# MLSysOps/MLE-agent

🤖 MLE-Agent: Your intelligent companion for seamless AI engineering and research. 🔍 Integrate with arxiv and paper with code to provide better code/research plans 🧰 OpenAI, Anthropic, Gemini, Ollama, etc supported. :fireworks: Code RAG

Repository: https://github.com/MLSysOps/MLE-agent
Canonical: https://ross.abutalabs.com/products/mle-agent
Language: Python
License: MIT
License Family: permissive
Topics: agent, ai, llm, ml, mle, mlops
Last push: 2026-07-10T19:42:42+00:00

## Health v2 (maintenance only)
Score: 67/100 (v2, computed 2026-09-03T02:20:16.233290+00:00)
- activity 91, release rhythm 40, longevity 62
- inputs: {"age_days": 869, "days_push": 54, "days_rel": 690, "gap_med": 29, "n_releases_24m": 2}
- flags: none
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 1568, forks 108 (observed 2026-08-28T04:05:05.053581+00:00)

## What it is
MLE-Agent is an LLM-powered CLI agent that acts as a pairing assistant for machine learning engineers and researchers. It automates ML task workflows such as building baselines, competing in Kaggle competitions, debugging code, and integrating research from Arxiv and Papers with Code.

## Use cases
- automatically build ML baselines from my requirements
- enter a Kaggle competition and have an agent complete it end-to-end
- find state-of-the-art methods from arxiv and papers with code for my task
- debug my ML training code automatically
- chat with an AI assistant about my ML project from the terminal
- generate weekly reports of my ML work
- integrate MLOps tools into my ML workflow

## When to choose
- you are an ML engineer or researcher wanting an LLM agent to automate ML pipelines
- you want autonomous Kaggle competition participation
- you need research-grounded code generation with arxiv and Papers with Code integration
- you want a terminal-based interactive AI assistant for ML projects

## When to avoid
- you need a general-purpose coding agent outside the ML domain
- you require a GUI-based ML platform rather than a CLI tool
- you need production ML pipeline orchestration rather than agent-assisted development
- your project cannot use external LLM APIs or local models via Ollama

## Facets
- artifact type: cli-tool
- maturity: active
- function: agent-framework, llm-inference, rag, cli, chatbot, machine-learning
- domain: machine-learning, artificial-intelligence, large-language-models, developer-tools
- platform: python, cli, cross-platform
- tags: mlops, kaggle, arxiv, papers-with-code, llm-agent, code-generation, research-assistant, ai-agents

## Member repositories
- MLSysOps/MLE-agent (main) score 67

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:05:05.053581+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 2026-08-30T03:58:56.272864+00:00, confidence not recorded.
  - readme: https://github.com/MLSysOps/MLE-agent (fetched 2026-08-28T04:05:05.053581+00:00, sha 0b07c4f23db3)
  - registry_pypi: https://pypi.org/pypi/mle-agent/json (fetched 2026-08-29T11:28:40.505130+00:00, sha 883ba3b80bdf)
- Data as of 2026-08-30T08:39:29.467469+00:00.