Uncourt is a foundational open-source language model, specialized in Indian law to democratize access to legal information. It is designed to understand the nuances of the Indian legal system and s...
A Python script that anonymizes an Excel file and synthesizes new data in its place. Excel Anonymizer is a python script that helps to ensure sensitive data is properly managed and governed. It pr...
MIT-licensed Python framework providing the semantic intelligence layer that AI applications are missing — bridging raw text and trustworthy, explainable AI. Problem: Modern RAG pipelines and ag...
A Docker-powered microservice for intelligent PDF document layout analysis, OCR, and content extraction. This tool provides advanced PDF layout analysis with VGT and LightGBM models, supporting 150...
A debate-native, multi-agent AI framework for evidence-based reasoning with structured argumentation, decision-theoretic planning, and full provenance tracking. ARGUS implements the Research Debate...
Analyses design writing for structural coherence across five dimensions (claim, evidence, scope, assumptions, gaps). A fine-tuned DeBERTa model qualifies input, deterministic rules judge severity, ...
Shows structural relationships between scattered text fragments. Four orthogonal signals (embedding similarity, TF-IDF distinctiveness, VADER sentiment, lexical profile) feed six deterministic rule...
BiasClear is open-source structural persuasion detection infrastructure for the AI ecosystem. It audits text for rhetorical manipulation patterns such as manufactured consensus, authority substitut...
AI-powered civic transparency platform for Costa Rica. Uses Whisper for automatic transcription and RAG with LlamaIndex to make thousands of hours of legislative sessions searchable via natural lan...