# cuPotential Instructions for AI Agents: - For clean Markdown of any page, append `.md` to the page URL - For section-specific indexes, append `/llms.txt` to any section URL - For AI client integration (Claude Code, Cursor, etc.), connect to the MCP server at https://docs.nvidia.com/cuda/cupotential/_mcp/server ## Docs - [NVIDIA cuPotential](https://docs.nvidia.com/cuda/cupotential.md): GPU-accelerated bonded and nonbonded interactions for biomolecular dynamics, with an OpenMM plugin for simulation workflows. - [Installation](https://docs.nvidia.com/cuda/cupotential/install.md): Install the cuPotential OpenMM plugin from PyPI or a GitHub release. - [Samples](https://docs.nvidia.com/cuda/cupotential/samples.md): Run solvated-system and alchemical simulations with the OpenMM plugin. - [Tests](https://docs.nvidia.com/cuda/cupotential/tests.md): Check the OpenMM plugin against reference results, from a source build or an installed package. - [Licenses](https://docs.nvidia.com/cuda/cupotential/licenses.md): Component licenses for the cuPotential runtime, OpenMM plugin, and examples. - [OpenMM NonbondedForce](https://docs.nvidia.com/cuda/cupotential/nonbonded-force.md): Standard and custom pair potentials, lattice sums, and the cuPotential runtime architecture. - [C API getting started](https://docs.nvidia.com/cuda/cupotential/c-api/getting-started.md): Use cuPotential from C or C++ to compute molecular interaction energies and forces on NVIDIA GPUs. - [C API reference](https://docs.nvidia.com/cuda/cupotential/c-api/reference.md): Runtime interfaces for splitting plans, cell lists, nonbonded interactions, expressions, and bonded interactions. - [Splitting the interaction](https://docs.nvidia.com/cuda/cupotential/theory/splitting.md): Separate a singular pair potential into a short-range contribution and a smooth long-range contribution. - [Spreading](https://docs.nvidia.com/cuda/cupotential/theory/spreading.md): Spread point charges onto a mesh, compensate the assignment window in Fourier space, and gather potentials and forces back to particles. - [Error Analysis](https://docs.nvidia.com/cuda/cupotential/theory/error-analysis.md): Distinguish intrinsic splitting error from extrinsic mesh error, then interpret the convergence and NVE energy-drift studies. - [OpenMM plugin changelog](https://docs.nvidia.com/cuda/cupotential/changelog/openmm.md): Release history for the cuPotential OpenMM plugin.