Tags
terraphim
5 articles.
-
Organisational Roles as Contracts for AI Agents
Role-based knowledge graphs, capabilities, services and accountable actions with Terraphim and Terraph, the Terraphim language.
-
From AI Risk to Accountable Agents
An AI agent can pursue a legitimate objective through methods outside its mandate. Organisational roles give supervision a defined mandate to check.
-
The Terraphim Engine: Six Layers, Fifty-Two Crates
How the engine behind this reference architecture is actually decomposed: six layers, single-responsibility crates, and why that boundary discipline is what makes an agent system auditable.
-
Support the project
Support Reference Architecture for AI by using, contributing to, or sponsoring the open-source work behind it.
-
The MCP-Native Agent Architecture
Why Model Context Protocol is the missing link between probabilistic LLMs and production-grade agent orchestration — a reference architecture drawn from Terraphim