Pinned Loading

1. IBM/vakra IBM/vakra Public

   A Benchmark for Evaluating Multi-Hop, Multi-Source Tool-Calling in AI Agents

   Python 78 17

2. Shallow-UWnet Shallow-UWnet Public

   Forked from mkartik/Shallow-UWnet

   Shallow-UWnet maintains performance and has fewer parameters than the state-of-art underwater image enhancement model.

   Python 1

3. Masters-Thesis Masters-Thesis Public

   Predicting mechanical properties of materials using Machine Learning techniques on reduced order representation of microstructures. Master's thesis project conducted in Indian Institute of Technolo…

   Python

4. cuga-agent cuga-agent Public

   Forked from cuga-project/cuga-agent

   CUGA is an open-source generalist agent harness for the enterprise, supporting complex task execution on web and APIs, OpenAPI/MCP integrations, composable architecture, reasoning modes, and policy…

   Python

5. cuga-eval cuga-eval Public

   Forked from cuga-project/cuga-eval

   Evaluation harness for running multiple agent benchmarks against cuga-agent.

   Python

6. IBM/m3-train-eval IBM/m3-train-eval Public

   m3 training/evaluation pipeline

   Python 1 1