# callous-youth/BOAT

A Compositional Operation Toolbox for Gradient-based Bi-Level Optimization

Repository: https://github.com/callous-youth/BOAT
Canonical: https://ross.abutalabs.com/products/boat
Homepage: https://boat.readthedocs.io/en/latest/
Language: Python
License: MIT
License Family: permissive
Last push: 2026-08-15T10:38:03+00:00

## Health v2 (maintenance only)
Score: 87/100 (v2, computed 2026-09-03T02:20:16.233290+00:00)
- activity 97, release rhythm 98, longevity 46
- inputs: {"age_days": 645, "days_push": 18, "days_rel": 18, "gap_med": 0, "n_releases_24m": 6}
- flags: none
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 1143, forks 159 (observed 2026-08-28T04:03:45.012054+00:00)

## What it is
BOAT is a PyTorch-based library providing a compositional, operation-level toolbox for gradient-based bi-level optimization (BLO). It decomposes BLO workflows into 19 atomic gradient operations that can be automatically composed into over 85 solver variants.

## Use cases
- implement bi-level optimization algorithms in PyTorch
- compose custom gradient-based BLO solvers from atomic operations
- run meta-learning experiments with bi-level optimization
- solve hyperparameter optimization via gradient-based BLO
- compare different bi-level optimization solver variants
- prototype new bi-level optimization methods without writing solvers from scratch

## When to choose
- you need flexible, composable bi-level optimization primitives rather than fixed solver routines
- you work in PyTorch and want a research-oriented BLO framework with many solver variants
- you want to experiment with or extend gradient-based bi-level optimization algorithms

## When to avoid
- you need a simple hyperparameter tuning tool rather than a research BLO framework
- your project does not use PyTorch or one of the supported alternative backends (Jittor, MindSpore)
- you need production-ready, turnkey AutoML rather than low-level optimization building blocks

## Facets
- artifact type: library
- maturity: active
- function: machine-learning, sdk, developer-tools
- domain: machine-learning, deep-learning
- platform: python, cross-platform
- tags: bi-level-optimization, pytorch, hyperparameter-optimization, meta-learning, gradient-based-optimization, compositional-operations, optimization, algorithms, research

## Member repositories
- callous-youth/BOAT (main) score 87

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:03:45.012054+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 2026-08-30T06:34:55.059394+00:00, confidence not recorded.
  - readme: https://github.com/callous-youth/BOAT (fetched 2026-08-28T04:03:45.012054+00:00, sha 3d1a15cb7e95)
- Data as of 2026-08-30T08:39:29.467469+00:00.