Heidelberg AI News

Video · GitHub ·

LangChain Deep Agents

In short

The video introduces LangChain Deep Agents, an open-source framework that provides opinionated defaults and best practices for building agents with any model. It covers sub-agents, skills, memory, proactive behavior, decision models, safeguards, and cloud execution, explaining why these primitives matter for reliable long-running and personal agents.

Key points

  • Deep Agents is built on LangChain and supports any model provider.
  • Built-in primitives include sub-agents, skills, background work, and summarization.
  • Proactive agents act on environmental events instead of waiting for human prompts.
  • Memory should prioritize useful context, learn from outcomes, and eventually forget irrelevant information.
  • Agent feedback includes signals such as ignored notifications, edited drafts, and sent emails.
  • Long-running agents benefit from durable cloud execution, online evaluations, progress checks, and kill switches.

Written by an AI model from the video’s captions and description.

Deep Agents is an open source agent harness — an opinionated agent that runs out of the box. Extend, override, or replace any piece.

Watch on YouTube The opening of the article at youtube.com.

In this story

A tool or model opens in the Heidelberg AI Curriculum: what it does, what it costs, how to start. A repo opens on GitHub.

Related stories

All stories

VideoGitHub

The view from the labs: What's next for AI-assisted development

يناقش panel من Anthropic وOpenAI وGoogle Cloud وGitHub كيف تنتقل البرمجة بالذكاء الاصطناعي من المساعدة المباشرة إلى وكلاء مستقلين وأنظمة وكلاء تنفذ العمل بالكامل. تكمن القيمة القادمة في بناء أنظمة قابلة للتحقق، وتأمين هوياتها وصلاحياتها، وامتلاك الحكم البشري لتحديد ما ينبغي بناؤه ولماذا ومتى.