Analysis updated 2026-05-18
Let an AI agent run Stata regressions and read results as structured JSON.
Speed up repeated Stata commands during a research session using daemon mode.
Run .do files, view datasets, and export graphs from a terminal instead of Stata's GUI.
| ashuigordon/stata-cli | hsy23/clif-co-orchestrating-llm-inference-serving-and-fine-tuning. | ant-research/memdreamer | |
|---|---|---|---|
| Stars | 41 | 41 | 42 |
| Language | Python | Python | Python |
| Setup difficulty | moderate | hard | hard |
| Complexity | 3/5 | 5/5 | 5/5 |
| Audience | researcher | researcher | researcher |
Figures from each repo's GitHub metadata at analysis time.
Requires an existing licensed Stata 17+ installation, the tool itself does not include Stata.
stata-cli is a command line tool that lets you run Stata, a statistics and econometrics program, from a terminal instead of its usual graphical interface. It works through PyStata, Stata's official Python library, and is designed for both human users and AI agents that need to call Stata programmatically. You can run Stata code directly, execute whole .do script files, view the current dataset, browse Stata's built in help topics, and export graphs, all through simple commands. A key feature is its daemon mode, which keeps Stata running in the background so each command executes in well under a tenth of a second, compared to two or three seconds when starting Stata fresh each time. This matters most for AI agents issuing many small commands in a row. The tool also returns results in structured JSON format on request, which makes it easier for an AI agent or another program to read the output automatically, and it ships with a SKILL.md file so agent tools like Claude can use it with no extra setup. Beyond running code, stata-cli can retrieve stored statistical results after commands like regress or summarize, read Stata matrices, inspect variable metadata and value labels, get or set Stata macros, and list Stata frames, the tool's term for multiple datasets held in memory at once. To use it you need Stata 17 or newer already installed and licensed on your machine, along with Python 3.9 or newer. It installs with a single pip or npm command, and after installing you first run a detect command to confirm your Stata installation is found, then start the daemon before running commands. It is released under the MIT license, and the project also ships a Chinese language translation of its documentation.
A command line wrapper around Stata that lets humans and AI agents run statistical commands fast, with structured JSON output.
Mainly Python. The stack also includes Python, PyStata, Stata.
Use freely for any purpose, including commercial use, as long as you keep the copyright notice.
Setup difficulty is rated moderate, with roughly 30min to a first successful run.
Mainly researcher.
This repo across BitVibe Labs
Verify against the repo before relying on details.