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.

OpenCodex: Universal LLM Provider Proxy

Connections

Related to

Agentic Coding: LLM Agents, Testing, and Hallucination Risks Both concern the infrastructure of agentic coding — OpenCodex sits at the provider layer enabling LLM choice, while this item examines the risks and testing challenges of LLM-based coding agents
Trismik: Evidence-Based Model Switching Both address the problem of LLM provider flexibility — OpenCodex enables switching between providers at the proxy level, while Trismik switches models based on evidence/performance; both abstract away provider lock-in
vLLM v0.28.0 Release Both are infrastructure-layer tools for LLM deployment flexibility — vLLM provides high-performance serving while OpenCodex provides a compatibility proxy layer; together they address the LLM accessibility stack

Supports

Prompting Claude Fable 5.1 OpenCodex allows Claude to be used via OpenAI-compatible tooling, directly enabling use cases like Claude-based coding prompts through Codex infrastructure rather than switching clients
Six Months Writing Code Exclusively With AI Agents A proxy enabling any LLM with Codex CLI directly supports workflows where developers write code exclusively with AI agents, allowing them to choose preferred models without tooling constraints
Comparing 11 Different AI Models OpenCodex enables practical comparison of 11+ different AI models within the same coding workflow, making cross-model evaluation like this more actionable for developers

Muse Connector Platform OpenCodex acts as a universal proxy integrating multiple LLM providers, similar to how Muse Connector integrates third-party products into an AI agent via a connector marketplace
Codex Cloud Gains Tailscale Support Both extend LLM/coding agent infrastructure - OpenCodex as a universal proxy and Codex Cloud's Tailscale support both address the networking layer for AI coding tools
MCP-over-ACP: Stateless MCP Requests Both address protocol-level abstraction for LLM/agent infrastructure; OpenCodex as a universal provider proxy and MCP-over-ACP both define interoperability layers between AI components
Parseable: Observability Infrastructure Platform Both are infrastructure proxy/routing layers built for developer tooling — OpenCodex as a universal LLM provider proxy and Parseable as a unified telemetry ingestion and query platform, both emphasizing cost reduction

Supported by

Muse Connector Platform OpenCodex as a universal LLM provider proxy addresses similar integration/connector patterns; Muse Connector Platform extends this concept into a marketplace model with developer submissions
Mistral Large 4 OpenCodex as a universal LLM provider proxy would integrate Mistral Large 4 as one of its supported backends, directly benefiting from new frontier model availability
Unreal Agent: Cost-Efficient AI Agent Harness 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

Type:	link
First published:	Sunday, 20 September 2026 at 02:17 UTC
Location:	https://github.com/lidge-jun/opencodex
URL:	https://mattwood.fyi/i/68c90276

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