dsh-cae-plugin
Run the following command in DeepSeek Harness:
dsh plugin install DaiYuhangSustc/dsh-cae-plugin
Paste the following prompt into your AI chat to install this plugin:
In DeepSeek Harness, install this plugin using the command dsh plugin install https://github.com/DaiYuhangSustc/dsh-cae-plugin.git.
About this plugin
Traditional Computer-Aided Engineering workflows are notoriously complex and fragmented, often requiring engineers to manually shuttle data between specialized software for geometry, meshing, solving, and post-processing—a time-consuming process that demands deep expertise in each tool. This plugin fundamentally reimagines the paradigm by transforming the entire simulation chain into a conversational, natural-language interface. As an agent-workflow plugin for DeepSeek Harness, it interprets plain-text requests like 'a square duct, 20x20 mm, 1 m long, water at 0.02 m/s inlet — steady laminar solve and a pressure contour' and autonomously orchestrates the full pipeline: geometry construction (build123d), tetrahedral meshing (Gmsh), physics solving (CalculiX for structures, OpenFOAM for fluids), and result visualization (PyVista). Its core strength is enabling natural-language-driven CAE, allowing users to focus on the engineering problem at hand rather than software mechanics. It is ideally suited for researchers, students, and engineers seeking rapid structural or internal flow analysis, offering a dramatically lowered barrier to entry and operational cost for simulation tasks.
Screenshots
Use Cases
- Verify the structural response of a cantilever beam under load with a single sentence command.
- Students input duct dimensions and fluid parameters to obtain laminar flow analysis results.
- Engineers perform rapid preliminary simulation assessments during the conceptual design phase.
Best For
- Engineers needing quick preliminary structural or fluid analysis.
- Researchers and students learning CAE methods who want to focus on engineering problems rather than software operations.
- Teams seeking low-cost, high-efficiency simulation for prototype validation.
Related Plugins
A method pack that makes AI coding agents plan against your real baseline, prove completion with fresh evidence, and reduce reworks and unsafe changes.
Turns the DeepSeek Harness session into a captain that builds a durable sub-agent team, splits goals into dependency-aware tasks, and coordinates work via direct messages and a live Web UI.
Gives coding agents design judgment, letting Claude Code, Cursor, and 70+ agents generate and iterate high-quality UI, presentations, and graphics right from the terminal.
Run the Pi ecosystem's plugins on DeepSeek Harness, unmodified, via a compatibility layer that implements Pi's public extension ABI on DSH's native services.