scitex 2.15.4

A comprehensive Python library for scientific computing and data analysis

scitex.ai · pip install scitex

---

Modular Python toolkit for scientific research automation — with verification features to ease peer review.

Empowers both human researchers and AI agents. Each module works independently and adapts to various academic workflows, handling primary and secondary research with real or simulated data.

🎬 Demo

40 min, zero human intervention — AI agent conducts full research pipeline:

Literature search → Data analysis → Statistics → Figures → 21-page manuscript → Peer review simulation

📦 Installation

uv pip install scitex[all]     # Recommended: Full installation
uv pip install scitex          # Core only

Three Interfaces

Interface	For	Description
🐍 Python API	Human researchers	import scitex as stx — 70% less code
🖥️ CLI Commands	Terminal users	scitex scholar fetch, scitex stats run
🔧 MCP Tools	AI agents	145 tools for Claude/GPT integration

🐍 Python API

@stx.session — Reproducible Experiment Tracking

import scitex as stx

@stx.session
def main(filename="demo.jpg"):
    fig, ax = stx.plt.subplots()
    ax.plot_line(t, signal)
    ax.set_xyt("Time (s)", "Amplitude", "Title")
    stx.io.save(fig, filename)
    return 0

Output:

script_out/FINISHED_SUCCESS/2025-01-08_12-30-00_AbC1/
├── demo.jpg                    # Figure with embedded metadata
├── demo.csv                    # Auto-exported plot data
├── CONFIGS/CONFIG.yaml         # Reproducible parameters
└── logs/{stdout,stderr}.log    # Execution logs

stx.io — Universal File I/O (30+ formats)

stx.io.save(df, "output.csv")
stx.io.save(fig, "output.jpg")
df = stx.io.load("output.csv")

stx.stats — Publication-Ready Statistics (23 tests)

result = stx.stats.test_ttest_ind(group1, group2, return_as="dataframe")
# Includes: p-value, effect size, CI, normality check, power

→ Full module status

🖥️ CLI Commands

scitex --help-recursive              # Show all commands
scitex scholar fetch "10.1038/..."   # Download paper by DOI
scitex scholar bibtex refs.bib       # Enrich BibTeX
scitex stats recommend               # Suggest statistical tests
scitex audio speak "Done"            # Text-to-speech
scitex capture snap                  # Screenshot

→ Full CLI reference

🔧 MCP Tools — 145 tools for AI Agents

Turn AI agents into autonomous scientific researchers.

Typical workflow: Scholar (find papers) → Stats (analyze) → Plt (visualize) → Writer (manuscript) → Capture (verify)

Category	Tools	Description
scholar	23	PDF download, metadata enrichment
stats	10	Automated statistical testing
plt	9	Matplotlib figure creation
capture	12	Screen monitoring and capture
audio	10	Text-to-speech, audio playback
introspect	11	Python introspection
diagram	7	Mermaid and flowchart creation
canvas	7	Scientific figure canvas
social	9	Social media posting
template	4	Project scaffolding
ui	5	Notifications
writer	1	LaTeX manuscript compilation

Claude Desktop (~/.config/claude/claude_desktop_config.json):

{
  "mcpServers": {
    "scitex": {
      "command": "scitex",
      "args": ["mcp", "start"]
    }
  }
}

→ Full MCP tool reference

🧩 Standalone Packages

SciTeX integrates several standalone packages that can be used independently:

Package	scitex Module	Description
figrecipe	scitex.plt	Publication-ready matplotlib figures
crossref-local	scitex.scholar.crossref_scitex	Local CrossRef database (167M+ papers)
socialia	scitex.social	Social media posting (Twitter, LinkedIn)
scitex-writer	scitex.writer	LaTeX manuscript compilation

Each package works standalone or as part of scitex:

pip install figrecipe        # Use independently
pip install scitex[plt]      # Or via scitex

📖 Documentation

• Read the Docs: Complete API reference
• Example Notebooks: 25+ Jupyter notebooks

🤝 Contributing

We welcome contributions! See CONTRIBUTING.md.

---

AGPL-3.0 · [e-mail]