Using one big chat thread in Hermes can inflate your API costs by 3–4x
The most common way people interact with Hermes Agent is through a single, never-ending thread where they discuss everything — content ideas, research, personal tasks. The problem is that every time you send a new message, the agent sends the entire prior conversation along with it. If that thread is massive, you're transmitting a huge payload with every single request, which causes costs to skyrocket. Alex notes that 'I'm paying a thousand dollars a month' is the number one complaint about Hermes, but the root cause is almost always poor session hygiene. If you keep your context slim and isolated by topic, you are not paying anything close to that amount.
Go deeper with Greg Isenberg
Ask anything about this, and Greg Isenberg answers from everything they've shared.
More to learn
See everything in Learn
MembersLLM-as-judge: automated quality scoring for agent outputs
Instead of relying on yourself as the sole judge of every agent output, you can use a separate LLM as a judge that fires off and scores outputs along the dimensions you care about. You can then see the trend line of how an agent is scoring
The $999 AI Assessment Playbook: Sell, Run, and Upsell a Productized AI Audit
Product: The $999 AI Assessment Playbook: Sell, Run, and Upsell a Productized AI Audit Format: Digital download: the-999-ai-assessment-playbook-sell-run-and-upsell-a-product.pdf Price: $79.00 USD Description: Learn to land your first pay
Small businesses are deploying AI agents faster than 50,000-person companies ever could
In Hyper Agent's early adoption base, small shops have become surprisingly sophisticated very quickly and are running their operations in genuinely game-changing ways. The reason is simple: a 50,000-person company can't pivot on a dime — th