Arize AX
Phoenix OSS
Docs

Arize AX
Managed AI engineering platform
Phoenix OSS
Open-source observability and evals
Start here

Blog
AI engineering best practices
Video tutorials
Hands-on product walkthroughs

Build your playbook

Resources
Guides, templates, and reports
Glossary
Learn AI engineering terminology

See it in production

Customers
How teams ship production AI
Events
Live and on-demand events
Community
Connect with AI engineers
Company

About
We power the future of AI
Careers
Join a world class team
Partners
Partner with us

Press
Updates from the newsroom
Security
We take your trust seriously
Pricing

Arize AX
Phoenix OSS
Docs
Learn
Company
Pricing

Blog

Filter

ADB Agent architecture Agent harness Agent reliability Agents AI In the Enterprise Case Studies Company Computer Vision Data Science Embeddings Enterprise Evaluations Generative AI Guardrails Harness engineering Integrations Interviews Large Language Models Leadership LLM Evals LLMOps ML Monitoring ML Observability MLOps Observability Observability & tracing Paper Readings Phoenix Podcasts Product Product Releases Product tutorials Prompt Learning Release Notes Research Responsible AI Sandboxing Self-improving agent Tutorials & quickstarts Use-Case

Clear all

How Hermes implements an open source agent harness architecture

Hermes from NousResearch is a strong open-source agent harness. This post examines how its runtime loop, context management, tool scoping, session infrastructure, and orchestration patterns map to a modern agent harness architecture.

6 minutes read

By Aparna Dhinakaran | 6 minutes read

Agent architecture

Hero image titled “The architecture of an agent harness” showing a circular diagram with nine core components of a modern agent system: iteration loop, context management, tools and skills, subagent management, session persistence, system prompt assembly, lifecycle hooks, and permissions, arranged around a central “Harness 1.0” core.

What is an agent harness?

A version of this article originally appeared on X. Someone asked me at a hacker event last week: “Can anyone actually tell me what a harness really is?” It was said with real skepticism. The kind of skepticism that says we all use the word “Harness” in the industry, but nobody actually knows what it…

9 minutes read

By Aparna Dhinakaran | 9 minutes read

Agent architecture

Subscribe to our resources and blogs

Subscribe

Platform

Arize AX
Alyx
adb
Phoenix Open Source
Arize AX Docs
Phoenix Docs
Pricing

Learn

Blog
AI Agent Evaluation Resources
Customers
Events
Community
Glossary

Topics

LLM Evaluations
Agent Evaluation Metrics
LLM Evals: Proving AI ROI
AI Agent Analytics: A Buyer’s Guide
LLM-as-a-Judge
Arize vs. Braintrust
Arize vs. Langsmith
Arize vs. Langfuse

Company

About
Careers
Press
Partners
Security

Get started
Book a Demo
Sign In
Contact
AX Platform Status
Privacy Policy
LLMs.txt
Linkedin
Twitter

Subscribe to The Evaluator

We’ll send you the latest news, expertise, and product updates from Arize. Your inbox is sacred, so we’ll only curate and send the best stuff.

*We're committed to your privacy. Arize uses the information you provide to contact you about relevant content, products, and services. You may unsubscribe from these communications at any time. For more information, check out our privacy policy.

Docs

Start here

Build your playbook

See it in production