# openai/supervised-reptile

Code for the paper "On First-Order Meta-Learning Algorithms"

Repository: https://github.com/openai/supervised-reptile
Canonical: https://ross.abutalabs.com/products/supervised-reptile
Homepage: https://arxiv.org/abs/1803.02999
Language: JavaScript
License: MIT
License Family: permissive
Topics: paper
Archived: true
Last push: 2023-05-20T19:59:33+00:00

## Health v2 (maintenance only)
Score: 10/100 (v2, computed 2026-09-03T02:20:16.233290+00:00)
- activity 0, release rhythm 35, longevity 100
- inputs: {"age_days": 3193, "days_push": 1201, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: no_releases, archived
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 1044, forks 209 (observed 2026-08-28T04:03:21.267563+00:00)

## What it is
Official research code for the Reptile meta-learning algorithm from the paper 'On First-Order Meta-Learning Algorithms'. It trains and evaluates few-shot classification models on Omniglot and Mini-ImageNet benchmarks.

## Use cases
- reproduce Reptile few-shot classification results
- run meta-learning experiments on Omniglot
- train 1-shot and 5-way Mini-ImageNet models
- learn how first-order meta-learning works
- compare MAML-style algorithms on few-shot benchmarks
- download and prepare Omniglot and Mini-ImageNet datasets

## When to choose
- you want to reproduce or study the Reptile paper's experiments
- you need a reference implementation of first-order meta-learning
- you're doing research on few-shot classification benchmarks

## When to avoid
- you need a maintained, production-ready meta-learning library
- you want modern framework support or GPU ecosystem updates
- you need anything beyond Omniglot or Mini-ImageNet benchmarks

## Facets
- artifact type: library
- maturity: abandoned
- function: machine-learning, deep-learning
- domain: machine-learning, artificial-intelligence
- platform: python
- tags: meta-learning, reptile, few-shot-learning, research-code, omniglot, mini-imagenet, tensorflow, archived, research, linux, macos

## Member repositories
- openai/supervised-reptile (main) score 10

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:03:21.267563+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 2026-08-30T07:02:15.008110+00:00, confidence not recorded.
  - readme: https://github.com/openai/supervised-reptile (fetched 2026-08-28T04:03:21.267563+00:00, sha ddcee74e7dd6)
  - homepage: https://arxiv.org/abs/1803.02999 (fetched 2026-08-29T13:03:20.186737+00:00, sha dcf210c2090d)
  - site_page: https://info.arxiv.org/about/donate.html (fetched 2026-08-29T13:03:20.196203+00:00, sha cca9c3a11c56)
  - site_page: https://info.arxiv.org/about/ourmembers.html (fetched 2026-08-29T13:03:20.200543+00:00, sha 47cbc55ff1de)
  - site_page: https://info.arxiv.org/about (fetched 2026-08-29T13:03:20.202609+00:00, sha a1f16f915a9a)
  - site_page: https://info.arxiv.org/labs/index.html (fetched 2026-08-29T13:03:20.198366+00:00, sha b14a8d05a0ec)
- Data as of 2026-08-30T08:39:29.467469+00:00.