LLM Router is a service that can be deployed on‑premises or in the cloud. It adds a layer between any application and the LLM provider. In real time it controls traffic, distributes a load among providers of a specific LLM, and enables analysis of outgoing requests from a security perspective (masking, anonymization, prohibited content).

llm_router_services provides HTTP services that implement the core functionality used by the LLM‑Router’s plugin system. The services expose guardrail and masking capabilities through Flask applications that can be called by the corresponding plugins in llm_router_plugins.

A companion repository for llm-router containing a collection of pipeline-ready plugins. Features a masking interface for anonymizing sensitive data and a guardrail system for validating input/output safety against defined policy rules.

Web interface for managing LLM Router configurations and text anonymization.

A modular research framework for large‑scale text analysis: it ingests heterogeneous corpora, applies multilingual preprocessing, computes dense embeddings, performs similarity‑based clustering, creates LLM‑driven abstractive summaries, and continuously updates a temporal knowledge‑graph that captures topic evolution and inter‑document relations.

radlab‑playground‑ui is a Streamlit‑based interactive playground that lets users explore information, graphs, browse generated news, interact with generative chat models, and monitor system status. All UI elements are localisation‑aware, so the interface can be presented in multiple languages with a single configuration step.

A hybrid Relational-GAT with a projection head that learns relation operators to transform embeddings, impute unseen node vectors, and expand search queries via relational paths.

Utilities and scripts to transform plWordNet into machine‑learning‑ready artifacts: build graphs, create balanced embedding datasets from lexical relations, split into train/test, and prepare indices for downstream retrieval tasks.

A collection of helper utilities and handlers designed to simplify common machine‑learning workflows.