pinned
Runtime error
Agents
3
LibVulnWatch
🥇
Vulnerability scores for AI libraries (ACL '25, ICML '25)
AI & ML interests
Responsible AI
Running
Persival Observability
🧠
Memory-aware agent trace viewer with attack overlay
Sleeping
4
AgentSeer
🔍
Visualize AI agent workflows and security risks
Running
1
AgentGraph
🕸
Visualize AI agent execution logs as interactive graphs
Sleeping
Agents
Stereotypical Gpt2
🐠
Sleeping
SAGED Build Demo
👀
Scraping and Assembling Benchmark. Arxiv: 2409.11149
Running
(paper) Explainability Metrics
📊
Evaluate explainability of machine learning models
Build error
Ragdemo
🦀
Build error
Recruiting Potshots
📊
Runtime error
LLM Risks
🦀
Sleeping
1
Explainbility Benchmark
👀
Running
1
Job Fair
👀
Upload resumes to evaluate fairness in hiring decisions
Build error
ML Vertical Risks Papers
🐠
Runtime error
1
Flops Calculator
🐠
Sleeping
LLM Mitigation
📈
Runtime error
Sythetic Evaluation Data Generation
🏃
Sleeping
LLM Open Generation Bias
👀
Runtime error
Agents
Emotion Recognition
😻