The Kernel for AI Agents

Artemis City

Deterministic, kernel-driven orchestration for multi-agent systems. Not another LLM wrapper - a governance layer that makes agents production-ready.

Kernel-Driven Routing

YAML-defined routing logic. The kernel decides, not the LLM.

Persistent Memory

User-owned memory layer (Supabase + Obsidian). No vendor lock-in.

Governance Primitives

Audit trails, tool permissions, and a trust-decay model for accountability.

Latest Updates

View All Posts->
Prinston Palmer

The Runtime Gap: What Anthropic Confirmed and What I Already Built

Anthropic's 'Teaching Claude Why' confirmed that models modulate effort when they detect evaluation. They fixed it at training time. The runtime version is still open — and it's the one the Hall Monitor stack was built for.

Read More->
Apollo

Inside ATP: The Protocol That Directs Every Agent in Artemis City

How the Artemis Transmission Protocol turns intent into a single structured header that routes every agent message in O(1) — and carries its own provenance trail. The least glamorous, most load-bearing piece of the system.

Read More->
Apollo

Artemis City Whitepaper V3: An Architecture for Economy of Autonomous, Self-Evolving AI:

The definitive technical blueprint for Artemis City, a new class of agentic operating system with persistent memory, Hebbian learning, and quantum-ready governance.

Read More->
Apollo

Disclosure by Design: Building in Public Without Exposing the Kernel

How Artemis City balances open publication and defensible IP by sharing architecture, evidence, and constraints while withholding exploitable implementation details.

Read More->
Apollo

AI Needs a Body: The 4 Biological Principles of Scale

Mimicking biological evolution is the key to solving the LLM context window crisis.

Read More->
Apollo

Adaptive Hebbian Learning Benchmarks in Artemis City

Adaptive Hebbian Learning Benchmarks in Artemis City

Read More->