A

ai-reasoning

OpenLedger Provenance System is an append-only, event-sourced knowledge infrastructure that records how information evolves over time through verifiable chains of events, evidence, and methods. It is designed for high-trust environments such as scientific research, archaeology, legal systems, and civic data, where every claim must be traceable, reproducible, and transparently linked to its origin and reasoning. https://roxanneardary.com/openledger-provenance-system/

VeritasChain is an open specification for evidence-based causal intelligence that enables AI systems to trace the relationships between decisions, laws, economic changes, technological developments, and historical events. It provides a modular framework for understanding why outcomes occur by connecting verified evidence, long-term timelines, and explainable causal analysis across industries and institutions. https://roxanneardary.com/veritaschain/

Axis Intelligence is an open-source, modular ambient AI platform designed to function as the central intelligence layer of a modern smart home. Built with a local-first approach, it combines real-time voice interaction, AI reasoning, voice cloning, and smart home automation into a unified system that users can fully control, extend, and customize. https://roxanneardary.com/axis-intelligence/

Horizon Runtime is an AGPL-3.0+ universal AI runtime built for adaptive mixed-precision inference, reasoning models, multimodal systems, and distributed AI workloads. Designed to be hardware-agnostic and future-proof, it provides a unified execution platform for open-source AI across local devices, enterprise infrastructure, and large-scale deployments. Built Together for the Future. https://roxanneardary.com/horizon-runtime/

VeriChain is an open-source AI-powered truth verification system that analyzes public information to evaluate claims and produce probabilistic truth scores. It builds structured evidence chains by aggregating, cross-referencing, and graph-linking sources, while providing full transparency through citations, reasoning traces, and uncertainty modeling. Instead of binary fact-checking, VeriChain focuses on explainable, evidence-based likelihood assessments of truth. https://roxanneardary.com/verichain/

ThreadGraph is an open-source, AGPL-3.0+ modular agent swarm runtime that transforms complex tasks into executable, graph-structured workflows. It orchestrates multiple specialized agents, tools, and memory systems through a dynamic execution graph, enabling parallel reasoning, structured decomposition, and fully observable workflows. Designed for extensibility and composability, ThreadGraph turns agent-based systems into scalable, reproducible infrastructure rather than linear prompt chains.

Project Solstice is a layered reasoning system stack designed to transform computation into structured, verifiable cognition. It combines neural inference, symbolic reasoning, adversarial validation, and autonomous orchestration into a unified architecture that emphasizes traceability, modularity, and correctness. Rather than producing isolated outputs, it builds full reasoning pipelines that can be decomposed, verified, versioned, and improved over time.

Most LLM reasoning benchmarks come from Western math, English logic, or code. Bazi-Bench tests multi-step rule-following inference in a different formal system: traditional Chinese Ba Zi. Frozen tables, Python reference impl, gold CoT cases, all mechanically verifiable.

An interactive React application to explore and visualize Gemini chat conversations with advanced rendering, sidebar navigation, and local JSON file loading. (This is a mirror project)

Logical concept analysis MCP server - break through confused thinking with structured decomposition. Uses Wittgenstein's Tractatus method to show WHAT something is (not HOW to do it) by revealing hidden dependencies and multiplicative requirements that sequential thinking misses.