agent, multiple channels.
- OpenAI-Compatible API - Port 8642 exposes a standard API. Drop-in replacement for any OpenAI client library.
- Scheduled Automations - Define cron-style tasks. The agent runs them unattended on schedule.
- Web Dashboard - Built-in monitoring UI on port 9119 with session history, token usage, and agent status.
- Multi-Profile - Run multiple independent agents from one instance, each with separate memory, skills, and credentials.
- BYO Model Provider - Works with OpenAI, Anthropic, local vLLM/Ollama, or any OpenAI-compatible endpoint.
Architecture
Hermes runs as a Docker container with s6-overlay process supervision. The gateway process manages LLM calls, messaging integrations, and the API server. All state persists in /opt/hermes-data on the EBS volume - config, sessions, memories, skills, and credentials.
Getting Started
- Launch this AMI (t3.micro is sufficient for the agent itself)
- SSH in and configure your LLM provider: docker exec -it hermes-agent hermes setup
- Set up messaging (optional): connect Telegram, Discord, Slack, or WhatsApp
- Access the API at http://your-instance:8642/v1/chat/completions
Use Cases
- Personal AI Assistant - A private ChatGPT that remembers everything, runs on your infra, costs only API fees.
- Team Automation Bot - Connect to Slack/Discord, automate workflows, answer questions from persistent knowledge.
- Development Agent - Code review, PR summaries, documentation generation with tool use and memory.
- Customer Support Agent - Multi-channel bot that learns from resolved tickets and improves over time.
Requirements
- An LLM API key (OpenAI, Anthropic, or self-hosted endpoint)
- t3.micro minimum (1 vCPU, 1GB RAM) - t3.small recommended for browser tools
- Security group: allow port 8642 (API), 9119 (dashboard), 22 (SSH)
Good to Know
- Hermes itself is free and MIT-licensed. You pay only for the EC2 instance plus your LLM API usage.
- 200,000+ GitHub stars. Active community with daily releases.
- All data stays on your EBS volume. Nothing phones home.
- Default API key is changeme-on-first-boot - change it immediately after launch.
Highlights
- Self-hosted autonomous AI agent with persistent memory - remembers across sessions, creates reusable skills, and improves over time. All data stays on your EC2 instance. 200K+ GitHub stars, MIT licensed, daily releases from Nous Research.
- Multi-platform messaging with one agent - connect Telegram, Discord, Slack, and WhatsApp simultaneously. Schedule automations, define cron tasks, and run unattended workflows. OpenAI-compatible API on port 8642.
- BYO model provider - works with OpenAI, Anthropic, local vLLM, Ollama, or any OpenAI-compatible endpoint. No vendor lock-in. Multi-profile support runs independent agents on one instance with separate memory and credentials.
Details
Sold by
Categories
Delivery method
Delivery option
64-bit (x86) Amazon Machine Image (AMI)
Latest version
Operating system
Ubuntu 24.04
Deployed on AWS
New
Introducing multi-product solutions
You can now purchase comprehensive solutions tailored to use cases and industries.
Features and programs
Financing for AWS Marketplace purchases
AWS Marketplace now accepts line of credit payments through the PNC Vendor Finance program. This program is available to select AWS customers in the US, excluding NV, NC, ND, TN, & VT.
Pricing
Free trial
Try this product free for 5 days according to the free trial terms set by the vendor. Usage-based pricing is in effect for usage beyond the free trial terms. Your free trial gets automatically converted to a paid subscription when the trial ends, but may be canceled any time before that.
Pricing is based on actual usage, with charges varying according to how much you consume. Subscriptions have no end date and may be canceled any time.
Additional AWS infrastructure costs may apply. Use the AWS Pricing Calculator to estimate your infrastructure costs.
If you are an AWS Free Tier customer with a free plan, you are eligible to subscribe to this offer. You can use free credits to cover the cost of eligible AWS infrastructure. See AWS Free Tier for more details. If you created an AWS account before July 15th, 2025, and qualify for the Legacy AWS Free Tier, Amazon EC2 charges for Micro instances are free for up to 750 hours per month. See Legacy AWS Free Tier for more details.
Dimension | Description | Cost/hour |
|---|---|---|
t3.medium Recommended | t3.medium instance | $0.08 |
t3.micro | t3.micro instance | $0.00 |
t3.large | t3.large instance | $0.08 |
m5.large | m5.large instance | $0.08 |
m5.xlarge | m5.xlarge instance | $0.08 |
r5.large | r5.large instance | $0.08 |
Vendor refund policy
No refunds. Cancel anytime. Contact support@waltsoft.net .
Legal
Vendor terms and conditions
Upon subscribing to this product, you must acknowledge and agree to the terms and conditions outlined in the vendor's End User License Agreement (EULA) .
Content disclaimer
Vendors are responsible for their product descriptions and other product content. AWS does not warrant that vendors' product descriptions or other product content are accurate, complete, reliable, current, or error-free.
Delivery details
64-bit (x86) Amazon Machine Image (AMI)
Amazon Machine Image (AMI)
An AMI is a virtual image that provides the information required to launch an instance. Amazon EC2 (Elastic Compute Cloud) instances are virtual servers on which you can run your applications and workloads, offering varying combinations of CPU, memory, storage, and networking resources. You can launch as many instances from as many different AMIs as you need.
Version release notes
Hermes Agent v4.0.0 - Self-hosted autonomous AI agent with persistent memory, skill creation, and multi-platform messaging. Port 8642 (API) + 9119 (dashboard).
Additional details
Usage instructions
- Launch instance (t3.micro minimum). Open ports 22, 8642, 9119 in Security Group.
- SSH in: ssh ubuntu@<public-ip>
- Configure your LLM provider: docker exec -it hermes-agent hermes setup
- OpenAI-compatible API at http://<public-ip>:8642/v1/chat/completions
- Web dashboard at http://<public-ip>:9119 (requires auth config)
IMPORTANT: Change the default API key immediately after launch. All agent data persists at /opt/hermes-data/ on the EBS volume.
Support
Vendor support
For technical support, email 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.
Similar products
Pre-configured Hermes Agent AI with browser automation, Docker, Tailscale, Caddy, and developer tools. SSH in, run hermes setup, start building with AI.
Self-hosted AI agent console for Amazon Bedrock on Rocky Linux.
Your business goals driven Customer Experience solution for Customer service, Sales and Marketing contact centre operations, made simple to deploy and use.
This daily dataset is best for analyzing the pricing and trading patterns of Hermes and Birkin luxury handbags in the secondary markets via auctions and online sales. It contains 20+ years of sales records across vendors in North America, Europe and Asia.
Customer reviews
No customer reviews yet
Be the first to review this product . We've partnered with PeerSpot to gather customer feedback. You can share your experience by writing or recording a review, or scheduling a call with a PeerSpot analyst.