Skip to main content
Reference Architecture for AI
Posts Docs
Harness Pattern
Latency < 10ns
Patterns 12 Core
Data Local Only
RA/AI
Posts Docs
Tags

agents

4 articles.

  • 8 Sep 2026

    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.

  • 8 Sep 2026

    The Twelve Core Patterns

    The twelve patterns this reference architecture is built from, grouped by the three jobs of an agent harness: context architecture, execution guardrails, and memory infrastructure.

  • 7 Sep 2026

    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

  • 6 Sep 2026

    Harness Engineering for Self-Improving Agents

    Proposed reference pattern for supervised feedback loops that make AI agent behavior measurable and improvable

Reference Architecture for AI
Production Agent Systems by Applied Knowledge Systems
Posts Docs RSS Support terraphim.ai terraphim.rs GitHub
Applied Knowledge Systems Ltd // Apache 2.0 // All data processed locally

Type at least 2 characters.