Skip to main content

CatGo — AI-driven workbench for computational materials science (3D viewer + workflow engine + MCP)

Project description

CatGo

AI-driven workbench for computational materials science — a 3D structure/trajectory viewer + workflow engine, installable straight from PyPI.

pip install catgo      # or:  uv pip install catgo
catgo                  # launches the app and opens it in your browser

Commands

Command What it does
catgo Start the backend and open the CatGo UI in a browser
catgo app / catgo web Same as bare catgo (--no-browser to skip opening one)
catgo view POSCAR CONTCAR … Open structure/trajectory file(s) in the viewer (like ase gui)
catgo serve Run the API/backend only (no browser)
catgo shell Interactive REPL
catgo setup Register the CatGo MCP server for Claude Code

The web UI is bundled in the wheel and served same-origin by the local backend (default http://localhost:8000), so it works offline after install.

Optional extras

pip install "catgo[analyze]"   # DOS/band/COHP plotting (matplotlib, scienceplots)
pip install "catgo[ml]"        # MACE ML potentials
pip install "catgo[full]"      # mdtraj, h5py, scikit-learn, custodian

Prefer the native desktop app (Tauri) for the fastest 3D — see the project repository. This package is the Python/CLI + web-UI distribution.

License: AGPL-3.0-or-later.

Project details


Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Source Distributions

No source distribution files available for this release.See tutorial on generating distribution archives.

Built Distribution

If you're not sure about the file name format, learn more about wheel file names.

catgo-1.4.5.post1-py3-none-any.whl (35.9 MB view details)

Uploaded Python 3

File details

Details for the file catgo-1.4.5.post1-py3-none-any.whl.

File metadata

  • Download URL: catgo-1.4.5.post1-py3-none-any.whl
  • Upload date:
  • Size: 35.9 MB
  • Tags: Python 3
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/6.1.0 CPython/3.13.12

File hashes

Hashes for catgo-1.4.5.post1-py3-none-any.whl
Algorithm Hash digest
SHA256 05851ac8f3a2add4f2f21c2ee021181415407550f24f8ba2bec03701c2443b1f
MD5 1326a050f762bc9f1a1c9fd44a9931dd
BLAKE2b-256 7944eb1ddf72a230f751f0a76f1e21af916820a7d0ca815bc4cd5ef9ed86d8ac

See more details on using hashes here.

Supported by

AWS Cloud computing and Security Sponsor Datadog Monitoring Depot Continuous Integration Fastly CDN Google Download Analytics Pingdom Monitoring Sentry Error logging StatusPage Status page