Best of langgraph — July 2025

1. 1
   Article

   LangChain·40w

   Open Deep Research

   LangChain introduces an open-source deep research agent built on LangGraph that automates comprehensive research tasks. The system uses a three-phase approach: scoping (clarifying user requirements), research (using supervisor and sub-agents for parallel investigation), and writing (generating final reports). Key insights include using multi-agent architecture only for parallelizable tasks, isolating context across research topics to avoid token bloat, and implementing context engineering to manage computational costs. The agent flexibly adapts research strategies based on request complexity and is available through LangGraph Studio and Open Agent Platform.

   22
2. 2
   Video

   YouTube·40w

   Agentic AI With Langgraph And MCP Crash Course-Part 1

   A comprehensive tutorial covering the fundamentals of building agentic AI applications using LangGraph. The course demonstrates how to create basic chatbots, integrate external tools like Tavily search, implement custom functions, and manage state across graph nodes. Key concepts include understanding nodes, edges, and state management in graph-based AI workflows, with practical examples of tool binding and LLM integration for creating production-ready conversational agents.

   13
3. 3
   Article

   AI·41w

   Ebiose - open source, agent evolution framework (agents that build agents that evolve)

   Ebiose is a free, open-source framework that uses evolutionary principles to automatically generate and improve AI agents. Instead of manually crafting agents, it employs architect agents that create and refine candidate agents through survival-of-the-fittest logic. The framework features isolated execution environments called 'forges', LangGraph compatibility, persistent memory, and customizable fitness goals. Developed from research at Inria, it aims to solve scalability and adaptability issues in traditional AI agent development.

   10

   2