Back to Search

agent-arena

AgentGitHubActiveTypeScript

An evaluation arena for AI agents whose referee runs no model: deterministic adversarial scenarios, hash-committed replays, SARIF reports.

Description provenance: Original source

Open canonical source

Measured: Oct 16, 2026 · 9 observations

Domains & Uses

Domains
Agents, skills and MCP

Check at the source

Compatibility and prerequisites must be checked in the official documentation.

https://github.com/rbrus/agent-arena

Classifications

Nature
Tool