What is mattwood.fyi?

A live, structured feed of riffs and links from Matt Wood, Chief AI & Technology Officer at AWS — readable by people and queryable by agents as a typed knowledge graph.

Is there an API and is it free?

Yes. A public, read-only query API is available with no authentication and no API keys. See https://mattwood.fyi/openapi.json and https://mattwood.fyi/docs.

How should an AI agent use this site?

Fetch https://mattwood.fyi/feed.json for the full structured feed, or query the API for keyword/semantic search and the connection graph. See https://mattwood.fyi/agents/ for when-to-use guidance.

Unreal Agent: Cost-Efficient AI Agent Harness

Unreal Agent is an agent harness that achieves up to 40% cost savings compared to Codex by managing tool calls asynchronously, allowing agents to respond quickly to users while reducing model overhead without sacrificing performance.

unreallabs.ai →

Connections

Develops into

Build a Custom Agent Harness Unreal Agent represents a concrete implementation of custom agent harness architecture with specific async tool call optimizations, extending the conceptual framework of building custom harnesses

Related to

SoL-Pi: Recursively Scaling Auto-Research Loops for Efficient Agent Harness Both focus on efficient agent harness design with cost/performance optimization as central themes, with SoL-Pi using recursive scaling loops and Unreal Agent using async tool management
Kiro Crew 0.6.0 Release: Remote Crews & Agent Harnesses Kiro Crew 0.6.0 also introduces agent harness infrastructure features; both items represent competing/complementary approaches to agent harness design with cost and scalability concerns
Strands Harness: Frontier Performance with 28% Lower Token Cost Both are agent harnesses explicitly focused on cost reduction through token/overhead optimization — Strands achieves 28% lower token cost while Unreal Agent claims 40% cost savings vs Codex

Supports

OpenCodex: Universal LLM Provider Proxy OpenCodex as a universal LLM provider proxy can serve as the underlying model routing layer that Unreal Agent's async cost-saving architecture would leverage for provider flexibility
Harness Engineering Paper Collection Unreal Agent provides a practical engineering case study that complements the harness engineering paper collection's theoretical and research foundations

Type:	link
First published:	Wednesday, 23 September 2026 at 07:49 UTC
Location:	https://unreallabs.ai/blog/unreal-agent/
URL:	https://mattwood.fyi/i/884e9ee4

I'm Matt Wood, and this is For Your Information. A live list of riffs and links for you and your agent, drawn from what I'm reading, noticing, questioning, concluding, and revising.

Connections