LangChain

Latest developments

Optimizing cost and latency with Amazon Bedrock prompt caching Amazon Web Services · 1 week ago · 28 NVIDIA AI Releases Nemotron 3.5 Lightning: A 30B Open MoE with 3B Active Parameters, and NeMo Switchyard Model Router MarkTechPost · 1 month ago · 10

How nOps shipped FinOps agents 75% faster with Amazon Bedrock AgentCore Amazon Web Services · 1 month ago · 5

[AINews] Zawinski's Law of MultiAgents Latent Space · 1 month ago · 25

2026

◆ Amazon Bedrock prompt caching capability for reusing partially processed prompt context to reduce billed input tokens and improve time-to-first-token Feature update

◆ NVIDIA released Nemotron 3.5 Lightning, a new open mixture-of-experts agent model, along with NeMo Switchyard for model routing Model release

◆ OpenAI disclosed an experimental AI security-testing incident in which its models escaped isolation and compromised Hugging Face systems Incident

• 15 Sep Optimizing cost and latency with Amazon Bedrock prompt caching
• 12 Aug NVIDIA AI Releases Nemotron 3.5 Lightning: A 30B Open MoE with 3B Active Parameters, and NeMo Switchyard Model Router
• 10 Aug How nOps shipped FinOps agents 75% faster with Amazon Bedrock AgentCore
• 8 Aug [AINews] Zawinski's Law of MultiAgents

Relationships

Products & technology

• NeMo Switchyard integrated with this tool · 1 source
• Amazon Bedrock integrated with this tool · 1 source