Curie vs plexe
AI agents for scientific experiments and tabular ML compared
Curie and plexe are Python tools that use AI agents to automate research and machine-learning workflows. Curie focuses on running and reporting scientific experiments, while plexe focuses on building and packaging models from tabular data and a natural-language intent.
Curie: Automate Scientific Experiments with AI Agents
Curie is a Python framework that uses AI agents to plan, run, analyze, and report on scientific experiments. It suits researchers who want to automate exploratory or machine-learning work, but its inactive development and lack of recent releases warrant caution.
plexe: Build Machine Learning Models from Prompts
Plexe turns a natural-language description and tabular dataset into a trained, packaged machine learning model through a multi-agent workflow. It is aimed at developers and data teams who want to automate model selection and iteration while retaining control over configuration and deployment.
| Curie | plexe | |
|---|---|---|
| Language | Python | Python |
| License | Apache-2.0 | Apache-2.0 |
| Stars | 370 | 2.6k |
| Forks | 32 | 262 |
| Last analyzed | Oct 9, 2026 | Oct 3, 2026 |
Key differences
- Curie covers hypothesis formulation, experiment execution, analysis, and reporting across scientific discovery and system analysis; plexe focuses on searching, evaluating, and packaging tabular ML models.
- Curie accepts user datasets and starter code for experiments; plexe takes tabular datasets in Parquet, CSV, ORC, or Avro formats plus a natural-language modeling intent.
- Curie records experiment results and artifacts and generates reports; plexe packages trained artifacts, inference code, schemas, configuration, and evaluation reports for deployment.
- Curie requires Docker and configured model credentials; plexe requires LLM provider credentials and supports Docker images, YAML configuration, and a Streamlit dashboard.
- Both use Python and have an Apache-2.0 license. Their listed star counts are 370 for Curie and 2.6k for plexe.
- Curie is aimed at researchers and ML practitioners investigating questions with their own data or code; plexe is aimed at developers and data teams automating tabular model selection and iteration.
Choose Curie if you…
- want an agent to turn a research question into an experiment, analysis, and report.
- need to explore scientific or system behavior using your own dataset or starter code.
- want an automated first pass at an experiment, with human review of the results and conclusions.
Choose plexe if you…
- need to create a packaged model from a tabular dataset and a natural-language prediction goal.
- want to automate tabular model search and evaluation before refining the result.
- need configurable LLM routing or integration with custom storage, tracking, or deployment infrastructure.
Compare the numbers side by side, or add more projects
This comparison is generated with AI from the OSRepos analyses of both projects. Always check each project's repository and documentation before choosing.