S

semantic-search

KiM Explorer is a two-stage RAG application for transport policy research publications from the KiM Netherlands Institute for Transport Policy Analysis. Users perform semantic search to identify relevant documents, manually select publications, then interact with an LLM using full document context rather than chunks. Built with Python/NiceGUI/OpenAI API, featuring citation generation, conversation history, filtering, and web/CLI interfaces. https://explorer.kim.rijkscloud.nl/

Cognitive Orchestration Stack (COS) is an open-source, modular AI infrastructure framework designed to improve efficiency and reduce compute waste by separating reasoning from generation. Instead of relying on monolithic language model calls, COS introduces structured modules for intent understanding, semantic processing, adaptive routing, memory, and synthesis, all governed by strict schema validation through the Spec Hygiene system. The result is a system that prioritizes structured thinking, reuse of reasoning, and intelligent model selection to enable more scalable and transparent AI systems. https://roxanneardary.com/cognitive-orchestration-stack/

PublicStack AI is an open-source system that analyzes software projects and recommends full open-source repositories to enhance or replace parts of a stack. Instead of suggesting code snippets, it focuses on system-level composition—helping developers build better software by assembling proven repositories from across the open-source ecosystem, with built-in license awareness and automatic attribution tracking. https://gitlab.com/Roxanne_Ardary/publicstackai

Semantic Firewall is a zero-trust privacy layer for AI systems that transforms user prompts before they reach any large language model. It detects and redacts sensitive data locally, replaces it with deterministic tokens, and only sends abstracted semantic intent to the model. This ensures AI systems can reason over information without ever accessing raw personal, financial, or proprietary data, with full rehydration handled securely on the user’s side. https://roxanneardary.com/semantic-firewall/

SynapCache is a distributed, zero-memory-loss caching system for all LLM outputs, designed to be LLM-agnostic, high-performance, and scalable. It combines TurboQuant-style compression, semantic search, edge caching, and predictive intelligence to store and retrieve outputs efficiently, ensuring instant recall and minimal resource usage. With developer-friendly SDKs, plugin support, and multi-cloud deployment, SynapCache provides a universal neural memory layer for modern AI workflows. https://roxanneardary.com/synapcache/

PatentCortex is a modular AI-powered patent intelligence engine that converts complex vehicle and machinery patents into structured, searchable engineering data. It decomposes patents into components and systems, analyzes design strengths and weaknesses, and enables semantic search and future-ready engineering workflows across analysis, comparison, and design exploration. https://roxanneardary.com/patentcortex/

ProvenanceHub is an open-source, community-driven provenance and lineage intelligence system that tracks the origin, evolution, and transformation of digital artifacts, specifications, and ideas over time. It combines immutable provenance records, semantic search, and AI-driven lineage analysis to build a verifiable “tree of life” for software, research, and digital creation—showing not only where something came from, but how it evolved and what it became. https://roxanneardary.com/provenancehub/

🧠 Open-source persistent memory engine for AI agents and LLMs with semantic search, automatic deduplication, and intelligent context retrieval.

Semantic search for documents and transcription files inside your browser using pre-trained transformers.

Remin is a local-first semantic search engine for personal notes. It combines embeddings, ANN vector indexing (HNSW), and reranking models to retrieve information based on intent rather than keywords — fully running on-device for privacy.

Built with Rust, DuckDB (VSS), and modern embedding models.

[2025] European news intelligence platform with dual-layer AI sentiment analysis. Tracks media narrative shifts across 12 sources using VADER baseline + Gemini nuance, vector embeddings for semantic search, and interactive relationship mapping with real-time trend visualization.

🎧 Podcast Search Engine. Try it now for free or run your own instance.

https://voilib.com