CatGo — AI Workbench for Computational Materials Science
One desktop workbench that unifies structure building, input generation, HPC job submission and results analysis for computational chemistry — driven by natural language.
- Source repo
- Hello-QM/catgo-LRG
- Stars
- ★ 209
- Last updated
- 29d ago
- License
- AGPL-3.0
- Primary language
- TypeScript
- FA score
- 64/100 · Some gaps
At a glance
- How it runs
- Works with
- Universal · cross-platformClaude CodeCodex (Partial support)
- Cost
- Free, no paid service needed
- Setup effort
- Low · running in minutes
- You'll need
- Typical use
- A catalysis researcher who needs to fetch a Cu structure from Materials Project, cut a four-layer (111) slab, add 15 Å of vacuum, place O at a hollow site, and generate an ORCA input
- Not a fit if
- Teams expecting the latest 1.5.0+ source in this repo (newer releases ship as installers only)
- Users without their own cluster or licensed codes who want to run VASP/CP2K out of the box
- Users needing only lightweight structure viewing with no backend workflows or HPC
- Maintenance
- Commits in the last 30 dayslast commit 2026-10-22latest release v1.4.14 (2026-08-25)
- Source review
- 64/100 · Some gaps
What does this agent do, and when should you use it?
CatGo is an AI workbench for computational materials science and chemistry, open-sourced at Hello-QM/catgo-LRG under AGPL-3.0. It brings an interactive 3D structure editor, the natural-language CatBot assistant, a visual DAG workflow engine, and remote HPC cluster access into a single workspace, built as a Tauri desktop app with a SvelteKit frontend and a FastAPI Python backend. It generates inputs and parses results for VASP, ORCA, CP2K, Quantum ESPRESSO, GPAW, DFTB+, SIESTA and LAMMPS, but bundles no commercial simulation codes — you supply the licensed software and compute. Entry points span Windows/macOS/Linux desktop installers, a static web app, a VS Code extension, iOS/Android mobile builds, the catgo CLI, and an MCP server. Note that open-source releases stop at 1.4.x; versions 1.5.0 and later ship only as installers from the official download center, with source not published in this repository.
CatGo reads dozens of structure and output formats — CIF, POSCAR, OUTCAR, vasprun.xml, CHGCAR, XYZ, LAMMPS dump, Gaussian cube and more — and lets you rotate, measure, and atom-edit crystals, molecules, surfaces and trajectories in its 3D viewer. It fetches structures from Materials Project and other database APIs, builds supercells and Miller-index slabs with vacuum, places adsorbates, and prepares defects, dopants, heterostructures and MOFs. It generates and exports inputs for ORCA, VASP, CP2K, Quantum ESPRESSO, ABACUS, Gaussian and LAMMPS, and connects optimization, single-point, frequency, DOS, NEB and MD steps via Quick Build recipes or a visual DAG. Through SSH it connects to your own cluster to browse remote files, submit scheduler jobs, and follow logs and convergence. CatBot performs structure retrieval, model construction, workflow editing and file analysis in natural language with visible tool calls. Analysis covers DOS/PDOS, bands, COHP/ICOHP, d-band centers, XRD, RDF, charge-density isosurfaces, free-energy diagrams and volcano plots, with export to figures, videos, CSV and 3D models.
- A catalysis researcher who needs to fetch a Cu structure from Materials Project, cut a four-layer (111) slab, add 15 Å of vacuum, place O at a hollow site, and generate an ORCA input
- A DFT user who wants a one-click VASP relaxation → static → DOS workflow for the current structure, with human review of inputs before submission
- A graduate student checking SLURM job status and browsing remote structure files over SSH from an iPhone or iPad
- A developer working in VS Code/Cursor who wants to view and export structures and trajectories directly in the editor
- A team automating file-first computational campaigns through MCP and the CLI with Claude Code, Codex or Gemini
- A researcher organizing OER/HER/ORR/CO₂RR/NRR adsorption energies, ZPE and thermal corrections, and plotting free-energy diagrams and volcano plots
Key setup facts
Pulled from the install and usage notes below. The project README has the current values.
- Install / run
pip install catgopip install catgo -i https://pypi.tuna.tsinghua.edu.cn/simple
- Runtime
- Node.js 20+ · Python 3.11
- Install notes cover
- Windows · macOS · Linux
How do you install or deploy this agent?
Fastest trial — open the web app (no install):
https://app.catgo-ucsd.orgFull experience — download installers from the official download center (1.5.0+ are installer-only; open-source releases stop at 1.4.x):
https://dl.catgo-ucsd.org/Windows ships CatGo_<ver>_x64-setup.exe/.msi, macOS (Apple Silicon) .dmg, Linux .deb/.rpm. Alternatively install the pip package, which bundles the full web UI:
bash
pip install catgo
# or: uv tool install catgoVS Code users can search CatGo in the Extensions marketplace; iOS users can join the public TestFlight beta at testflight.apple.com/join/FdHup5Hz. Mainland-China fallback via a PyPI mirror:
bash
pip install catgo -i https://pypi.tuna.tsinghua.edu.cn/simpleBuilding the open-source 1.4.x from source requires Node.js 20+, pnpm, Python 3.11, the Rust toolchain, and wasm-pack.
How do you use this agent?
After the pip install, launch and configure with:
bash
catgo # launch the app
catgo setup # register the MCP server and Claude Code skills
catgo serve
catgo status
catgo --helpDesktop flow: launch CatGo and drop in a structure/output file or fetch one from a database; prepare the model with the structure toolbar, Quick Build, or CatBot; connect your lab's cluster from the HPC panel via SSH; review generated inputs and scheduler settings before approving submission; then monitor the workflow and continue to analysis. Prompts you can send CatBot directly:
text
Fetch Cu from Materials Project, cut a four-layer (111) slab,
add 15 Å of vacuum, and place O at a hollow site.
text
Create a VASP relaxation → static → DOS workflow for the current structure.
Let me review the inputs first; do not submit it yet.
Before your first cluster submission, confirm cluster identity, scheduler, executable or module commands, Python environment, and POTCAR/pseudopotential locations.
What are this agent's strengths and limitations?
- Covers the full chain — structure building → input generation → HPC submission → post-processing — replacing the juggle between a structure builder, terminal, SSH client and plotting scripts
- Complete cross-platform coverage: desktop, web, VS Code extension, iOS (with a native Rust SSH transport), Android, CLI/MCP, with a purpose-built mobile interface rather than a compressed desktop layout
- CatBot tool calls remain visible and workflows include explicit human review gates, keeping researchers responsible for settings and conclusions
- Very broad read/write format support across VASP/CP2K/ORCA/QE/ABACUS/LAMMPS plus built-in catalysis analysis for free-energy diagrams and volcano plots
- Versions 1.5.0+ are closed-source and installer-only; GitHub Releases cover only 1.4.x, so the repo does not publish the latest application
- No commercial codes or pseudopotentials are bundled — VASP/CP2K etc. require your own licences, installations and cluster environment, and cluster configuration must be manually verified before first submission
- HPC paths (VASP, CP2K, xTB, etc.) go through a Python SSH adapter with simpler retry/resume behavior than the local DAG engine; QE, Gaussian and GROMACS are export-only with no executable workflow nodes
- The backend has no built-in authentication layer — a self-deployed web backend must stay on loopback or a controlled private network and must never face the public internet
How does this agent compare with similar options?
CatGo's 3D structure viewer, periodic table, and parts of its core UI originate from MatterViz by Janosh Riebesell and have been substantially reworked; on that foundation CatGo adds the catalysis pipeline, workflow engine, HPC integration, CatBot and a plugin system. Its CatRender is a Rust/WASM port of aligfellow/xyzrender (lineage includes xyz2svg).
Key facts side by side with the most closely related agents.
| Agent | Source review | Form / cost | Stars | Updated | Language | Full support on |
|---|---|---|---|---|---|---|
| CatGo — AI Workbench for Computational Materials Science This agent | 64 · Some gaps | Desktop appFree | ★ 209 | 29d ago | TypeScript | Claude Code |
| NeuroSkill — Local-First EXG/BCI Neurofeedback Workbench | 57 · Major gaps | Desktop appFree | ★ 107 | 4d ago | Rust | — |
| EvoScientist: Self-Evolving AI Scientist | 69 · Some gaps | CLIFree + model costs | ★ 5k | today | Python | OpenAI API · Claude API |
| Metaflow | 60 · Some gaps | Library / SDKFree | ★ 10k | 4d ago | Python | — |
How does FollowAgents rate this agent?
Why each dimension lost points
AGENTS.md and the README require review and confirmation before submission, and the README says tool calls remain visible. Configuration docs describe OS-keychain storage for API keys and warn that a self-hosted backend has no built-in authentication, recommending loopback or a controlled private network. HPC, terminal, plugin, and external-agent capabilities can have significant effects, but the excerpts do not adequately show permission scopes, detailed data flows, key-protection implementation, or rollback mechanisms, so these criteria do not receive full marks. The README credits MatterViz; publisher identity is unknown and does not affect the score.
The materials provide a mostly understandable product description, but workflow execution paths are not fully consistent: the README distinguishes local Rust from Python HPC, the student guide gives a similar split, and the FAQ describes workflows more generally as cluster-oriented. Installation and configuration docs identify Python, Node, external programs, and HPC requirements, but provide limited evidence about dependency availability and version guarantees. The FAQ and student guide give concrete causes and troubleshooting steps, supporting a good but not comprehensive failure-message score.
The intended audience, research tasks, and desktop, Web, VS Code, mobile, and CLI/MCP scenarios are described concretely. The README and guides distinguish input export, skill guidance, and executable workflows, and identify platform limitations. Skills use descriptions and trigger scenarios to define applicability, though the sample cannot establish consistent trigger boundaries across all skills. Environment fit covers multiple platforms and HPC configuration while listing external software, keys, and system dependencies; the excerpts do not establish complete coverage across environments.
Documentation is organized across installation, configuration, FAQ, and development guidance, with many examples; the installation guide includes steps and troubleshooting. Naming varies between CatGo/CatGO and across entry points, and the README says releases after 1.5.0 are closed source while this repository stops at 1.4.x, weakening evidence for naming stability and the update path. The AGPL-3.0-or-later declaration and license text are present. Version guidance is clear in the README, but the excerpts do not show a complete changelog; maintenance responsibility and maintainer identity are also unclear.
Examples show actionable structure-building, workflow, and analysis tasks, including a path to review generated inputs. Integrating structure operations, workflows, HPC, and analysis into one research workbench offers clear potential value. Cost-benefit depends on optional dependencies, compute resources, external software licenses, and differences among platform editions; the materials do not quantify those costs or demonstrate end-to-end outputs.
The README, configuration docs, skills, and code excerpts support some feature and configuration claims, with FAQ and guides providing corroboration. Some capabilities remain documented assertions, and workflow-path and capability descriptions are inconsistent; omitted files and runtime evidence are not treated as evidence. The docs distinguish implemented, experimental, unavailable, and guidance-only capabilities in several places and assign scientific judgment to researchers, but demos and product claims are not independent verification.
- The self-hosted backend has no built-in authentication; do not expose it directly to the public internet.
- Before submitting HPC jobs, verify cluster identity, scheduler, software paths, pseudopotential or basis paths, and input settings. The docs say some HPC paths have simpler retry and resume behavior.
- Installers for 1.5.0 and later are not represented by open-source source code in this repository; do not confuse the repository version with the current application version.
Recent releases
Latest entries from the project's GitHub Releases. Notes are quoted from upstream as written, not rewritten or tested by FollowAgents.
-
v1.4.14 CatGo v1.4.14
Release notes excerpt
CatGo 1.4.14 CatGo 1.4.14 is the completed cross-platform reliability release for CatBot, Campaigns, scientific workflows, large trajectories, and the integrated terminal. It supersedes the unpublished 1.4.10–1.4.13 drafts and includes a Windows UTF-8 correction found by the packaged-runtime release smoke test. Highlights - Installed CatBot is complete on Windows, macOS, and Linux — Claude, Codex, and Gemini discovery, attachments, voice, Skills, CatGo MCP tools, structures, workflows, and Campaigns are exercised from packaged backends. …View on GitHub ↗ -
v1.4.9 CatGo v1.4.9
Release notes excerpt
CatGo 1.4.9 CatGo 1.4.9 makes large trajectory work fast and editable across the web app, desktop app, VS Code, and Antigravity. It also adds physics-aware verification for CatBot numerical results, per-pane structure-toolbar customization, and a periodic-aware JavaScript bond fallback for frontend-only sessions. Highlights - Fast trajectories on every CatGo surface — indexed structure-only streaming avoids eagerly loading full multi-frame files and keeps the same trajectory behavior across browser, desktop, VS Code, and Antigravity. …View on GitHub ↗ -
v1.4.8 CatGo v1.4.8
Release notes excerpt
CatGo 1.4.8 CatGo 1.4.8 restores database search and completes the shared WebGL/WebGPU rendering work for periodic structures. Standard rendering and Large System Performance Mode now use the same authoritative atom, bond, boundary, camera, and visual-state data while retaining the WebGPU fast path for large structures. Highlights - Consistent periodic structures in both rendering modes — standard WebGL and Large System Performance Mode now agree on atom positions, bond geometry, periodic boundary images, lattice vectors, colors, radii, shading, camera …View on GitHub ↗
FAQ
Can CatGo run VASP calculations for me out of the box?
Does using CatGo cost money?
Can I use it without installing the desktop app?
How do external AI agents integrate with CatGo?
catgo setup, which registers the MCP server and campaign skills for Claude Code; Codex, Gemini and other agents can use the same MCP endpoints and skills after manual configuration.What is the status of the iOS and Android builds?
Is CatGo — AI Workbench for Computational Materials Science open source?
Is CatGo — AI Workbench for Computational Materials Science safe to use?
Is CatGo — AI Workbench for Computational Materials Science still maintained?
Who makes CatGo — AI Workbench for Computational Materials Science?
Thanks — we use this to improve the page.