Agent Arena
Agent Arena is an open-source, browser-native multi-agent playground.
You place LLM-powered characters on a 3D map (office, forest, or
space), watch them idle-talk, and chat with them privately or in a
shared arena. It runs entirely in the browser with OpenAI, Gemini,
Claude, or Ollama — no Agent Arena backend.
This live page is a WebGL playground and needs JavaScript. Enable JS,
or open the
source repo.
What you can do
- Drop personas onto Office, Nature, or Space maps
- Private chat, arena broadcast, and @mention
- Idle speech bubbles while the world runs
- Full-screen map editor with .aamf.json import / export
- YAML config for prompts, roles, characters, and defaults
What this is not: not a hosted multi-agent orchestration framework,
not a Discord bot, and not a server-side agent runtime.
GitHub
·
llms.txt
· Code MIT; 3D assets CC0 / CC BY