# plexe-ai/plexe

✨ Build a machine learning model from a prompt

Repository: https://github.com/plexe-ai/plexe
Canonical: https://ross.abutalabs.com/products/plexe
Homepage: https://plexe.ai
Language: Python
License: Apache-2.0
License Family: permissive
Topics: agentic-ai, agents, machine-learning, ml, mlengineering, mlops, multiagent, ai
Last push: 2026-03-06T11:41:05+00:00

## Health v2 (maintenance only)
Score: 61/100 (v2, computed 2026-09-03T02:39:23.370411+00:00)
- activity 70, release rhythm 61, longevity 43
- inputs: {"age_days": 605, "days_push": 180, "days_rel": 180, "gap_med": 0.0, "n_releases_24m": 71}
- flags: none
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 2614, forks 255 (observed 2026-08-28T04:07:04.547394+00:00)

## What it is
Plexe is a Python library and CLI that builds machine learning models from natural language descriptions using a multi-agent AI workflow. You provide a tabular dataset and an intent, and it autonomously selects metrics, searches for models, and packages a deployable model artifact.

## Use cases
- build an ml model from a prompt
- automate model training on tabular data
- predict outcomes from a csv dataset without writing ml code
- auto-select the best model architecture for my dataset
- generate a deployable model package from natural language intent
- run automated ml experiments with ai agents

## When to choose
- you want to build tabular ML models without manual feature engineering or model selection
- you have a labeled dataset and can describe the prediction task in plain language
- you want a self-contained model package deployable without plexe dependencies

## When to avoid
- you need fine-grained manual control over every training step
- your data is unstructured text, images, or audio rather than tabular
- you cannot share data with an LLM-backed agentic pipeline or lack API keys for OpenAI/Anthropic

## Facets
- artifact type: library
- maturity: active
- function: machine-learning, agent-framework, llm-training, cli, sdk
- domain: machine-learning, artificial-intelligence, data-science, developer-tools
- platform: python, cli, cross-platform
- tags: agentic-ai, multi-agent, automl, tabular-data, mlops, natural-language, model-building, xgboost, pytorch, ai-agents

## Member repositories
- plexe-ai/plexe (main) score 61

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:07:04.547394+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-30T02:20:34.753795+00:00, confidence not recorded.
  - readme: https://github.com/plexe-ai/plexe (fetched 2026-08-28T04:07:04.547394+00:00, sha a66956e56875)
  - homepage: https://plexe.ai (fetched 2026-08-29T10:03:28.009580+00:00, sha 6da557cfeb0c)
  - registry_pypi: https://pypi.org/pypi/plexe/json (fetched 2026-08-29T10:03:28.012371+00:00, sha f2474835b2b3)
- Data as of 2026-08-30T08:39:29.467469+00:00.