A minimal graph engine for grounded AI — records, associates, and retrieves, but never invents. Written in Rust.
Agent Capability Standard is an open specification for composable AI agent capabilities. It defines 36 atomic capabilities across 9 cognitive layers, a type-safe workflow DSL, and grounded world modeling with trust-aware conflict resolution. Built on the Grounded Agency philosophy, it makes agent reliability structural—not optional.
Instruction-following vision-language model (VLM): grounded text instructions executed via multi-modal reasoning
The Autonomous, Grounded Hardware Diagnostic Engine. A multi-modal infrastructure for physical-world engineering.
C7 — A Two-Hemisphere Grounded Cognitive Architecture
Full-stack knowledge operations platform for owner-scoped notes, retrieval-ready indexing, grounded answers, and persisted evaluation workflows.
A portfolio of practical AI projects demonstrating retrieval, grounded synthesis, evaluation workflows, and production-ready AI application patterns.
A modular, reproducible Retrieval‑Augmented Generation (RAG) and Grounded AI pipeline built from scratch. Includes ingestion, token‑based chunking, YAML‑driven configs, and end‑to‑end testing. Part of a multi‑week project demonstrating production‑grade LLM system design, source governance, and grounded reasoning.
TraceRAG is a citation-first RAG system that retrieves answers at sentence-level precision with exact verbatim grounding and structured source traceability.
Add a description, image, and links to the grounded-ai topic page so that developers can more easily learn about it.
To associate your repository with the grounded-ai topic, visit your repo's landing page and select "manage topics."