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.

Raven: Multi-Agent Ecosystem for Composable AI Intelligence

Raven is an open-source framework that automatically constructs and evolves modular harnesses for AI agents, enabling them to decompose complex goals, coordinate specialized agents across domains, and improve performance through shared experience. The system demonstrates superior performance on long-horizon, cross-domain tasks compared to existing agent systems.

arxiv.org →

Connections

Related to

AX: Agentic Task Execution Platform Both are agentic task execution platforms enabling complex goal decomposition and specialized agent coordination; Raven adds automatic harness evolution distinguishing it from AX's execution focus
Kiro Crew 0.6.0 Release: Remote Crews & Agent Harnesses Both address multi-agent harness orchestration with modular composition; Kiro Crew's remote crews and agent harnesses share structural goals with Raven's composable ecosystem, representing parallel approaches to the same architectural problem
Dream-RSI: Recursive Self-Improvement through Evolving Worlds Both incorporate self-evolution mechanisms for AI systems; Dream-RSI uses recursive self-improvement through world simulation while Raven automatically evolves modular harnesses, both targeting adaptive AI capability expansion
Strands Harness: Frontier Performance with 28% Lower Token Cost Both are agent harness frameworks targeting frontier AI performance; Strands Harness focuses on token cost reduction while Raven emphasizes composable multi-agent ecosystems with automatic harness construction
Unreal Agent: Cost-Efficient AI Agent Harness Both focus on AI agent harness architectures for cost-efficient orchestration; Raven's modular harness construction directly parallels Unreal Agent's harness concept, though Raven emphasizes automatic evolution and multi-agent composition

Supports

Thinking Before Thinking: Scaling Agentic Inference Through Meta-Reasoning Raven's automatic goal decomposition and agent coordination architecture operationalizes the meta-reasoning and agentic inference scaling principles described in 'Thinking Before Thinking', providing a concrete implementation of hierarchical planning

Type:	link
First published:	Friday, 2 October 2026 at 12:31 UTC
Location:	https://arxiv.org/abs/2609.33439v1
URL:	https://mattwood.fyi/i/62a5f0fa

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