8 tracked signals on orchestration.
Operating Distributed Inference Systems at Scale — Nishant Gupta & Naman Ahuja, Meta
AI Engineer · Sep 19, 2026
Inference is now hyperscale infrastructure whose orchestration/control plane, not models, captures the value.
“The infence traffic already outpaces the largest microservices in the world and the rate of growth is fastest of any workload we have ever seen.”
[AINews] not much happened today
Aravind Srinivas · Latent Space Blog · Sep 18, 2026
Anthropic, Google, and others are standardizing persistent, asynchronous agent runtimes as the default UX.
“one conversation, many cloud threads”
Dynamic Subagents: How to Run Parallel Agents Reliably in Deep Agents
LangChain · Jun 29, 2026
LangChain launched dynamic subagents in Deep Agents, letting agents spawn and coordinate parallel subagents by writing code.
“So the orchestration effectively moves out of the agent's head and into code.”
AI Stack Explained in 3 Layers (LLM, Agent Harness, Omnigent)
Databricks · Jun 29, 2026
Databricks open-sourced Omnigent, a meta-harness that routes queries across multiple agent harnesses through one runner.
“So, Databricks open-sourced a fix, Omnigen. It's a meta harness. One layer that sits above every harness.”
Market surveillance agent with LangGraph and Strands on AgentCore
AWS Machine Learning Blog · Jul 28, 2026
AWS combines LangGraph and Strands on AgentCore for production multi-agent market surveillance.
Build high-performance generative AI systems with Strands Agents, NVIDIA NIM, and Amazon Bedrock AgentCore
AWS Machine Learning Blog · May 26, 2026
AWS combines NVIDIA NIM, Bedrock AgentCore, and Strands Agents for production-grade multi-agent systems
I Turned Coding Agents Into a Strategy Game — Ido Salomon, AgentCraft
AI Engineer · Sep 27, 2026
AgentCraft applies real-time strategy game mechanics to reduce human bottleneck in multi-agent orchestration
“really, we are a bottleneck”
Claude vs GPT: Live AI Debate with Omnigent
Databricks · Aug 02, 2026
OmniGen is an open source harness that orchestrates multiple AI agents to collaborate in real time.
“Instead of choosing between agents, it orchestrates them together and enables agents talk to each other, no longer living in isolation.”