LuSaur / Technology & games
LuSaur develops software for accountable AI use and games built around athletes, competition, and original worlds.
Public technology projects / Armored combat partnership
LuSaur
Our technology work addresses how AI accesses information, supports decisions, and stays within its authority. Our games work starts with the people and competition that make an experience worth playing.
Specifications and software for source traceability, controlled access, review, and authorized use. Explore the public projects and find the right starting point for your team.
LuSaur is teaming up with an armored combat organization to create games based on its dynamic athletes. Their skill with armor, individual techniques, and competitive styles are the starting point for the experience.
LuSaur Games / Armored combat partnership
We are teaming up with an armored combat organization to develop games around its athletes. The aim is to give fans another way to engage with the competitors they follow, through play shaped by their individual strengths and styles.
Five public repositories
A governance specification for tracing how information becomes a decision or an action. GKOS defines records for sources, claims, checks, review, context, and authorized use. It gives governance and engineering teams a common structure for specifying what an AI workflow must retain and when it must stop.
A TypeScript engine, command-line tool, and local service for governed Markdown knowledge. It validates records, resolves lineage, builds graphs, and supports indexed search with citations checked against source files. Its local service applies credential-based access to knowledge views and exposes a bounded set of read-only MCP tools.
A focused command-line interface that delegates validation, indexing, assessment, search, graph creation, and export to a pinned GKOS Engine. It targets everyday note collections and human-editable metadata. Optional AI assistance produces candidate suggestions for review; it does not edit notes.
A visual knowledge application that presents folders and linked notes as an explorable astronomical map. It offers search, focused navigation, and time-based views. The standalone viewer can open a local folder offline; the Obsidian edition adds vault integration and knowledge tools.
The maintained Frozen Core edition of the Vault Kosmos line combines a 3D note viewer with readable GKX metadata. Formatting uses previewed changes and backups. It also documents a local read-only Agent API, with sensitivity settings controlling which notes can be exposed.
How we work
Identify who owns a decision, who can approve it, and what needs to be recorded.
Limit access to the task at hand. Treat missing permissions as a reason to stop.
Keep original sources and distinguish documented behavior from work still in development.
Give people clear settings, review steps, and recovery options when software changes their work.
What we are working toward
An operating foundation for agents, persistent state, and controlled execution. Marshal is the alpha development track.
A future workspace connecting source evidence, AI-assisted research, review, and reproducible records.
Simpler desktop access to local knowledge tools, with explicit permissions and review controls.
Work with LuSaur
Tell us where AI enters your workflow, what information it uses, and which decisions need oversight.