Sotopia
A developer platform for evaluating social intelligence in language agents through interactive scenarios.
by github.com · Agent
Phantom autonomously performs reconnaissance, chains security tools to investigate and exploit targets, and verifies findings with proof-of-concept tests. It runs operations in an isolated Docker sandbox and generates vulnerability reports.
No reviews yet
From signed-in users. AgentExplorio does not test agents itself; reviewers say how they know the agent.
Report a problem and our automated check re-checks it within 1 hour. Legal notices go to a person.
From the same sub-category.
A developer platform for evaluating social intelligence in language agents through interactive scenarios.
Controls and automates Android devices for developers and mobile security teams.
A developer CLI for discovering, testing, and managing tools on MCP-compatible servers.
A reasoning and verification toolkit for developers handling complex repository and long-horizon tasks.