Deep Agents v0.7
Deep Agents v0.7 introduces a lightweight, configurable base harness that reduces input tokens by 65% while maintaining performance, focusing on context engineering and prompt optimization. The new harness improves token and cost efficiency, achieving reward stability across benchmarks, particularly for gpt-5.6-luna, with significant reductions in both token and cost usage. It offers full control over prompts and middleware stacks, enhancing customization and flexibility, while improving filesystem performance with optimized operations and tool enhancements.
More from Langchain
Why managed agents are the next big thing in agent building
Managed Deep Agents gives developers a managed way to build, run, and deploy Deep Agents with built-in runtime, streaming, sandboxes, evals, memory, and auth.
langchain.com··Mads Kristian Nylund·AI InfrastructureAI-agents
LangSmith BYOC on AWS is generally available
LangSmith Bring Your Own Cloud is now generally available on AWS, giving Enterprise teams managed observability, evaluation, and deployment inside their own VPC.
langchain.com··Mads Kristian Nylund·AI DevelopmentAI InfrastructureAI Platforms
What is an AI agent?
Learn what AI agents are, how they work in an LLM loop, and where workflows fit so you can build reliable, production-ready autonomous systems.
langchain.com··Mads Kristian Nylund·AI DevelopmentAI InfrastructureAI-agents