# tensorflow/tflite-micro

Infrastructure to enable deployment of ML models to low-power resource-constrained embedded targets (including microcontrollers and digital signal processors).

Repository: https://github.com/tensorflow/tflite-micro
Canonical: https://ross.abutalabs.com/products/tflite-micro
Language: C++
License: Apache-2.0
License Family: permissive
Last push: 2026-08-26T14:15:39+00:00

## Health v2 (maintenance only)
Score: 77/100 (v2, computed 2026-09-03T02:20:16.233290+00:00)
- activity 99, release rhythm 35, longevity 100
- inputs: {"age_days": 1973, "days_push": 7, "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 3059, forks 1064 (observed 2026-08-28T04:07:41.083083+00:00)

## What it is
TensorFlow Lite for Microcontrollers (TFLM) is a C++ port of TensorFlow Lite for running ML models on microcontrollers, DSPs, and other memory-constrained embedded devices. It provides a minimal inference runtime with ports for targets like Cortex-M, RISC-V, Hexagon, and Xtensa.

## Use cases
- run a neural network on an Arduino or Cortex-M microcontroller
- deploy a keyword-spotting model to a DSP
- do on-device inference with only kilobytes of RAM
- port TensorFlow Lite models to embedded targets like RISC-V or Xtensa
- build tinyml applications on resource-constrained hardware

## When to choose
- you need ML inference on microcontrollers or DSPs with very limited memory
- you want a maintained, hardware-ported runtime for embedded TensorFlow Lite models
- you are building tinyml/edge-ai applications without an OS or with minimal resources

## When to avoid
- you need training or full TensorFlow tooling on servers or desktops
- your target has ample compute and memory, where standard TensorFlow Lite or a full framework is better
- you need GPU-accelerated or cloud inference

## Facets
- artifact type: library
- maturity: active
- function: machine-learning, deep-learning, llm-inference, embedded
- domain: machine-learning, embedded-systems, deep-learning, iot
- platform: cpp, embedded, iot, cross-platform
- tags: tensorflow-lite, microcontrollers, dsp, edge-ai, tinyml, inference

## Member repositories
- tensorflow/tflite-micro (main) score 77

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:07:41.083083+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 2026-08-30T07:28:27.262451+00:00, confidence not recorded.
  - readme: https://github.com/tensorflow/tflite-micro (fetched 2026-08-28T04:07:41.083083+00:00, sha 6b9d2eaf56ea)
- Data as of 2026-08-30T08:39:29.467469+00:00.