# mit-han-lab/tinyml

Repository: https://github.com/mit-han-lab/tinyml
Canonical: https://ross.abutalabs.com/products/tinyml
Language: Python
License: MIT
License Family: permissive
Last push: 2023-11-29T04:22:13+00:00

## Health v2 (maintenance only)
Score: 32/100 (v2, computed 2026-09-02T17:46:02.011165+00:00)
- activity 0, release rhythm 35, longevity 100
- inputs: {"age_days": 2091, "days_push": 1008, "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 1211, forks 168 (observed 2026-08-28T04:04:00.128354+00:00)

## What it is
MIT Han Lab's TinyML research repository containing projects like TinyTL and NetAug for memory-efficient deep learning on microcontrollers and IoT devices. It hosts code for on-device learning and training techniques for tiny neural networks, with MCUNet refactored into a standalone repo.

## Use cases
- run deep learning inference on microcontrollers
- train tiny neural networks for IoT devices
- memory-efficient transfer learning on edge devices
- deploy AI models on resource-constrained hardware
- augment training of small neural networks
- fit deep learning models into limited MCU memory

## When to choose
- you need memory-efficient deep learning on microcontrollers or IoT devices
- you want on-device transfer learning with minimal RAM
- you're researching efficient tiny neural network training techniques

## When to avoid
- you need general-purpose deep learning on servers or GPUs
- you want actively maintained code - MCUNet moved to a standalone repo
- you need production-ready deployment tooling rather than research code

## Facets
- artifact type: library
- maturity: maintenance
- function: machine-learning, deep-learning, llm-training
- domain: machine-learning, iot, embedded-systems, computer-vision
- platform: python, embedded, iot
- tags: tinyml, microcontrollers, model-efficiency, on-device-learning, research-code, nasa-han-lab

## Member repositories
- mit-han-lab/tinyml (main) score 32

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:04:00.128354+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 2026-08-30T06:18:05.453890+00:00, confidence not recorded.
  - readme: https://github.com/mit-han-lab/tinyml (fetched 2026-08-28T04:04:00.128354+00:00, sha da3580396ac0)
- Data as of 2026-08-30T08:39:29.467469+00:00.