# huggingface/ml-intern

🤗 ml-intern: an open-source ML engineer that reads papers, trains models, and ships ML models

Repository: https://github.com/huggingface/ml-intern
Canonical: https://ross.abutalabs.com/products/ml-intern
Language: Python
License: Apache-2.0
License Family: permissive
Last push: 2026-07-30T22:54:26+00:00

## Health v2 (maintenance only)
Score: 59/100 (v2, computed 2026-09-03T02:20:16.233290+00:00)
- activity 95, release rhythm 35, longevity 21
- inputs: {"age_days": 307, "days_push": 34, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: no_releases
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 10753, forks 1172 (observed 2026-08-28T04:10:44.099038+00:00)

## What it is
An open-source autonomous ML engineer agent from Hugging Face that reads papers, writes code, trains models, and ships ML work using the Hugging Face ecosystem. It runs as an interactive or headless CLI, powered by LLMs via HF Inference Providers or local OpenAI-compatible endpoints.

## Use cases
- autonomously fine-tune an LLM on my dataset
- agent that reads ML papers and implements them
- train and ship models using the Hugging Face ecosystem
- CLI coding agent for machine learning tasks
- run an AI agent on local models via ollama or vllm
- automate ML research and experimentation

## When to choose
- you want an autonomous agent for end-to-end ML workflows within the Hugging Face ecosystem
- you want both hosted and local model support in one CLI
- you need a headless agent for scripted ML tasks

## When to avoid
- you need a general-purpose coding agent outside ML domains
- you cannot provide an HF token and have no local inference server
- you want a GUI-based ML tool

## Facets
- artifact type: cli-tool
- maturity: active
- function: agent-framework, llm-inference, cli, machine-learning, chatbot
- domain: artificial-intelligence, machine-learning, developer-tools, large-language-models
- platform: python, cli, cross-platform
- tags: hugging-face, autonomous-agent, coding-agent, fine-tuning, litellm, research-agent, ai-agents

## Member repositories
- huggingface/ml-intern (main) score 59

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:10:44.099038+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 2026-08-29T17:17:54.605752+00:00, confidence not recorded.
  - readme: https://github.com/huggingface/ml-intern (fetched 2026-08-28T04:10:44.099038+00:00, sha 7aaaf977872f)
- Data as of 2026-08-30T08:39:29.467469+00:00.