Skip to main content
All Hermes Stories
Dev Workflow5 min read@exitcode42

9 Hermes Agents Split Into 2 Rival AI Companies — Building and Shipping Code Autonomously

The GLADIATOR experiment: 9 agents divided into rival companies competing for GitHub stars. They write code, create skills, grow memory, and commit to git — with no human intervention.

9

competing agents

2

rival AI companies

0

human commits required

Key Takeaways

  • Multi-agent competition — two teams of agents with conflicting goals — produces more diverse and innovative output than single-agent or cooperative setups.
  • Agents committed to git, created skills, and grew their own memory without human intervention: the full development loop ran autonomously.
  • This is a proof of concept for agent-native software development teams, where humans provide direction and review rather than implementation.

The GLADIATOR Setup

Nine Hermes agents were split into two rival groups, each constituting a fictional AI company competing for GitHub stars. Each group had a distinct goal, a shared codebase, and no human operators in the implementation loop.

actually learn and improve — they wrote code

What Autonomous Actually Means Here

The agents autonomously wrote code, created skills, updated their own memory files, and committed directly to git. Not 'autonomously generated code that a human reviewed and committed' — the agents ran the full loop independently.

The competition mechanic meant each team developed different strategies for acquiring GitHub stars, leading to diverse approaches that a single-agent setup wouldn't have produced.

  • Write code independently without human implementation
  • Create and save reusable skills from completed tasks
  • Update MEMORY.md with project context
  • Commit to git and manage branches without human intervention
  • Adapt strategy based on competitor behaviour

Why Competition Produces Better Output

The competition mechanic is the key insight. Cooperative multi-agent systems tend to converge on consensus approaches. Competitive systems develop divergent strategies. For software development, divergent strategies mean exploring a wider solution space — which produces more innovative outcomes than any single agent or cooperative team would.

Story sourced from the official Nous Research Hermes user-stories page. Original author: @exitcode42.

Give your Hermes agent a soul

A consistent identity makes Hermes more powerful

AgentSoul generates a four-file personality bundle — identity, soul, user context, and agent directives — tuned to your Enneagram type. Drop it into Hermes and your agent has a coherent voice from session one.