dsh-diffgeom
Run the following command in DeepSeek Harness:
dsh plugin install hatter123/dsh-diffgeom
Paste the following prompt into your AI chat to install this plugin:
Run dsh plugin install hatter123/dsh-diffgeom in the DeepSeek Harness terminal to install this plugin; the full source code is available at https://github.com/hatter123/dsh-diffgeom .
About this plugin
Symbolic differential-geometry computation typically means manually importing SymPy submodules, layering manifolds and coordinate systems, and only then writing the first tensor expression. dsh-diffgeom turns SymPy.diffgeom into a ready-to-use tool inside DeepSeek Harness: write coordinate-free differential-geometry code, run it, and get the symbolic result back without environment setup or context switching.
The plugin covers the full toolkit: manifolds, patches, and coordinate systems; abstract scalar and tensor fields; the exterior derivative d; the wedge product; the Lie derivative; and the derivation chain from covariant derivative through Christoffel symbols to Riemann and Ricci tensor components. Preloaded 2-D and 3-D Euclidean manifolds come with basis 1-forms, basis vectors, and the metric already wired up, so you can start writing expressions immediately.
It is built for graduate students and engineers working in general relativity, differential geometry, or tensor calculus who need to verify a curvature computation, run a symbolic derivation for a paper, or prototype a geometric invariant without leaving the Harness conversation. A few lines of Python, one run, and the result is on screen.
Use Cases
- Verifying Riemann and Ricci tensor derivations in a general-relativity course
- Computing Christoffel symbols and simplifying curvature components for a physics paper
- Working through Lie derivatives and exterior derivatives directly inside a Harness conversation without switching to Jupyter
Best For
- Graduate students in general relativity and differential geometry
- Physics and math researchers who need symbolic curvature derivations for a paper
- Engineers prototyping geometric invariants through tensor calculus inside Harness
Related Plugins
A unified suite combining hot runtime injection, task-aware thinking-mode routing, and a graded session protocol with red-team gates to sustain model diligence across long-horizon inference.
ModLens is a vision plugin for DeepSeek Harness that gives text-only models sight by reading images pasted directly into chat, with zero-config setup and multiple vision engines.
On-demand vision for text-only DeepSeek Harness agents: built-in free keyless vision chain and 14 vision tools, routing image turns as tool calls to vision models with pixel fidelity, no Python needed, one-command install.
Give text-only models in DeepSeek Harness eyes, enabling image Q&A, long-screenshot OCR, UI restoration, and GUI visual tasks.