🇿🇦South Africa

Zabantu is a family of XLM-RoBERTa masked language models (roughly 80M to 250M params) trained from scratch on South African Bantu languages including Tshivenda, Zulu, Xhosa, Swati, Northern and Southern Sotho, Setswana and Xitsonga. It serves as a benchmark for low-resource Bantu language NLP. It was built by the Data Science for Social Impact group at the University of Pretoria.

[ingest-scout] Keyless MCP server connecting AI agents to South African Reserve Bank (SARB) financial data via the Pipeworx gateway; last commit June 2 2026, MIT licensed. Part of the same pipeworx-io family as the tenders MCP; provides access to SARB monetary policy and financial stability data — a South Africa macroeconomic data gap in the registry.

Imported from a community submission, needs review.

[ingest-scout] Keyless MCP server providing access to South Africa's National Treasury eTenders and OCPO procurement data via the Pipeworx gateway; initial commit July 2 2026, MIT licensed. Enables AI agents to query South African government tenders in natural language — fills the South Africa government data gap in the registry.

Imported from a community submission, needs review.