Pinned Loading

1. agentward-ai/agentward agentward-ai/agentward Public

   Open-source permission control plane for AI agents. Scan, enforce, and audit every tool call.

   Python 4

2. RealBench-Pro RealBench-Pro Public

   Benchmark and eval platform for frontier risks in genAI models

   Python

3. IsItBenchmark IsItBenchmark Public

   A sophisticated system to a) identify if a given prompt is benchmarky, b) add benchmaring datasets to the system c) pick a matching method from some SOTA approaches and d) a custom 'Contamination D…

   Python

4. MixtureOfRecursions MixtureOfRecursions Public

   Python 2

5. CoTBasedAbuseDetection CoTBasedAbuseDetection Public

   Python

6. provos/ironcurtain provos/ironcurtain Public

   A secure* runtime for autonomous AI agents. Policy from plain-English constitutions. (*https://ironcurtain.dev)

   TypeScript 66 14