Your first 2 examples on your readme involve single agents. These are a waste of time. We don't need yet another llm api call wrapper. An agentic system with just 1 tool / agent is pointless.
Thankfully your third example half way down does have an eg with 3 agents. May have helped to have a judge/architect agent.
Not clear about the infra required or used.
Would help to have helper functions to get and set session state/memory. Being able to bootstrap from json could be a good feature.
Would help to have diff agents with diff llms to show that you have thought things through.
Why should spawning 1000's of agents even be in your benchmark. Since when did we start counting variables. Maybe saying each agent would take X memory/ram would suffice - because everything is subjective, can't be generalized.
Consider a rest api that can do what the examples did via curl?
Thankfully your third example half way down does have an eg with 3 agents. May have helped to have a judge/architect agent.
Not clear about the infra required or used.
Would help to have helper functions to get and set session state/memory. Being able to bootstrap from json could be a good feature.
Would help to have diff agents with diff llms to show that you have thought things through.
Why should spawning 1000's of agents even be in your benchmark. Since when did we start counting variables. Maybe saying each agent would take X memory/ram would suffice - because everything is subjective, can't be generalized.
Consider a rest api that can do what the examples did via curl?
Good luck!