Policy-first retrieval-augmented generation gateway with PHI/PII redaction, access control, and audit logging. Self-hostable with no mandatory cloud dependencies.
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...
LLM4S is an open-source Scala-native framework for building production-grade LLM applications. Most LLM tooling today is Python-first, while many production systems in finance, telecom, data platfo...
An open source retrieval-augmented generation system that analyzes multi-language codebases using Tree-sitter, builds comprehensive knowledge graphs, and enables natural language querying and editi...
Open-source, enterprise-ready platform for benchmarking, monitoring, and managing LLM & RAG applications. Features include multi-tenant support, RBAC, structured evaluation workflows, 20+ metrics (...
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...
Async, thread-safe Node.js native bindings for Facebook FAISS. Supports FLAT_L2, FLAT_IP, IVF_FLAT, and HNSW indexes with TypeScript support and zero-copy C++ data transfer. Designed for production...
PRSense (Patch-Review Sense) is an open-source, local-first, self-hosted CLI tool for LLM-powered code review of pull request diffs. It produces high-confidence, grounded review signals that cannot...
Ogulcan Aydogan
LLM4S Foundation