Vibe Coding Discover

AI Tools

StatsPAI

View on GitHub

StatsPAI is the first Agent-native Python library for causal inference and applied econometrics — unified API, broad cross-method coverage, structured result objects, machine-readable schemas, Skills, an MCP server, and R/Stata parity validation.

★ 32267 forksPythonMITbrycewang-stanford

Agent-native Python library for causal inference and applied econometrics, offering a unified Stata/R-style API, machine-readable function schemas, a bundled MCP server, and Skills for LLM agents. Covers DiD, IV, RD, synthetic control, matching, DML, and panel models with R/Stata parity checks.

Use Cases

run Stata/R-style econometric regressions in Pythonestimate difference-in-differences with Callaway-Sant'Annadouble machine learning for causal effectsinstrumental variable and 2SLS estimationregression discontinuity designssynthetic control and matching/PSMexpose causal estimators to LLM agents via MCP servergenerate machine-readable function schemas for agentsexport publication-ready LaTeX/DOCX tablescross-check Python results against R and Statarun Stata command lines through a Python APIagent-driven empirical research workflows with skills

Built With

Language
Python
Frameworks
numpy · pandas · scipy · statsmodels · linearmodels · scikit-learn · numba · patsy · PyMC · ArviZ · PyTorch · JAX · pyfixest · geopandas

Tags

agent-native · mcp · causal-inference · econometrics · statistics · skills · python · difference-in-differences · instrumental-variables · panel-data · double-machine-learning · synthetic-control · regression-discontinuity · treatment-effects · stata · rstats