runtimenoteslabs

runtimenoteslabs / gladiator

Public

Two zero-human AI companies battle for GitHub stars using Hermes Agent + Paperclip. Nous Research Hackathon 2026.

ai-agents autonomous-agents hackathon hermes-agent nous-research
17
2
100% credibility
Found Mar 20, 2026 at 17 stars -- GitGems finds repos before they trend. Get early access to the next one.
Sign Up Free
AI Analysis
Python
AI Summary

Gladiator is an open-source demonstration that simulates a competition between two autonomous AI companies improving a terminal-based LLM comparison tool, tracked via a real-time dashboard to showcase agent learning and strategy.

How It Works

1
🏟️ Discover Gladiator

You stumble upon this fun AI battle arena on GitHub, where two rival companies compete to build the best product.

2
🛠️ Get your setup ready

Follow easy guides to prepare your computer, like installing a few helpers and starting a simple planning tool.

3
🤖 Connect smart thinkers

Link a creative AI service so the agents can plan, code, and learn like real team members.

4
👥 Build the rival teams

Create Blitz for speedy growth tricks and Craft for perfect quality work, each with their own leaders and workers.

5
📊 Launch the live show

Open the colorful dashboard in your web browser to see scoreboards, task lists, and agent actions updating live.

6
▶️ Start the battle

Click the big launch button and watch the 9 agents race through 10 tasks in about 5 minutes, improving a handy tool.

🎉 Crown the winner and unite

Celebrate the top team by projected popularity, then merge them to share skills and prove AI teams learn together.

Sign up to see the full architecture

5 more

Sign Up Free

Star Growth

See how this repo grew from 17 to 17 stars Sign Up Free
Repurpose This Repo

Repurpose is a Pro feature

Generate ready-to-use prompts for X threads, LinkedIn posts, blog posts, YouTube scripts, and more -- with full repo context baked in.

Unlock Repurpose
AI-Generated Review

What is gladiator?

Gladiator runs zero-human AI companies in a GitHub stars battle: Blitz (growth hacks) vs Craft (quality focus), both improving the same Python CLI tool for side-by-side LLM comparisons using Anthropic models. Launch via dashboard to watch agents commit code, draft tweets, add tests, and rack up projected stars in real-time, powered by Hermes Agent workers and Paperclip orchestration. It demos if rapid shipping or deep polish wins OSS traction, like gladiator 1 vs gladiator 2 in a gladiator film arena.

Why is it gaining traction?

Stands out with live 9-panel dashboard—task boards, Gantt charts, code diffs, skill timelines—tracking AI learning across heartbeats, unlike solo-agent toys. Hook: merge winners post-battle to prove cross-team skill transfer, echoing gladiator github io spectacles or gladiator hoppers github experiments. Low 17 stars but buzz from hackathon vibes and two GitHub accounts simulation (same computer, Mac/VSCode/SSH/email setups).

Who should use this?

AI agent builders benchmarking Hermes/Paperclip stacks, hackathon hackers needing a gladiator plus demo (even gladiator plus pferd-style battles), or OSS maintainers testing strategies like knulli gladiator github or nano gladiator github. Ideal for gladiators rtl fans scripting gladiators trier tickets for automated repo wars.

Verdict

Amusing hackathon toy (1.0% credibility, 17 stars, great docs/video) to visualize multi-agent dev—run it for $5-6 Anthropic runs, but skip for production until maturity grows. Worth a spin if two GitHub accounts intrigue you.

(198 words)

Sign up to read the full AI review Sign Up Free

Similar repos coming soon.