# Hironsan/anago

Bidirectional LSTM-CRF and ELMo for Named-Entity Recognition, Part-of-Speech Tagging and so on.

Repository: https://github.com/Hironsan/anago
Canonical: https://ross.abutalabs.com/products/anago
Homepage: https://anago.herokuapp.com/
Language: Python
License: MIT
License Family: permissive
Topics: natural-language-processing, machine-learning, deep-learning, named-entity-recognition, keras, sequence-labeling
Last push: 2022-12-07T23:44:31+00:00

## Health v2 (maintenance only)
Score: 23/100 (v2, computed 2026-09-03T02:20:16.233290+00:00)
- activity 0, release rhythm 8, longevity 100
- inputs: {"age_days": 3355, "days_push": 1365, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: none
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 1482, forks 359 (observed 2026-08-28T04:04:51.090578+00:00)

## What it is
anaGo is a Python library for sequence labeling tasks such as named entity recognition, part-of-speech tagging, and semantic role labeling, built on Keras with BiLSTM-CRF and ELMo support. It is language-independent, requiring no hand-crafted language-specific features, and includes pre-trained models and a simple fit/score/analyze API.

## Use cases
- extract named entities from text
- train a custom NER model in Python
- part-of-speech tagging with deep learning
- sequence labeling for any language
- semantic role labeling
- use ELMo embeddings for NER

## When to choose
- you need a Keras-based NER or POS tagging model trainable on your own data
- you want language-independent sequence labeling without feature engineering
- you want a simple high-level API with pre-trained models

## When to avoid
- you need actively maintained state-of-the-art transformer-based NER (e.g. spaCy, Hugging Face)
- you don't work in the Keras/TensorFlow ecosystem
- you need production support or recent updates

## Facets
- artifact type: library
- maturity: maintenance
- function: nlp, machine-learning, deep-learning
- domain: machine-learning, deep-learning
- platform: python
- tags: named-entity-recognition, pos-tagging, sequence-labeling, keras, elmo, lstm-crf, natural-language-processing

## Member repositories
- Hironsan/anago (main) score 23

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:04:51.090578+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 2026-08-30T04:34:04.894833+00:00, confidence not recorded.
  - readme: https://github.com/Hironsan/anago (fetched 2026-08-28T04:04:51.090578+00:00, sha 00fe0394f2bf)
  - registry_pypi: https://pypi.org/pypi/anago/json (fetched 2026-08-29T11:40:34.652758+00:00, sha 819a4368c7a8)
- Data as of 2026-08-30T08:39:29.467469+00:00.