← Back to List
⚠
Notice:This resource is provided by a third-party author. Please review the code with AI tools or manually before use to ensure security and compatibility.
Pythonethz-spylab/agentdojo

agentdojo

A Dynamic Environment to Evaluate Attacks and Defenses for LLM Agents.

69.7/100
★ 736Forks: 191
View on GitHub →Homepage →
Loading report...

Similar Projects

FlashRAG

83

⚡FlashRAG: A Python Toolkit for Efficient RAG Research (WWW2025 Resource)

Python★ 3.5K

llm-guard

67

The Security Toolkit for LLM Interactions

Python★ 3.2K

promptbench

54

A unified evaluation framework for large language models

Python★ 2.8K

ADR

78

ADR secures enterprise AI agents through observability, security benchmarking, and threat detection. Deployed at Uber.

Python★ 1.3K
← Back to List