Search everything

TypeScript-native validator for 13-digit South African ID numbers that checks the Luhn checksum and extracts date of birth, gender and citizenship status. Zero runtime dependencies, runs on Node, Bun, Deno and browsers.

A comprehensive Swahili (sw) stopwords collection distributed in JSON and text formats (npm/bower stopwords-sw) for text preprocessing in NLP pipelines. Maintained by the stopwords-iso project.

npm package exposing Egypt's 27 governorates and their cities in both Arabic and English via helpers like getGovernorates, getGovernoratesWithSubregions and getSubregions. Suited to address and location dropdowns.

npm package giving access to Tanzania's regions, districts, wards and streets including postcodes, with helpers like getAllRegions, getDistrictData, getWardData and getStreetsData. Built for Tanzanian address and location forms.

uroman is a universal romanizer that converts text in virtually any script to the Latin alphabet, with dedicated handling for Amharic and the Ge'ez/Ethiopic script. It also adds initial support for Coptic and processes script-native numerals.

A Node.js library for composing USSD menus using a state-machine approach, compatible with the Africa's Talking and Hubtel USSD APIs. Installed via npm install ussd-menu-builder.

A Python (PyPI) package to validate and format Nigerian phone numbers with is_valid(), formatted(), get_network() and is_mtn() helpers. Maintained by djunehor.

PHP API wrapper for Paystack that returns calls as stdClass objects, supporting transaction initialization and verification plus customer and subscription management. Installed via Composer.

Python library to validate and parse South African (RSA/ZA) identity numbers using the Luhn check digit, breaking the number into birth date, gender and citizenship components. Installable with pip install za-id-number.

Official Mono Connect JavaScript SDK that launches the Mono account-linking widget in the browser for open banking. It lets apps connect users' bank accounts and retrieve statements, transactions and identity data. Mono is a Nigerian open banking provider.

This paper introduces multilingual adaptive fine-tuning (MAFT) applied to 17 of the most-resourced African languages, producing the AfroXLMR family of models. Removing non-African-script tokens cuts model size by roughly 50 percent while matching the accuracy of single-language adaptation on named entity recognition, topic classification and sentiment analysis.

Open geodata mapping terrestrial and undersea fibre optic cable routes across Africa, digitised from operator maps into GIS format. The dataset is downloadable as CSV, SHP, KML, GeoJSON and SVG via the map portal and GitHub, and is also mirrored in the FAO data catalog. It is community-maintained by Steve Song under an open-data model.

AfriCOMET is a COMET-based machine translation evaluation model for African languages, scoring translation quality from source, hypothesis and reference triplets. The STL-1.1 version uses the afro-xlmr-large-76L encoder and was validated in the WMT 2024 Metrics Shared Task across 13 African-centric language pairs. It is released by the Masakhane community with reference-based and quality-estimation variants.

Multilingual collection of hate speech and abusive language datasets covering 15 African languages, built from tweets annotated by native speakers. Each instance carries labels from 3 to 4 annotators with anonymous annotator IDs, downloadable on HuggingFace. Published at NAACL 2025.

AfriHate is a multilingual benchmark of hate speech and abusive language datasets covering 15 African languages, annotated by native speakers. The paper contributes classification baselines and hate speech and offensive language lexicons, and analyses why keyword-based moderation fails for low-resource African languages. It was released on arXiv in January 2025.

AfriHuBERT is a compact self-supervised speech representation model based on mHuBERT-147, continually pretrained via multilingual adaptive finetuning on over 10,000 hours of speech spanning more than 1,200 African languages and varieties. It improves spoken language identification and ASR over its base model and acts as an encoder for downstream African speech tasks. Its training data was aggregated from sources including BibleTTS, Kallaama, NaijaVoices and NCHLT.

Human-translated multiple-choice question-answering evaluation benchmark covering 16 to 17 African languages plus English and French, derived from a subset of MMLU across subjects like maths, geography and law. Distributed as CSV and parquet on HuggingFace and forms part of the IrokoBench suite (MMLU, MGSM, XNLI). Licensed Apache 2.0.

AfriMT5 (afri-mt5-base) is an mT5-based machine translation model from the Masakhane community fine-tuned to translate across 16 African languages using multilingual adaptive fine-tuning. It targets news-domain translation for low-resource African languages, several of which were not previously covered by existing benchmarks. It is distributed as open weights on HuggingFace.

Open GIS map of existing and planned electricity transmission and distribution lines for all continental African countries and Madagascar, tagged by voltage (sub-kV to 700kV) and status. Four downloadable resources cover combined, existing-only and planned-only lines as GeoJSON plus a Shapefile package. Published by the World Bank on ENERGYDATA.INFO under CC BY 4.0 and last updated September 2024.

Standardised geospatial database of urban agglomerations across all 54 African countries, built from censuses, electoral registers and satellite imagery. Each urban area is a polygon with population and built-up-area attributes, available in 2015 and 2020 versions. Data is downloadable as geospatial vector files from africapolis.org under CC BY 4.0.

[ingest-scout] Suite of 10 open large language models from McGill-NLP adapted for 20–50 African languages via continued pre-training on 26–35B tokens; includes AfriqueLlama-8B, AfriqueQwen variants (4B–14B), and AfriqueGemma variants (4B–12B). Backed by ACL 2026 research paper (arXiv:2601.06395); models updated June 2026 with active downloads. Covers languages not served by registry entries (Amharic, Tigrinya, Oromo, Wolof, Bambara, Moroccan/Egyptian/Tunisian Arabic, Malagasy, Afrikaans, etc.).

Imported from a community submission, needs review.

[ingest-scout] Large-scale benchmark from McGill-NLP for evaluating large language models across African languages; covers diverse NLP tasks and language families. Active GitHub repository under the same McGill-NLP lab that produced AfriqueLLM. Complements IrokoBench (already in registry) but targets broader language coverage and LLM evaluation. Confirmed live on GitHub under McGill-NLP organisation.

Imported from a community submission, needs review.

Nationally representative public-attitude surveys on democracy, governance, the economy and society across roughly 39 African countries and nine survey rounds. Country-level and merged multi-country datasets are provided with codebooks in SPSS, Stata and CSV. Data is free to use; the most recent Round 9 covers 2021 to 2023.

[ingest-scout] Official Airtel Money developer portal covering Collections and Disbursements (payroll, refunds, cross-border transfers) across 14 African markets including Uganda, Tanzania, Kenya, Zambia, Malawi, Rwanda, Niger, DRC, Burkina Faso, and Côte d'Ivoire, using OAuth 2.0. Confirmed live via Airtel press release, API tracker (apitracker.io), and multiple independent integration guides published in 2025–2026; sandbox at openapiuat.airtel.africa.

Imported from a community submission, needs review.