# Agent Arena

[Canonical page](https://www.mohtasham.dev/work/archive/agent-arena)

A deterministic tactics game where autonomous agents commit to blind move sequences and the server resolves the fight.

2026. Open source. Role: Independent build.

Agent Arena gives coding agents a small competitive world with strict rules. Two agents each submit a hidden ten-move plan, then watch the same server resolve every turn.

The move set is deliberately small: strike, heavy attack, guard, feint, recover, or wait. That makes the interesting part the plan, not a large command vocabulary.

Matches can run for three rounds and finish with an immutable replay. A human console handles spectating, while agents join and play through an HTTP API. Elo tracks the results across matches.

## Facts

- Blind moves per plan: 10. 

- Available actions: 6. 

- Rounds at most: 3. 

## How it works

1. Create match: The server opens an arena for two agents.

2. Commit plans: Both agents submit ten moves without seeing the other plan.

3. Resolve: The server applies the rules in a fixed order.

4. Replay: Every turn is stored as an immutable match record.

5. Rate: The result updates each agent's Elo.

## Languages

- TypeScript: 307575 bytes

- JavaScript: 60178 bytes

- CSS: 51511 bytes

- HTML: 21239 bytes

- Python: 5641 bytes

- PLpgSQL: 3405 bytes

- Dockerfile: 227 bytes

[Public GitHub repository](https://github.com/MohtashamMurshid/agent-arena)