Powered by NVIDIA cuOpt: a GPU-accelerated portfolio optimization toolkit for building, backtesting, and scaling Mean-CVaR and Mean-Variance investment workflows with CUDA-X Data Science.
Use NVIDIA cuOpt GPU solvers (LP, MIP, QP) from GAMS and GAMSPy
Autonomous last-mile delivery company run by a Hermes agent — earns, spends, and runs real operations. Detects breakdowns, reroutes with NVIDIA cuOpt, and pays drivers via Stripe, reasoning on Nemotron 3 Ultra inside a NemoClaw sandbox.
Scheduling with MILP using cuOpt example
Agentic multilingual municipal-services triage for Singapore on NVIDIA Nemotron NIM + cuOpt.
Solving the Traveling Salesman Problem using Concorde, CuOpt, Gurobi and approximations using neural networks
Autonomous Airline Disruption Recovery Agent built with NVIDIA NemoClaw, OpenShell, NeMo Retriever, and cuOpt.
Turns NVIDIA cuOpt's official Intra-factory Transport example into a package that actually calls cuOpt to solve, then animates the result with ROS2 waypoints + tf2: on startup it solves a 6-pair pickup-delivery VRP (2 AMRs, capacity 2 each) over a 10-waypoint factory floor graph,
To associate your repository with the cuopt topic, visit your repo's landing page and select "manage topics."