# microsoft/ELL

Embedded Learning Library

Repository: https://github.com/microsoft/ELL
Canonical: https://ross.abutalabs.com/products/microsoft-ell
Homepage: https://microsoft.github.io/ELL
Language: C++
License: NOASSERTION
License Family: other
Archived: true
Last push: 2024-06-01T16:49:37+00:00

## Health v2 (maintenance only)
Score: 10/100 (v2, computed 2026-09-03T02:20:16.233290+00:00)
- activity 0, release rhythm 8, longevity 100
- inputs: {"age_days": 3627, "days_push": 823, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: archived, no_license
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 2302, forks 291 (observed 2026-08-28T04:06:35.547250+00:00)

## What it is
ELL (Embedded Learning Library) is a C++ library and toolset from Microsoft Research for designing and deploying machine-learned models onto resource-constrained devices like Raspberry Pi, Arduino, and micro:bit. It acts like a cross-compiler for embedded intelligence, letting models run locally without cloud or network connectivity.

## Use cases
- run machine learning models on a raspberry pi without internet
- deploy image classification to arduino or micro:bit
- build offline AI-powered gadgets and embedded devices
- compile trained models for resource-constrained hardware
- run inference locally on single-board computers
- embed computer vision models in maker projects

## When to choose
- you need ML inference on small embedded or single-board hardware with no network
- you want models to run fully offline without cloud servers
- you're building maker or IoT projects in C++ or Python on Raspberry Pi-class devices

## When to avoid
- you need a actively developed framework with frequent updates and modern model support
- you target servers, GPUs, or cloud inference rather than embedded devices
- you need stable APIs - ELL is an early preview with breaking changes
- you primarily work in Python with PyTorch/TensorFlow deployment pipelines

## Facets
- artifact type: library
- maturity: maintenance
- function: machine-learning, deep-learning, compiler, sdk
- domain: machine-learning, embedded-systems, iot, artificial-intelligence
- platform: cpp, python, windows, embedded, iot, cross-platform
- tags: embedded-ai, single-board-computers, raspberry-pi, arduino, edge-deployment, microsoft-research, offline-inference, linux, macos

## Member repositories
- microsoft/ELL (main) score 10

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:06:35.547250+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 2026-08-30T02:40:10.060373+00:00, confidence not recorded.
  - readme: https://github.com/microsoft/ELL (fetched 2026-08-28T04:06:35.547250+00:00, sha e3e499648a2a)
  - homepage: https://microsoft.github.io/ELL (fetched 2026-08-29T10:20:17.432981+00:00, sha 6adc1e20d7c2)
- Data as of 2026-08-30T08:39:29.467469+00:00.